CA2078423C - Method and apparatus for supplementing significant portions of a document selected without document image decoding with retrieved information - Google Patents
Method and apparatus for supplementing significant portions of a document selected without document image decoding with retrieved informationInfo
- Publication number
- CA2078423C CA2078423C CA002078423A CA2078423A CA2078423C CA 2078423 C CA2078423 C CA 2078423C CA 002078423 A CA002078423 A CA 002078423A CA 2078423 A CA2078423 A CA 2078423A CA 2078423 C CA2078423 C CA 2078423C
- Authority
- CA
- Canada
- Prior art keywords
- image
- document
- units
- image units
- significant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/268—Morphological analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/169—Annotation, e.g. comment data or footnotes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/55—Rule-based translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/416—Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
A method and apparatus for applying morphological image criteria that identify image units in an undecoded document image having significant information content, and for retrieving related data that supplements the document either from elsewhere within the document or a source external to the document. The retrieved data can result from character code, recognition or template matching of the identified significant image units, or the retrieved data can result directly from an analysis of the morpho-logical image characteristics of the identified signifi-cant image units. A reading machine can allow a user to browse and select documents or segments thereof, and to obtain interactive retrieval of documents and supplemental data.
Description
-METHOD AND APPARATUS FOR SUPPLEM~NLlNG
SIGNIFICANT PORTIONS OF A DOCUMENT SELECTED
~l'L~U'L DOCUNENT IMAGE DECODING WITH
RETRIEVED INFORMATION
BACKGROUND OF THE INVENTION
1. Cross-References to Related APPlications and Patents The following concurrently filed and related U.S.
Patent Applications are hereby cross referenced.
~ Method and Apparatus for Determining Boundaries of Words in Text" to Huttenlocher et al., U.S. Patent No.
5,321,770, issued June 14, 1994.
"A Method of Deriving Wordshapes for Subsequent Comparison" to Huttenlocher et al., Canadian application No. 2,077,969, filed September 10, 1992.
"Method and Apparatus for Determining the Frequency of Words in a Document without Document Image Decoding" to Cass et al., Canadian application No.
SIGNIFICANT PORTIONS OF A DOCUMENT SELECTED
~l'L~U'L DOCUNENT IMAGE DECODING WITH
RETRIEVED INFORMATION
BACKGROUND OF THE INVENTION
1. Cross-References to Related APPlications and Patents The following concurrently filed and related U.S.
Patent Applications are hereby cross referenced.
~ Method and Apparatus for Determining Boundaries of Words in Text" to Huttenlocher et al., U.S. Patent No.
5,321,770, issued June 14, 1994.
"A Method of Deriving Wordshapes for Subsequent Comparison" to Huttenlocher et al., Canadian application No. 2,077,969, filed September 10, 1992.
"Method and Apparatus for Determining the Frequency of Words in a Document without Document Image Decoding" to Cass et al., Canadian application No.
2,077,604, filed September 4, 1992.
"Optical Word Recognition By Ex~m;n~tion of Word Shape" to Huttenlocher et al., Canadian application No.
2,077,970, filed September 10, 1992.
"A Method and Apparatus for Image Hand Markup Detection" to Bloomberg et al., U.S. Patent No. 5,201,011, issued June 14, 1994.
2. Field of the Invention This invention relates to improvements in methods and apparatuses for electronic document processing, and more particularly to improvements in methods and appara-tuses for automatically selecting semantically significant words, characters, images, or image segments in a document image without first decoding the document or otherwise understanding the information in the document, and aug-menting the document with additional retrieved information relating to the selected words, characters, images, or image segments.
"Optical Word Recognition By Ex~m;n~tion of Word Shape" to Huttenlocher et al., Canadian application No.
2,077,970, filed September 10, 1992.
"A Method and Apparatus for Image Hand Markup Detection" to Bloomberg et al., U.S. Patent No. 5,201,011, issued June 14, 1994.
2. Field of the Invention This invention relates to improvements in methods and apparatuses for electronic document processing, and more particularly to improvements in methods and appara-tuses for automatically selecting semantically significant words, characters, images, or image segments in a document image without first decoding the document or otherwise understanding the information in the document, and aug-menting the document with additional retrieved information relating to the selected words, characters, images, or image segments.
3. References and Bac~qround one objective of computer based electronic docu-ment processing is to facilitate the user's access to and understanding of the information contained in a document or corpus of documents. However, in many cases, such as with a document in a language or form (e.g., non-Braille text for a blind user) which is foreign to the user, the user needs additional information or translation of the document in order to obtain any understanding of the document. In other cases, even after a user reaches a leY~l of underst2ndinq about a document or group of documents, the user often desires to obtain supplemental information with which to enhance the user's understand-ing. However, locating semantically significant portions of a document, or among a collection of documents, for ~Y~mple, and evaluating the relative significance of such portions can be a very arduous and time~consu~ng task.
The pro~lem of sele(~till~ t~e mos~ ~i~nificant portions of dor~l~Prlts and retrieving supplemental information related thereto is particularly difficult when dealing directly with bit mapped document images rather than with character code representations (such as ASCII for text images). In the past, perfectly recognizable scanned text has been treated as being interchangeable with electronically stored character code files, rather than as a special problem domain. However, in contrast to ASCII text files, which permit users to perform operations such as Boolean algebraic key word searches to locate text of interest, text information that is scanned without decoding is difficult to retrieve, without exhaustive viewing of each document, or without hand-crafting summaries of the documents for search purposes. Of course, document viewing or creation of document summaries requires exten-sive human effort.
Examples of retrieval techniques that rely upon locating useful te~ms in a document can be found in Salton 20784~3 and McGill, Introduction To Modern InformatiOn Retrieval, McGraw-Hill, Inc., 1983. Thus, techni~ues exist for computing key word matches, locating the most frequent noun phrases in a text, composing stop-lists of words which are not likely to be of interest to a user of an information retrieval system, and so on. Such techniques generally assume noise-free (perfectly recognizable) text.
The pro~lem of sele(~till~ t~e mos~ ~i~nificant portions of dor~l~Prlts and retrieving supplemental information related thereto is particularly difficult when dealing directly with bit mapped document images rather than with character code representations (such as ASCII for text images). In the past, perfectly recognizable scanned text has been treated as being interchangeable with electronically stored character code files, rather than as a special problem domain. However, in contrast to ASCII text files, which permit users to perform operations such as Boolean algebraic key word searches to locate text of interest, text information that is scanned without decoding is difficult to retrieve, without exhaustive viewing of each document, or without hand-crafting summaries of the documents for search purposes. Of course, document viewing or creation of document summaries requires exten-sive human effort.
Examples of retrieval techniques that rely upon locating useful te~ms in a document can be found in Salton 20784~3 and McGill, Introduction To Modern InformatiOn Retrieval, McGraw-Hill, Inc., 1983. Thus, techni~ues exist for computing key word matches, locating the most frequent noun phrases in a text, composing stop-lists of words which are not likely to be of interest to a user of an information retrieval system, and so on. Such techniques generally assume noise-free (perfectly recognizable) text.
4. References U.S. Patent No. 4,972,349 to Kleinberger describes a computerized information retrieval system and method formed of a textbase of texts of variable length and content. The texts are selected from the textbase on the basi~ of Booiean logic searches among ~ey words associated with the texts. When a group is retrieved from such a search, the system automatically segregates the texts based on the presence or absence of a criteria-key keyword selected to segregate the texts into sub-groups. The same criteria key analysis can then be applied recursively to the subgroups. The resulting subgroups are then displayed to the user in a hierarchical display to illustrate the relationships among the texts. A string comparison routine is also described to search for similar keywords.
U.S. Patent No. 4,98S,863 to Fujisawa et al.
describes a doc~lm~nt storage and retrieval system and a method of document retrieval that stores a portion of characters for outputting and also stores the document in the form of an image for retrieving. A retrieval request - for a text is made ~Ising ~ ~r~er n~ t~._ 'e~.t c, -special symbol. The dqr~l~Pnt image can then be retrieved and stored or decoded to character codes for outputting.
Character recognition is performed to recognize a retrieval key of a document before retrieval, although the actual retrieval or transf~er of the document does not require complete character recognition.
U.S. Patent No. s,010,581 to Kanno descri~es a data processing apparatus for retrieving abstract and original image data. The abstract image is an abbreviated form of the original imaqe. The apparatus includes input ~ 4 ~ 2n78423 means for inputtinq an original image; first memory means for temporarily storing the original imaqe input by the input means; drafting means for drafting an abstract image of the original image; second memory means for storing the original and abstract images; and retrieval means for retrieving the abstract image based on retrieval data corresponding to both the original and abstract image.
The second memory means stores the abstract image as a first page of the original image.
U.S. Patent No. 4,996,707 to O'Malley et al.
describes a computer system that includes a capability to receive and store graphic images from remote facsimile machines. The system includes software that can convert graphic images of textual material into an ASCII coded file so that either keywords or the converted text may be converted to speech, giving the addressee-user the ability to review incoming facsimiles from a remote telephone.
The system includes a relay capability, the capability to print on command and to originate facsimiles either from text files or scanned papers.
SUMMARY OF THE lN V~N l lON
Accordingly, it is an object of an aspect of the invention to provide an improved method and apparatus for electronic document processing wherein supplemental data is retrieved for association with the electronic document which is relevant to significant portions of the document selected without decoding of the document.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may perform retrieval operations based on morphological (structural) image characteristics of the document image to select the portions of the document on which the supplemental data retrieval is based, either with or without the supporting use of optical character recognition techniques to retrieve the supplemental data.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may be used to provide supplemental information relating to - 5 ~ 2078423 a source document to be used in reading machines for the blind.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may be used to provide translations for selected words in a source document.
In accordance with one aspect of the invention, a method for processing an undecoded document image is presented. According to the method, the document image is segmented into image units having information content without decoding of the document image. The significant image units on which the document supplementation is to be based are then identified, based solely on an evaluation of at least one morphological (structural) image charac-teristic of selected image units, or of hand-drawn docu-ment markings associated therewith. Supplemental data related to the identified significant image units are then retrieved, either with or without decoding of the identi-fied significant image units in dependence on the form of the supplemental data.
The morphological image characteristics used to identify significant image units include image unit shape dimensions, typeface, font, location in the document image and frequency of image unit occurrence. In one embodi-ment, the significant image units are identified accordingto hand-drawn graphical markings placed on the document by the user adjacent word units of interest to the user, such as encircling or underscoring.
The retrieval method may be used to retrieve, for example, foreign language translation data corresponding to the selected image units, or Braille versions of the selected image units for print out. The supplemental data may also take the form of a different mode of display, such as speech synthesized verbal output of the selected image units.
In accordance with another aspect of the inven-tion, an apparatus for retrieving data to supplement a document is presented. The apparatus includes a scanner 2078~ 23 for scanning the document image, and means for segmenting the document image into image units. Means are provided for classifying selected image units as significant image units, and means are provided for retrieving supplemental data related to the significant image units for utilization with the document. The apparatus may include a programmed digital computer to provide the means for segmenting the document image, means for classifying significant image units, and the means for retrieving supplemental data.
Other aspects of the invention are as follows:
A method for electronically processing an electronic document image, comprising:
segmenting the document image into image units without decoding the document image;
identifying significant ones of said image units in accordance with selected morphological image characteristics; and retrieving supplemental data related to the identified significant image units.
A method for translating a selected word in a text document, comprising:
marking the selected word in the document text with a hand-drawn graphical notation;
scanning the text document to produce an undecoded document image;
segmenting the document image into image segments without decoding of the document image;
evaluating the morphological image characteristics of scanned document image to identify said graphical notation;
identifying the image unit associated with said identified graphical notation;
retrieving translation data related to said identified image unit; and incorporating said retrieved translation data in said scanned document image.
, -6a- 2078423 A method for electronically processing an undecoded document image containing word text, comprising:
segmenting the document image into word image units without decoding the document image;
evaluating selected word image units according to at least one morphological image characteristic thereof without decoding the word image units to identify significant word image units;
retrieving supplemental data related to the identified significant word image units;
and outputting said retrieved supplemental data.
An apparatus for retrieving data to supplement a document, comprising:
a means for inputting the document to produce an undecoded document image;
means for segmenting the document image into image units having undecoded information content without decoding the document image;
means for evaluating selected image units according to at least one morphological image characteristic thereof to identify significant image units;
means for retrieving supplemental data related to the identified significant image units; and an output device which utilizes the retrieved supplemental data.
BRIEF DESCRIPTION OF THE DRAWINGS
A preferred embodiment of the invention is illustrated in the accompanying drawings, in which:
Figure lA is a flow chart of a first embodiment of a method of the invention.
Figure lB is a flow chart of a second embodiment of a method of the invention.
Figure 2 is a block diagram of an apparatus according to the invention for carrying out the method embodiments of either Figure lA or lB.
- 6b - 2078423 Figure 3 is an example of a text document on which selected terms have been underlined for identification and association with supplemental information, in accordance with the method embodiment of Figure lB.
Figure 4 is an example of the document of Figure 3 on which supplemental information has been associated in accordance with the method of the invention.
DET~TT-T'n DESCRIPTION OF THE PREFERRED EMBODIMENTS
In contrast to prior techniques, such as those described above, the invention is based upon the recognition that scanned image files and character code files exhibit important differences for image processing, especially in data retrieval. The method of a preferred 2078~23 embodiment of the invention capitalizes on the visual properties of text contained in paper documents, such as the presence or frequency of linguistic terms (such as words of importance like "important", "significant", "crucial", or the like) used by the author of the text to draw attention to a particular phrase or a region of the text; font and type face variations used to emphasize significant words, formatting conventions, and so on. Two preferred embodiments of the method of the invention are 10 illustrated in the flow charts of Figures lA and lB, and an apparatus for performing both methods is shown in Figure 2. For the sake of clarity, the invention will be described with reference to the processing of a single document. However, it will be appreciated that the invention is applicable to the processing of a corpus of documents containing a plurality of documents.
The invention provides a method and apparatus for retrieving data to supplement the data or text in, for example, a scanned document. However, the invention is not limited to systems utilizing document scanning.
Rather, other systems such as a bitmap workstation (i.e., a workstation with a bitmap display) or a system using both bitmapping and scanning would work equally well for the implementation of the methods and apparatus described herein.
The supplementing data may be retrieved from a wide number of sources, for example, from internal data in another portion or page of the source document, or from external data, such as an on-line data base. The retrieved data can be presented in any num~er of ways. For example, it can be presented as marginal notes on the source document, i.e., the document containing material to be supplemented, adjacent the source document portion(s) to which it pertains; printed as footnotes on the source document; printed on separate documents or in special formats (e.g., Braille); presented in a different form of display, such as a video display or synthesized voice output; or in some other appropriate manner.
2~842~
Still more particularly, in accordance with one aspect of the invention (Fig. lB), selected portions of the source document can be denoted by a user by hand-marking the source document. Due to the varied applica-tions for the invention, the marking may take variousforms. For example, a user may underline or encircle or otherwise highlight selected words to be supplemented. An example of such selection is illustrated in Figure 3, in which selected words in a text 7 have been marked by underlining 11.
The selection, on the other hand, may take a more automatic form (Fig. lA), for example, in which signifi-cant portions of the source document are targeted and automatically identified by a general purpose digital computer or the like according to one or more morphologi-cal image characteristics which are predetermined or selected by the user.
With reference first to Figure 2, the method is performed on an electronic image of an original document 5 (e.g., a bitmap image or a scanned image), which may include lines of text 7, titles, drawings, figures 8, or the like, contained in one or more sheets or pages of paper 10 or other tangible form. The electroniC document image to be processed is created in any conventional manner, for example, by an input means, sucA as an optical scanner 12 and sensor 13 as shown, a document copier machine scanner, a Braille reading machine scanner, a bitmap workstation, an electronic beam scanner or the like. Such means are well known in the art, and thus are not described in detail herein. An output derived from, for example, a scanner sensor 13 is digitized to produce undecoded bit mapped image data representing the document image for each page of the document, which data is stored, for example, in a memory 15 of a special or general purpose digital computer 16. The output from the computer 16 is delivered to an output device 17, such as, for example, a memory or other form of storage unit; an output display 17A as shown, which may be, for instance, a CRT
display; a printer device 17B as shown, which may be incorporated in a document copier machine or a Braille or standard form printeri a facsimile machine, speech synthesizer or the like.
The more automatic embodiment of the method of the invention, in which the image characteristics of selected image units are evaluated, will now be described with reference to Figure lA. The first phase of the image processing technique of the invention involves a low level document image analysis in which the document image for each page is segmented into undecoded information containing image units (step 20) using conventional image analysis techniques; or, in the case of text documents, preferably using the bounding box method described in U.S.
Patent No. 5,321,770, issued June 14, 1994 to Huttenlocher and Hopcroft, and entitled ~Method and Apparatus for Determining Boundaries of Words in Text."
Another method for finding word boxes is to close the image with a horizontal SE that joins characters but not words, followed by an operation that labels the bounding boxes of the connected image components (which in this case are words). The process can be greatly accelerated by using 1 or more threshold reductions (with threshold value 1), that have the effect both of reducing the image and of closing the spacing between the characters. The threshold reduction(s) are typically followed by a closing with a small horizontal SE. The connected component labeling operation is also done at the reduced scale, and the results are scaled up to full size.
The disadvantage of operating at reduced scale is that the word bounding boxes are only approximate; however, for many applications the accuracy is sufficient. The described method works fairly well for arbitrary text 3S fonts, but in extreme cases, such as large fixed width fonts that have large inter-character separation or small variable width fonts that have small inter-word separation, mistakes can occur. The most robust method 207842~
chooses a SE for closing based on a measurement of specific image characteristics. This requires adding the following two steps:
(l) Order the image components in the original or reduced (but not closed) image in line order, left to right and top to bottom.
(2) Build a histogram of the horizontal inter-component spacing. This histogram should naturally divide into the small inter-character spacing and the larger inter-word spacings. Then use the valley between these peaks to determine the size of SE to use for closing the image to merge characters but not join words.
Once the bounding boxes or word boxes are determined, the locations of and spatial relationships between the image units on a page can be determined (step 25). For example, an English language document image can be segmented into word image units based on the relative difference in spacing between characters within a word and the spacing between words. Sentence and paragraph boundaries can be similarly ascertained. Additional region segmentation image analysis can be performed to generate a physical document structure description that divides page images into labelled regions corresponding to auxiliary document elements li~e figures, tables, footnotes and the like. Figure regions can be distinguished from text regions based on the relative lack of image units arranged in a line within the region, for example. Using this segmentation, knowledge of how the documents being processed are arranged (e.g., left-to-right, top-to-bottom)~ and, optionally, other inputted information such as document style, a ~reading order"
sequence for word images can also be generated. The term "image unit" is thus used herein to denote an identifiable segment of an image such as a number, character, glyph, symbol, word, phrase or other unit that can be reliably extracted. Advantageously, for purposes of document review and evaluation, the document image is segmented into sets of signs, symbols or other elements, such as words, which together form a single unit of understanding.
Such single units of understanding are characterized in an image as being separated by a spacing greater than that which separates the elements forming a unit.
Advantageously, a discrimination step 30 is next performed to identify the image units which have insuffi-cient information content to be useful in evaluating the subject matter content of the document being processed.
Next, in step 40, selected image units, e.g., the image units not discriminated in step 30, are evaluated, without decoding the selected image units or reference to decoded image data, based on an evaluation of predeter-mined or selected image characteristics of the image units. The evaluation entails a determination (step 41) of the morphological image characteristics and a compari-son (step 42) of the determined image characteristics for each image unit either with the determined morphological image characteristics of the other image units or with predetermined morphological image characteristics or morphological image characteristics selected by the user.
One preferred method for defining the image unit image characteristics to be evaluated is to use the word shape derivation techniques disclosed in the copending Canadian Patent Application No 2,077,969 filed September 10, 1992, by D. Huttenlocher and M Hopcroft, and entitled "A Method for Deriving Wordshapes for Subsequent Comparison." (It should be noted that the present invention is concerned with comparing word shapes within a document and not comparing word shapes with a predetermined list of wordshapes such as a dictionary entry). As described in - 12 - ~078423 the aforesaid application, at least one, one-dimensional signal characterizing the shape of the word unit is derived; or an image function is derived defining a boundary enclosing the word unit, and the image function is augmented so that an edge function representing edges of the character string detected within the boundary is defined over its entire domain by a single independent variable within the closed boundary, without individually detecting and/or identifying the character or characters making up the word unit.
The determined morphological characteristic(s), e.g., the derived image unit shape representations, of each selected image unit are compared, as noted above (step 42), either with the determined morphological image characteristic(s) or derived image unit shape representa-tions of the other selected image units (step 42A), or with predetermined/user-selected image characteristics to locate specific types of image units (step 42B). The determined morphological image characteristics of the selected image units are advantageously compared with each other for the purpose of identifying equivalence classes of image units such that each equivalence class contains most or all of the instances of a given image unit in the document, and the relative frequencies with which image units occur in a document can be determined, as is set forth more fully in the copending Canadian Patent Application No. 2,077,604 filed September 4, 1992, Cass et al , and entitled "Method and Apparatus for Determining the Frequency of Words in a Document with Document Image Decoding." Image units can then be classified or identified as significant according to the frequency of their occurrence, as well as other characteristics of the image units, such as their length.
For example, it has been recognized that for business communications in English, a useful combination of selection criteria is to select the medium frequently word units.
2~784~3 It will be appreciated that the specification of the image characteristics for titles, headings, captions, linguistic criteria or other significance indicating visual features of a document image can be predetermined and selected by the user to determine the selection criteria defining a "significant" image unit. Comparing the image characteristics of the selected image units of the document image for matches with the image characteris-tics associated with the selection criteria permits the significant image units to be readily identified without any document decoding.
Any of a number of different methods of comparison can be used. One technique that can be used, for example, is by correlating the raster images of the extracted image units using decision networks, such technique being described for characters in a Research Report entitled "Unsupervised Construction of Decision networ~s for Pattern Classification" by Casey et al., I8M Research Report, 1984.
Preferred techniques that can be used to identify equivalence classes of word units are the word shape comparison techniques disclosed in Canadian Patent Application 2,077,970, filed September 10, 1992, Huttenlocher and Hopcroft, and entitled "Optical Word Recognition By Examination of Word Shape "
Depending on the particular application, and the relative importance of processing speed versus accuracy, for example, evaluations of different degrees of precision can be performed. For example, useful evaluations can be based on length, width and/or other measurement dimensions of the image unit (or derived image unit shape representa-tion, e.g., the largest figure in a document image); the location of the image unit in the document (including any selected figure or paragraph of a document image, e.g., headings, initial figures, one or more paragraphs or figures), font, typeface, cross-section (a cross-section being a sequence of pixels of similar state in an image unit); the number of ascenders; the number of descenders;
S the average pixel density; the length of a top line contour, including peaks and troughs; the length of a base contour, including peaks and troughs; the location of image units with respect to neighboring image units;
vertical position; horizontal inter-image unit spacing;
and combinations of such classifiers.
Referring to Figure lB, the embodiment of the method of the invention in which significant image units are selected based on user hand-drawn markings placed on the document does not require an initial document image lS segmentation step. Instead, the morphological method for identifying hand-drawn graphical markings disclosed in U.S.
Patent No. 5,201,011, issued April 6, 1993, Bloomberg, and entitled "A Method and Apparatus for Image Hand Markup Detection" is preferably utilized (step 40') to identify the regions of the document image containing the user markings. This method also permits the image units associated with the user markings to be identified.
In instances in which multiple page documents are 2S processed, each page is processed and the data held in the memory 15 (see Figure 1), as described above. The entirety of the data can then be processed.
Through use of equipment such as illustrated in Figure 2, the identified word units 11 are morphologically detected; that is, significant morphological (structural) image characteristics inherent in the image form of the word units are detected. The non-content based image recognition aspect of the invention allows image process-ing of documents to provide integral information about the documents without first converting text in the document to character codes. Data retrieval can be then provided to automatically and directly access supplemental information associated with the detected word units.
207~2~
A salient feature provided by the method of the invention is the initial processing and identification of significant word units being accomplished without an accompanying requirement that the content of the word units be decoded. More particularly, to ~his stage in the process, the actual content of the word units is not required to be specifically determined. Thus, for exam-ple, in such applications as copier machines or electronic printers that can print or reproduce images directly from one document to another without regard to ASCII or other encoding/decoding requirements, image units can be iden-tified and processed using one or more morphological image characteristics or properties of the image units. The image units of unknown content can then be further opti-cally or electronically processed. One of the advantagesthat results from the ability to perform such image unit processing without having to decode the image unit con-tents at this stage of the process is that the overall speed of image handling and manipulation can be signifi-cantly increased.
The second phase of the document analysis accord-ing to both method embodiments of the invention involves further processing (step 50) of the identified image units in connection with the supplemental data retrieval. The further processing can be accomplished using a number of different techniques, depending upon the particular application. For example, word units 11 (Figure 3) that have been identified from the scanned document may be decoded (step 52) by optical character recognition tech-niques, which techniques are well known in the art andthus are not described herein in detail. The decoded word units are then matched (step 54) with associated supple-mental data in a conventional manner. For instance, in one embodiment, the supplemental data is contained in a data base 18 (see FIG. 2) that may contain specific data pertaining to the specific decoded word units. Data base 18 may be, for example, a dictionary containing defini-tions of the decoded words, translations of foreign words, 2~7~%3 or cross-references to related documents. Alternatively, the supplemental data may be vectors or keys to particular data such as synthesized speech data, memory locations, etc.
The supplemental data is then retrieved and outputted (step 60) to an appropriate output device. In the embodiment exemplified in Figures 3 and 4, for exam-ple, the supplemental data is translated words 45 corre-sponding to the words underlined by the user. In this case, the translated words are outputted by adding them to the document image in a conventional manner so that they appear in the margin adjacent the line containing the words underlined by the user when the document image is printed or displayed, as shown in FIG. 4.
Thus, employing the method and apparatus of the invention, a "translating copier" machine, for example, may be constructed to assist a user in understanding documents written in foreign languages. Depending on the degree to which the user is familiar with the foreign language, the user may either mark difficult or unknown words in a printed copy of the document or portion thereof for translation supplementation, or enter through an appropriate user interface a request that all significant words in the document or document portion be automatically selected in accordance with either predetermined or user-selected significance criteria. The translating photo-copier then either scans the marked-up copy of the document and identifies the marked word units in accordance with the above described Figure lB method embodiment, or evaluates the image characteristics of selected word units in the scanned document image pursuant to the user's request to identify significant word units in accordance with the above described Figure lA
embodiment. The copier then retrieves the relevant translation supplemental data as described above, and prints a fresh copy of the document or document portion with translations of the underlined words in the margins opposite the underlined words, as shown in FIG. 4.
2~78423 Another application of the document supplementa-tion techni~ues of the invention is in readinq machines for the blind. One embodiment supports the designation by a user of key words, for example, on a key word list to designate likely points of interest in a document. Using the user designated key words, occurrences of the word can be found in the document of interest by OCR techniques or the like, and regions of text forward and behind the key word can be retrieved and processed using the techniques described above. Or, significant key words can be auto-matically determined using the morphological recognition techniques described above. The words thus identified as significant words or word units can then be decoded using optical character recognition techniques, for example, for retrieval of supplemental data which permits, for example, Braille versions of the significant words to be printed using a plastic-~ased ink printer associated with the reading machine. Alternatively, speech synthesized output devices can be employed to produce a voice output repre-sentation of the significant words as the supplementaldata.
Once a document has been supplemented, the user may wish to return to the original source to have printed or hear a full text rendition. This may be achieved in a number of ways. One method is for a synthesizer or printer to provide source information, for example, "on top of page 2 is an article entitled ...." The user would then return to the point of interest.
Two classes of apparatus extend this capability through providing the possibility of user interaction while the supplemental data is being communicated. One type of apparatus is a simple index marker. This can be, for instance, a hand held device with a button that the user depresses whenever he or she hears a title of inter-est, or, for instance, an N-way motion detector in a mouse 19 (Fig. 2) for registering a greater variety of commands.
The reading machine records such marks of interest and 2û78~23 returns to the original article after the supplemental data is communicated.
Another type of apparatus makes use of the tech-nology of touch-sensitive screens. Such an apparatus operates by requiring the user to lay down a Braille summarization sheet 41 on a horizontal display. The user then touches the region of interest on the screen 42 in order to trigger either a full printout or synthesized reading. The user would then indicate to the monitor when a new page was to be processed.
It will be appreciated that the method of the invention reduces the amount of material presented to the user for evaluation, and thus is capable of circumventing many problems inherent in the use of current reading technology for the blind and others, such as the problems associated with efficient browsing of a document corpus, using synthesized speech, and the problems created by the bulk and expense of producing Braille paper copies, and the time and effort required to read such copies.
The method of the invention has been described above to perform document retrieval using conventional character recognition techniques, such as OCR, in conjunc-tion with morphological identification techniques. It will be appreciated, however, that direct retrieval using only image characteristic word unit recognition techniques may be performed in the case of supplemental data which is also stored as bit mapped image data compatible with the image data of the source document to be supplemented.
Although the invention has been described and illustrated with a certain degree of particularity, it is understood that the present disclosure has been made only by way of example, and that numerous changes in the combination and arrangement of parts can be resorted to by those skilled in the art without departing from the spirit and scope of the invention, as hereinafter claimed.
U.S. Patent No. 4,98S,863 to Fujisawa et al.
describes a doc~lm~nt storage and retrieval system and a method of document retrieval that stores a portion of characters for outputting and also stores the document in the form of an image for retrieving. A retrieval request - for a text is made ~Ising ~ ~r~er n~ t~._ 'e~.t c, -special symbol. The dqr~l~Pnt image can then be retrieved and stored or decoded to character codes for outputting.
Character recognition is performed to recognize a retrieval key of a document before retrieval, although the actual retrieval or transf~er of the document does not require complete character recognition.
U.S. Patent No. s,010,581 to Kanno descri~es a data processing apparatus for retrieving abstract and original image data. The abstract image is an abbreviated form of the original imaqe. The apparatus includes input ~ 4 ~ 2n78423 means for inputtinq an original image; first memory means for temporarily storing the original imaqe input by the input means; drafting means for drafting an abstract image of the original image; second memory means for storing the original and abstract images; and retrieval means for retrieving the abstract image based on retrieval data corresponding to both the original and abstract image.
The second memory means stores the abstract image as a first page of the original image.
U.S. Patent No. 4,996,707 to O'Malley et al.
describes a computer system that includes a capability to receive and store graphic images from remote facsimile machines. The system includes software that can convert graphic images of textual material into an ASCII coded file so that either keywords or the converted text may be converted to speech, giving the addressee-user the ability to review incoming facsimiles from a remote telephone.
The system includes a relay capability, the capability to print on command and to originate facsimiles either from text files or scanned papers.
SUMMARY OF THE lN V~N l lON
Accordingly, it is an object of an aspect of the invention to provide an improved method and apparatus for electronic document processing wherein supplemental data is retrieved for association with the electronic document which is relevant to significant portions of the document selected without decoding of the document.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may perform retrieval operations based on morphological (structural) image characteristics of the document image to select the portions of the document on which the supplemental data retrieval is based, either with or without the supporting use of optical character recognition techniques to retrieve the supplemental data.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may be used to provide supplemental information relating to - 5 ~ 2078423 a source document to be used in reading machines for the blind.
It is an object of an aspect of the invention to provide a method and apparatus of the type described that may be used to provide translations for selected words in a source document.
In accordance with one aspect of the invention, a method for processing an undecoded document image is presented. According to the method, the document image is segmented into image units having information content without decoding of the document image. The significant image units on which the document supplementation is to be based are then identified, based solely on an evaluation of at least one morphological (structural) image charac-teristic of selected image units, or of hand-drawn docu-ment markings associated therewith. Supplemental data related to the identified significant image units are then retrieved, either with or without decoding of the identi-fied significant image units in dependence on the form of the supplemental data.
The morphological image characteristics used to identify significant image units include image unit shape dimensions, typeface, font, location in the document image and frequency of image unit occurrence. In one embodi-ment, the significant image units are identified accordingto hand-drawn graphical markings placed on the document by the user adjacent word units of interest to the user, such as encircling or underscoring.
The retrieval method may be used to retrieve, for example, foreign language translation data corresponding to the selected image units, or Braille versions of the selected image units for print out. The supplemental data may also take the form of a different mode of display, such as speech synthesized verbal output of the selected image units.
In accordance with another aspect of the inven-tion, an apparatus for retrieving data to supplement a document is presented. The apparatus includes a scanner 2078~ 23 for scanning the document image, and means for segmenting the document image into image units. Means are provided for classifying selected image units as significant image units, and means are provided for retrieving supplemental data related to the significant image units for utilization with the document. The apparatus may include a programmed digital computer to provide the means for segmenting the document image, means for classifying significant image units, and the means for retrieving supplemental data.
Other aspects of the invention are as follows:
A method for electronically processing an electronic document image, comprising:
segmenting the document image into image units without decoding the document image;
identifying significant ones of said image units in accordance with selected morphological image characteristics; and retrieving supplemental data related to the identified significant image units.
A method for translating a selected word in a text document, comprising:
marking the selected word in the document text with a hand-drawn graphical notation;
scanning the text document to produce an undecoded document image;
segmenting the document image into image segments without decoding of the document image;
evaluating the morphological image characteristics of scanned document image to identify said graphical notation;
identifying the image unit associated with said identified graphical notation;
retrieving translation data related to said identified image unit; and incorporating said retrieved translation data in said scanned document image.
, -6a- 2078423 A method for electronically processing an undecoded document image containing word text, comprising:
segmenting the document image into word image units without decoding the document image;
evaluating selected word image units according to at least one morphological image characteristic thereof without decoding the word image units to identify significant word image units;
retrieving supplemental data related to the identified significant word image units;
and outputting said retrieved supplemental data.
An apparatus for retrieving data to supplement a document, comprising:
a means for inputting the document to produce an undecoded document image;
means for segmenting the document image into image units having undecoded information content without decoding the document image;
means for evaluating selected image units according to at least one morphological image characteristic thereof to identify significant image units;
means for retrieving supplemental data related to the identified significant image units; and an output device which utilizes the retrieved supplemental data.
BRIEF DESCRIPTION OF THE DRAWINGS
A preferred embodiment of the invention is illustrated in the accompanying drawings, in which:
Figure lA is a flow chart of a first embodiment of a method of the invention.
Figure lB is a flow chart of a second embodiment of a method of the invention.
Figure 2 is a block diagram of an apparatus according to the invention for carrying out the method embodiments of either Figure lA or lB.
- 6b - 2078423 Figure 3 is an example of a text document on which selected terms have been underlined for identification and association with supplemental information, in accordance with the method embodiment of Figure lB.
Figure 4 is an example of the document of Figure 3 on which supplemental information has been associated in accordance with the method of the invention.
DET~TT-T'n DESCRIPTION OF THE PREFERRED EMBODIMENTS
In contrast to prior techniques, such as those described above, the invention is based upon the recognition that scanned image files and character code files exhibit important differences for image processing, especially in data retrieval. The method of a preferred 2078~23 embodiment of the invention capitalizes on the visual properties of text contained in paper documents, such as the presence or frequency of linguistic terms (such as words of importance like "important", "significant", "crucial", or the like) used by the author of the text to draw attention to a particular phrase or a region of the text; font and type face variations used to emphasize significant words, formatting conventions, and so on. Two preferred embodiments of the method of the invention are 10 illustrated in the flow charts of Figures lA and lB, and an apparatus for performing both methods is shown in Figure 2. For the sake of clarity, the invention will be described with reference to the processing of a single document. However, it will be appreciated that the invention is applicable to the processing of a corpus of documents containing a plurality of documents.
The invention provides a method and apparatus for retrieving data to supplement the data or text in, for example, a scanned document. However, the invention is not limited to systems utilizing document scanning.
Rather, other systems such as a bitmap workstation (i.e., a workstation with a bitmap display) or a system using both bitmapping and scanning would work equally well for the implementation of the methods and apparatus described herein.
The supplementing data may be retrieved from a wide number of sources, for example, from internal data in another portion or page of the source document, or from external data, such as an on-line data base. The retrieved data can be presented in any num~er of ways. For example, it can be presented as marginal notes on the source document, i.e., the document containing material to be supplemented, adjacent the source document portion(s) to which it pertains; printed as footnotes on the source document; printed on separate documents or in special formats (e.g., Braille); presented in a different form of display, such as a video display or synthesized voice output; or in some other appropriate manner.
2~842~
Still more particularly, in accordance with one aspect of the invention (Fig. lB), selected portions of the source document can be denoted by a user by hand-marking the source document. Due to the varied applica-tions for the invention, the marking may take variousforms. For example, a user may underline or encircle or otherwise highlight selected words to be supplemented. An example of such selection is illustrated in Figure 3, in which selected words in a text 7 have been marked by underlining 11.
The selection, on the other hand, may take a more automatic form (Fig. lA), for example, in which signifi-cant portions of the source document are targeted and automatically identified by a general purpose digital computer or the like according to one or more morphologi-cal image characteristics which are predetermined or selected by the user.
With reference first to Figure 2, the method is performed on an electronic image of an original document 5 (e.g., a bitmap image or a scanned image), which may include lines of text 7, titles, drawings, figures 8, or the like, contained in one or more sheets or pages of paper 10 or other tangible form. The electroniC document image to be processed is created in any conventional manner, for example, by an input means, sucA as an optical scanner 12 and sensor 13 as shown, a document copier machine scanner, a Braille reading machine scanner, a bitmap workstation, an electronic beam scanner or the like. Such means are well known in the art, and thus are not described in detail herein. An output derived from, for example, a scanner sensor 13 is digitized to produce undecoded bit mapped image data representing the document image for each page of the document, which data is stored, for example, in a memory 15 of a special or general purpose digital computer 16. The output from the computer 16 is delivered to an output device 17, such as, for example, a memory or other form of storage unit; an output display 17A as shown, which may be, for instance, a CRT
display; a printer device 17B as shown, which may be incorporated in a document copier machine or a Braille or standard form printeri a facsimile machine, speech synthesizer or the like.
The more automatic embodiment of the method of the invention, in which the image characteristics of selected image units are evaluated, will now be described with reference to Figure lA. The first phase of the image processing technique of the invention involves a low level document image analysis in which the document image for each page is segmented into undecoded information containing image units (step 20) using conventional image analysis techniques; or, in the case of text documents, preferably using the bounding box method described in U.S.
Patent No. 5,321,770, issued June 14, 1994 to Huttenlocher and Hopcroft, and entitled ~Method and Apparatus for Determining Boundaries of Words in Text."
Another method for finding word boxes is to close the image with a horizontal SE that joins characters but not words, followed by an operation that labels the bounding boxes of the connected image components (which in this case are words). The process can be greatly accelerated by using 1 or more threshold reductions (with threshold value 1), that have the effect both of reducing the image and of closing the spacing between the characters. The threshold reduction(s) are typically followed by a closing with a small horizontal SE. The connected component labeling operation is also done at the reduced scale, and the results are scaled up to full size.
The disadvantage of operating at reduced scale is that the word bounding boxes are only approximate; however, for many applications the accuracy is sufficient. The described method works fairly well for arbitrary text 3S fonts, but in extreme cases, such as large fixed width fonts that have large inter-character separation or small variable width fonts that have small inter-word separation, mistakes can occur. The most robust method 207842~
chooses a SE for closing based on a measurement of specific image characteristics. This requires adding the following two steps:
(l) Order the image components in the original or reduced (but not closed) image in line order, left to right and top to bottom.
(2) Build a histogram of the horizontal inter-component spacing. This histogram should naturally divide into the small inter-character spacing and the larger inter-word spacings. Then use the valley between these peaks to determine the size of SE to use for closing the image to merge characters but not join words.
Once the bounding boxes or word boxes are determined, the locations of and spatial relationships between the image units on a page can be determined (step 25). For example, an English language document image can be segmented into word image units based on the relative difference in spacing between characters within a word and the spacing between words. Sentence and paragraph boundaries can be similarly ascertained. Additional region segmentation image analysis can be performed to generate a physical document structure description that divides page images into labelled regions corresponding to auxiliary document elements li~e figures, tables, footnotes and the like. Figure regions can be distinguished from text regions based on the relative lack of image units arranged in a line within the region, for example. Using this segmentation, knowledge of how the documents being processed are arranged (e.g., left-to-right, top-to-bottom)~ and, optionally, other inputted information such as document style, a ~reading order"
sequence for word images can also be generated. The term "image unit" is thus used herein to denote an identifiable segment of an image such as a number, character, glyph, symbol, word, phrase or other unit that can be reliably extracted. Advantageously, for purposes of document review and evaluation, the document image is segmented into sets of signs, symbols or other elements, such as words, which together form a single unit of understanding.
Such single units of understanding are characterized in an image as being separated by a spacing greater than that which separates the elements forming a unit.
Advantageously, a discrimination step 30 is next performed to identify the image units which have insuffi-cient information content to be useful in evaluating the subject matter content of the document being processed.
Next, in step 40, selected image units, e.g., the image units not discriminated in step 30, are evaluated, without decoding the selected image units or reference to decoded image data, based on an evaluation of predeter-mined or selected image characteristics of the image units. The evaluation entails a determination (step 41) of the morphological image characteristics and a compari-son (step 42) of the determined image characteristics for each image unit either with the determined morphological image characteristics of the other image units or with predetermined morphological image characteristics or morphological image characteristics selected by the user.
One preferred method for defining the image unit image characteristics to be evaluated is to use the word shape derivation techniques disclosed in the copending Canadian Patent Application No 2,077,969 filed September 10, 1992, by D. Huttenlocher and M Hopcroft, and entitled "A Method for Deriving Wordshapes for Subsequent Comparison." (It should be noted that the present invention is concerned with comparing word shapes within a document and not comparing word shapes with a predetermined list of wordshapes such as a dictionary entry). As described in - 12 - ~078423 the aforesaid application, at least one, one-dimensional signal characterizing the shape of the word unit is derived; or an image function is derived defining a boundary enclosing the word unit, and the image function is augmented so that an edge function representing edges of the character string detected within the boundary is defined over its entire domain by a single independent variable within the closed boundary, without individually detecting and/or identifying the character or characters making up the word unit.
The determined morphological characteristic(s), e.g., the derived image unit shape representations, of each selected image unit are compared, as noted above (step 42), either with the determined morphological image characteristic(s) or derived image unit shape representa-tions of the other selected image units (step 42A), or with predetermined/user-selected image characteristics to locate specific types of image units (step 42B). The determined morphological image characteristics of the selected image units are advantageously compared with each other for the purpose of identifying equivalence classes of image units such that each equivalence class contains most or all of the instances of a given image unit in the document, and the relative frequencies with which image units occur in a document can be determined, as is set forth more fully in the copending Canadian Patent Application No. 2,077,604 filed September 4, 1992, Cass et al , and entitled "Method and Apparatus for Determining the Frequency of Words in a Document with Document Image Decoding." Image units can then be classified or identified as significant according to the frequency of their occurrence, as well as other characteristics of the image units, such as their length.
For example, it has been recognized that for business communications in English, a useful combination of selection criteria is to select the medium frequently word units.
2~784~3 It will be appreciated that the specification of the image characteristics for titles, headings, captions, linguistic criteria or other significance indicating visual features of a document image can be predetermined and selected by the user to determine the selection criteria defining a "significant" image unit. Comparing the image characteristics of the selected image units of the document image for matches with the image characteris-tics associated with the selection criteria permits the significant image units to be readily identified without any document decoding.
Any of a number of different methods of comparison can be used. One technique that can be used, for example, is by correlating the raster images of the extracted image units using decision networks, such technique being described for characters in a Research Report entitled "Unsupervised Construction of Decision networ~s for Pattern Classification" by Casey et al., I8M Research Report, 1984.
Preferred techniques that can be used to identify equivalence classes of word units are the word shape comparison techniques disclosed in Canadian Patent Application 2,077,970, filed September 10, 1992, Huttenlocher and Hopcroft, and entitled "Optical Word Recognition By Examination of Word Shape "
Depending on the particular application, and the relative importance of processing speed versus accuracy, for example, evaluations of different degrees of precision can be performed. For example, useful evaluations can be based on length, width and/or other measurement dimensions of the image unit (or derived image unit shape representa-tion, e.g., the largest figure in a document image); the location of the image unit in the document (including any selected figure or paragraph of a document image, e.g., headings, initial figures, one or more paragraphs or figures), font, typeface, cross-section (a cross-section being a sequence of pixels of similar state in an image unit); the number of ascenders; the number of descenders;
S the average pixel density; the length of a top line contour, including peaks and troughs; the length of a base contour, including peaks and troughs; the location of image units with respect to neighboring image units;
vertical position; horizontal inter-image unit spacing;
and combinations of such classifiers.
Referring to Figure lB, the embodiment of the method of the invention in which significant image units are selected based on user hand-drawn markings placed on the document does not require an initial document image lS segmentation step. Instead, the morphological method for identifying hand-drawn graphical markings disclosed in U.S.
Patent No. 5,201,011, issued April 6, 1993, Bloomberg, and entitled "A Method and Apparatus for Image Hand Markup Detection" is preferably utilized (step 40') to identify the regions of the document image containing the user markings. This method also permits the image units associated with the user markings to be identified.
In instances in which multiple page documents are 2S processed, each page is processed and the data held in the memory 15 (see Figure 1), as described above. The entirety of the data can then be processed.
Through use of equipment such as illustrated in Figure 2, the identified word units 11 are morphologically detected; that is, significant morphological (structural) image characteristics inherent in the image form of the word units are detected. The non-content based image recognition aspect of the invention allows image process-ing of documents to provide integral information about the documents without first converting text in the document to character codes. Data retrieval can be then provided to automatically and directly access supplemental information associated with the detected word units.
207~2~
A salient feature provided by the method of the invention is the initial processing and identification of significant word units being accomplished without an accompanying requirement that the content of the word units be decoded. More particularly, to ~his stage in the process, the actual content of the word units is not required to be specifically determined. Thus, for exam-ple, in such applications as copier machines or electronic printers that can print or reproduce images directly from one document to another without regard to ASCII or other encoding/decoding requirements, image units can be iden-tified and processed using one or more morphological image characteristics or properties of the image units. The image units of unknown content can then be further opti-cally or electronically processed. One of the advantagesthat results from the ability to perform such image unit processing without having to decode the image unit con-tents at this stage of the process is that the overall speed of image handling and manipulation can be signifi-cantly increased.
The second phase of the document analysis accord-ing to both method embodiments of the invention involves further processing (step 50) of the identified image units in connection with the supplemental data retrieval. The further processing can be accomplished using a number of different techniques, depending upon the particular application. For example, word units 11 (Figure 3) that have been identified from the scanned document may be decoded (step 52) by optical character recognition tech-niques, which techniques are well known in the art andthus are not described herein in detail. The decoded word units are then matched (step 54) with associated supple-mental data in a conventional manner. For instance, in one embodiment, the supplemental data is contained in a data base 18 (see FIG. 2) that may contain specific data pertaining to the specific decoded word units. Data base 18 may be, for example, a dictionary containing defini-tions of the decoded words, translations of foreign words, 2~7~%3 or cross-references to related documents. Alternatively, the supplemental data may be vectors or keys to particular data such as synthesized speech data, memory locations, etc.
The supplemental data is then retrieved and outputted (step 60) to an appropriate output device. In the embodiment exemplified in Figures 3 and 4, for exam-ple, the supplemental data is translated words 45 corre-sponding to the words underlined by the user. In this case, the translated words are outputted by adding them to the document image in a conventional manner so that they appear in the margin adjacent the line containing the words underlined by the user when the document image is printed or displayed, as shown in FIG. 4.
Thus, employing the method and apparatus of the invention, a "translating copier" machine, for example, may be constructed to assist a user in understanding documents written in foreign languages. Depending on the degree to which the user is familiar with the foreign language, the user may either mark difficult or unknown words in a printed copy of the document or portion thereof for translation supplementation, or enter through an appropriate user interface a request that all significant words in the document or document portion be automatically selected in accordance with either predetermined or user-selected significance criteria. The translating photo-copier then either scans the marked-up copy of the document and identifies the marked word units in accordance with the above described Figure lB method embodiment, or evaluates the image characteristics of selected word units in the scanned document image pursuant to the user's request to identify significant word units in accordance with the above described Figure lA
embodiment. The copier then retrieves the relevant translation supplemental data as described above, and prints a fresh copy of the document or document portion with translations of the underlined words in the margins opposite the underlined words, as shown in FIG. 4.
2~78423 Another application of the document supplementa-tion techni~ues of the invention is in readinq machines for the blind. One embodiment supports the designation by a user of key words, for example, on a key word list to designate likely points of interest in a document. Using the user designated key words, occurrences of the word can be found in the document of interest by OCR techniques or the like, and regions of text forward and behind the key word can be retrieved and processed using the techniques described above. Or, significant key words can be auto-matically determined using the morphological recognition techniques described above. The words thus identified as significant words or word units can then be decoded using optical character recognition techniques, for example, for retrieval of supplemental data which permits, for example, Braille versions of the significant words to be printed using a plastic-~ased ink printer associated with the reading machine. Alternatively, speech synthesized output devices can be employed to produce a voice output repre-sentation of the significant words as the supplementaldata.
Once a document has been supplemented, the user may wish to return to the original source to have printed or hear a full text rendition. This may be achieved in a number of ways. One method is for a synthesizer or printer to provide source information, for example, "on top of page 2 is an article entitled ...." The user would then return to the point of interest.
Two classes of apparatus extend this capability through providing the possibility of user interaction while the supplemental data is being communicated. One type of apparatus is a simple index marker. This can be, for instance, a hand held device with a button that the user depresses whenever he or she hears a title of inter-est, or, for instance, an N-way motion detector in a mouse 19 (Fig. 2) for registering a greater variety of commands.
The reading machine records such marks of interest and 2û78~23 returns to the original article after the supplemental data is communicated.
Another type of apparatus makes use of the tech-nology of touch-sensitive screens. Such an apparatus operates by requiring the user to lay down a Braille summarization sheet 41 on a horizontal display. The user then touches the region of interest on the screen 42 in order to trigger either a full printout or synthesized reading. The user would then indicate to the monitor when a new page was to be processed.
It will be appreciated that the method of the invention reduces the amount of material presented to the user for evaluation, and thus is capable of circumventing many problems inherent in the use of current reading technology for the blind and others, such as the problems associated with efficient browsing of a document corpus, using synthesized speech, and the problems created by the bulk and expense of producing Braille paper copies, and the time and effort required to read such copies.
The method of the invention has been described above to perform document retrieval using conventional character recognition techniques, such as OCR, in conjunc-tion with morphological identification techniques. It will be appreciated, however, that direct retrieval using only image characteristic word unit recognition techniques may be performed in the case of supplemental data which is also stored as bit mapped image data compatible with the image data of the source document to be supplemented.
Although the invention has been described and illustrated with a certain degree of particularity, it is understood that the present disclosure has been made only by way of example, and that numerous changes in the combination and arrangement of parts can be resorted to by those skilled in the art without departing from the spirit and scope of the invention, as hereinafter claimed.
Claims (24)
1. A method for electronically processing an electronic document image, comprising:
segmenting the document image into image units without decoding the document image;
identifying significant ones of said image units in accordance with selected morphological image characteristics; and retrieving supplemental data related to the identified significant image units.
segmenting the document image into image units without decoding the document image;
identifying significant ones of said image units in accordance with selected morphological image characteristics; and retrieving supplemental data related to the identified significant image units.
2. The method of claim 1 wherein said step of identifying significant image units comprises classifying said image units according to frequency of occurrence.
3. The method of claim 1 wherein said step of identifying significant image units comprises classifying said image units according to location within the document image.
4. The method of claim 1 wherein said selected morphological image characteristics include image charac-teristics defining image units having predetermined linguistic criteria.
5. The method of claim 1 wherein said selected morphological image characteristics include at least one of an image unit shape dimension, font, typeface, number of ascender elements, number of descender elements, pixel density, pixel cross-sectional characteristic, the location of image units with respect to neighboring image units, vertical position, horizontal inter-image unit spacing, and contour characteristic of said image units.
6. The method of claim 1 wherein said step of identifying significant image units comprises identifying image units having an associated hand-drawn marking created by a user.
7. The method of claim 1 wherein said step of retrieving supplemental data comprises retrieving foreign language data corresponding to said identified significant image units.
8. The method of claim 1 wherein said step of retrieving supplemental data comprises retrieving data from within the document.
9. The method of claim 1 wherein said step of retrieving supplemental data comprises retrieving data external to the document.
10. The method of claim 1 further comprising modifying the document image with retrieved data to provide a document annotation.
11. The method of claim 10 wherein the document annotation is in the form of marginal notes.
12. The method of claim l wherein said step of retrieving supplemental data retrieves Braille versions of the identified significant image units.
13. The method of claim 12 further comprising outputting said retrieved Braille versions of the identi-fied significant image units in printed form.
14. The method of claim 3 wherein said step of retrieving supplemental data for the document comprises retrieving synthesized speech versions of the identified significant image units.
15. A method for translating a selected word in a text document, comprising:
marking the selected word in the document text with a hand-drawn graphical notation;
scanning the text document to produce an undecoded document image;
segmenting the document image into image segments without decoding of the document image;
evaluating the morphological image character-istics of scanned document image to identify said graphi-cal notation;
identifying the image unit associated with said identified graphical notation;
retrieving translation data related to said identified image unit; and incorporating said retrieved translation data in said scanned document image.
marking the selected word in the document text with a hand-drawn graphical notation;
scanning the text document to produce an undecoded document image;
segmenting the document image into image segments without decoding of the document image;
evaluating the morphological image character-istics of scanned document image to identify said graphi-cal notation;
identifying the image unit associated with said identified graphical notation;
retrieving translation data related to said identified image unit; and incorporating said retrieved translation data in said scanned document image.
16. The method of claim 15 wherein said retriev-ing step includes decoding the identified image unit and matching the decoded image unit with decoded data entries in a dictionary database.
17. A method for electronically processing an undecoded document image containing word text, comprising:
segmenting the document image into word image units without decoding the document image;
evaluating selected word image units accord-ing to at least one morphological image characteristic thereof without decoding the word image units to identify significant word image units;
retrieving supplemental data related to the identified significant word image units;
and outputting said retrieved supplemental data.
segmenting the document image into word image units without decoding the document image;
evaluating selected word image units accord-ing to at least one morphological image characteristic thereof without decoding the word image units to identify significant word image units;
retrieving supplemental data related to the identified significant word image units;
and outputting said retrieved supplemental data.
18. An apparatus for retrieving data to supple-ment a document, comprising:
a means for inputting the document to produce an undecoded document image;
means for segmenting the document image into image units having undecoded information content without decoding the document image;
means for evaluating selected image units according to at least one morphological image characteris-tic thereof to identify significant image units, means for retrieving supplemental data related to the identified significant image units; and an output device which utilizes the retrieved supplemental data.
a means for inputting the document to produce an undecoded document image;
means for segmenting the document image into image units having undecoded information content without decoding the document image;
means for evaluating selected image units according to at least one morphological image characteris-tic thereof to identify significant image units, means for retrieving supplemental data related to the identified significant image units; and an output device which utilizes the retrieved supplemental data.
19. The apparatus of claim 18 wherein said means for segmenting the document image, said means for identi-fying significant word units, and said means for retriev-ing supplemental data comprise a programmed digital computer.
20. The apparatus of claim 18 wherein said input means and output device are part of a copier machine in which said output device produces printed document copies;
and said apparatus comprises means for incorporating said retrieved supplemental data into a document image for printing as part of a printed document copy.
and said apparatus comprises means for incorporating said retrieved supplemental data into a document image for printing as part of a printed document copy.
21. The apparatus of claim 20 wherein said retrieved supplemental data is translation data.
22. The apparatus of claim 18 wherein said input means and output device are part of a Braille reading machine in which said output device produces an output intelligible to a blind user.
23. The apparatus of claim 22 wherein said output device is a Braille printer for producing document copies in Braille format.
24. The apparatus of claim 22 wherein said output device is a speech synthesizer for producing synthesized speech output corresponding to said identified significant image units.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US79541991A | 1991-11-19 | 1991-11-19 | |
| US795,419 | 1991-11-19 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CA2078423A1 CA2078423A1 (en) | 1993-05-20 |
| CA2078423C true CA2078423C (en) | 1997-01-14 |
Family
ID=25165475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002078423A Expired - Fee Related CA2078423C (en) | 1991-11-19 | 1992-09-16 | Method and apparatus for supplementing significant portions of a document selected without document image decoding with retrieved information |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US5748805A (en) |
| EP (1) | EP0544434B1 (en) |
| JP (1) | JP3289968B2 (en) |
| CA (1) | CA2078423C (en) |
| DE (1) | DE69226611T2 (en) |
Families Citing this family (133)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5903454A (en) | 1991-12-23 | 1999-05-11 | Hoffberg; Linda Irene | Human-factored interface corporating adaptive pattern recognition based controller apparatus |
| US6418424B1 (en) | 1991-12-23 | 2002-07-09 | Steven M. Hoffberg | Ergonomic man-machine interface incorporating adaptive pattern recognition based control system |
| US6850252B1 (en) | 1999-10-05 | 2005-02-01 | Steven M. Hoffberg | Intelligent electronic appliance system and method |
| US10361802B1 (en) | 1999-02-01 | 2019-07-23 | Blanding Hovenweep, Llc | Adaptive pattern recognition based control system and method |
| US6400996B1 (en) | 1999-02-01 | 2002-06-04 | Steven M. Hoffberg | Adaptive pattern recognition based control system and method |
| US8352400B2 (en) | 1991-12-23 | 2013-01-08 | Hoffberg Steven M | Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore |
| JP3039204B2 (en) * | 1993-06-02 | 2000-05-08 | キヤノン株式会社 | Document processing method and apparatus |
| US5857038A (en) * | 1993-06-29 | 1999-01-05 | Canon Kabushiki Kaisha | Image processing apparatus and method for synthesizing first and second image data |
| US5867597A (en) * | 1995-09-05 | 1999-02-02 | Ricoh Corporation | High-speed retrieval by example |
| US6104833A (en) * | 1996-01-09 | 2000-08-15 | Fujitsu Limited | Pattern recognizing apparatus and method |
| JPH11110480A (en) * | 1997-07-25 | 1999-04-23 | Kuraritec Corp | Method and device for displaying text |
| US6910184B1 (en) | 1997-07-25 | 2005-06-21 | Ricoh Company, Ltd. | Document information management system |
| US6356922B1 (en) * | 1997-09-15 | 2002-03-12 | Fuji Xerox Co., Ltd. | Method and system for suggesting related documents |
| US6658623B1 (en) * | 1997-09-15 | 2003-12-02 | Fuji Xerox Co., Ltd. | Displaying in a first document a selectable link to a second document based on a passive query |
| US7596755B2 (en) * | 1997-12-22 | 2009-09-29 | Ricoh Company, Ltd. | Multimedia visualization and integration environment |
| US20080028292A1 (en) * | 1997-12-22 | 2008-01-31 | Ricoh Company, Ltd. | Techniques to facilitate reading of a document |
| US7954056B2 (en) | 1997-12-22 | 2011-05-31 | Ricoh Company, Ltd. | Television-based visualization and navigation interface |
| US7124093B1 (en) | 1997-12-22 | 2006-10-17 | Ricoh Company, Ltd. | Method, system and computer code for content based web advertising |
| JP4183311B2 (en) | 1997-12-22 | 2008-11-19 | 株式会社リコー | Document annotation method, annotation device, and recording medium |
| US7263659B2 (en) | 1998-09-09 | 2007-08-28 | Ricoh Company, Ltd. | Paper-based interface for multimedia information |
| US7257589B1 (en) * | 1997-12-22 | 2007-08-14 | Ricoh Company, Ltd. | Techniques for targeting information to users |
| GB9727322D0 (en) * | 1997-12-29 | 1998-02-25 | Xerox Corp | Multilingual information retrieval |
| US6064767A (en) * | 1998-01-16 | 2000-05-16 | Regents Of The University Of California | Automatic language identification by stroke geometry analysis |
| GB9806085D0 (en) | 1998-03-23 | 1998-05-20 | Xerox Corp | Text summarisation using light syntactic parsing |
| FR2778476B1 (en) * | 1998-05-07 | 2000-06-16 | France Telecom | PROCESS FOR SEGMENTATION AND RECOGNITION OF A DOCUMENT, ESPECIALLY FROM A TECHNICAL PLAN |
| JP4286345B2 (en) | 1998-05-08 | 2009-06-24 | 株式会社リコー | Search support system and computer-readable recording medium |
| US7263671B2 (en) * | 1998-09-09 | 2007-08-28 | Ricoh Company, Ltd. | Techniques for annotating multimedia information |
| US6582475B2 (en) | 1998-09-09 | 2003-06-24 | Ricoh Company Limited | Automatic adaptive document printing help system |
| US6369811B1 (en) | 1998-09-09 | 2002-04-09 | Ricoh Company Limited | Automatic adaptive document help for paper documents |
| US7215436B2 (en) * | 1998-09-09 | 2007-05-08 | Ricoh Company, Ltd. | Device for generating a multimedia paper document |
| US7266782B2 (en) * | 1998-09-09 | 2007-09-04 | Ricoh Company, Ltd. | Techniques for generating a coversheet for a paper-based interface for multimedia information |
| JP2000101853A (en) * | 1998-09-21 | 2000-04-07 | Fuji Photo Film Co Ltd | Image encryption method, image encryption device, recording medium recorded with procedure of image encryption, and recording medium recorded with image file for encrypted image |
| US6269189B1 (en) | 1998-12-29 | 2001-07-31 | Xerox Corporation | Finding selected character strings in text and providing information relating to the selected character strings |
| US7904187B2 (en) | 1999-02-01 | 2011-03-08 | Hoffberg Steven M | Internet appliance system and method |
| US6565611B1 (en) * | 1999-02-26 | 2003-05-20 | Xerox Corporation | Automatic index creation for handwritten digital ink notes |
| US6282540B1 (en) * | 1999-02-26 | 2001-08-28 | Vicinity Corporation | Method and apparatus for efficient proximity searching |
| US6310633B1 (en) * | 1999-03-23 | 2001-10-30 | Ricoh Company Limited | Method and system for organizing document information |
| US6473730B1 (en) * | 1999-04-12 | 2002-10-29 | The Trustees Of Columbia University In The City Of New York | Method and system for topical segmentation, segment significance and segment function |
| US6647534B1 (en) | 1999-06-30 | 2003-11-11 | Ricoh Company Limited | Method and system for organizing document information in a non-directed arrangement of documents |
| US7228492B1 (en) * | 1999-07-06 | 2007-06-05 | Ricoh Company, Ltd. | 2D graph displaying document locations of user-specified concept of interest |
| DE19941123A1 (en) * | 1999-08-25 | 2001-03-08 | Only Solutions Ges Fuer Softwa | Digital image processing system |
| WO2001058075A2 (en) * | 2000-02-03 | 2001-08-09 | Xmpie Inc. | System and method for production of dynamic documents utilizing a page description language |
| US20020049702A1 (en) * | 2000-02-03 | 2002-04-25 | Jacob Aizikowitz | System and method for creating customized documents for cross media publishing |
| US6513010B1 (en) * | 2000-05-30 | 2003-01-28 | Voxi Ab | Method and apparatus for separating processing for language-understanding from an application and its functionality |
| US20010053252A1 (en) * | 2000-06-13 | 2001-12-20 | Stuart Creque | Method of knowledge management and information retrieval utilizing natural characteristics of published documents as an index method to a digital content store |
| US10114821B2 (en) * | 2000-12-27 | 2018-10-30 | Tractmanager, Inc. | Method and system to access to electronic business documents |
| US8539334B2 (en) | 2000-12-27 | 2013-09-17 | Tractmanager, Inc. | Document management system having automatic notifications |
| US6957384B2 (en) | 2000-12-27 | 2005-10-18 | Tractmanager, Llc | Document management system |
| US20020124025A1 (en) * | 2001-03-01 | 2002-09-05 | International Business Machines Corporataion | Scanning and outputting textual information in web page images |
| US20020126918A1 (en) * | 2001-03-08 | 2002-09-12 | Ernesto Solis | Apparatus and method for interacting with printed materials |
| US7062572B1 (en) | 2001-03-19 | 2006-06-13 | Microsoft Corporation | Method and system to determine the geographic location of a network user |
| US6760139B2 (en) * | 2001-04-25 | 2004-07-06 | Hewlett-Packard Development Company, L.P. | Optical image scanner with lens arrays that are non-perpendicular to the image being scanned |
| US7127671B1 (en) * | 2001-09-14 | 2006-10-24 | Mcdonald David C | Publishing a customized publication by defining multiple sources and time periods for obtaining article quotable information |
| US7712028B2 (en) * | 2001-10-19 | 2010-05-04 | Xerox Corporation | Using annotations for summarizing a document image and itemizing the summary based on similar annotations |
| US20040034832A1 (en) * | 2001-10-19 | 2004-02-19 | Xerox Corporation | Method and apparatus for foward annotating documents |
| US7743347B2 (en) * | 2001-11-19 | 2010-06-22 | Ricoh Company, Ltd. | Paper-based interface for specifying ranges |
| US7495795B2 (en) * | 2002-02-21 | 2009-02-24 | Ricoh Company, Ltd. | Interface for printing multimedia information |
| US7747655B2 (en) | 2001-11-19 | 2010-06-29 | Ricoh Co. Ltd. | Printable representations for time-based media |
| US7788080B2 (en) * | 2001-11-19 | 2010-08-31 | Ricoh Company, Ltd. | Paper interface for simulation environments |
| US8539344B2 (en) | 2001-11-19 | 2013-09-17 | Ricoh Company, Ltd. | Paper-based interface for multimedia information stored by multiple multimedia documents |
| US7149957B2 (en) | 2001-11-19 | 2006-12-12 | Ricoh Company, Ltd. | Techniques for retrieving multimedia information using a paper-based interface |
| US7861169B2 (en) | 2001-11-19 | 2010-12-28 | Ricoh Co. Ltd. | Multimedia print driver dialog interfaces |
| US8635531B2 (en) * | 2002-02-21 | 2014-01-21 | Ricoh Company, Ltd. | Techniques for displaying information stored in multiple multimedia documents |
| US7703044B2 (en) * | 2001-11-19 | 2010-04-20 | Ricoh Company, Ltd. | Techniques for generating a static representation for time-based media information |
| US7151864B2 (en) * | 2002-09-18 | 2006-12-19 | Hewlett-Packard Development Company, L.P. | Information research initiated from a scanned image media |
| AU2002952106A0 (en) * | 2002-10-15 | 2002-10-31 | Silverbrook Research Pty Ltd | Methods and systems (npw008) |
| AU2003901428A0 (en) | 2003-03-24 | 2003-04-10 | Objective Systems Pty Ltd | A system and method for formatting and distributing reading material |
| US7739583B2 (en) * | 2003-03-31 | 2010-06-15 | Ricoh Company, Ltd. | Multimedia document sharing method and apparatus |
| US7703002B2 (en) | 2003-03-31 | 2010-04-20 | Ricoh Company, Ltd. | Method and apparatus for composing multimedia documents |
| US7509569B2 (en) | 2003-03-31 | 2009-03-24 | Ricoh Co., Ltd. | Action stickers for nested collections |
| US20070050696A1 (en) * | 2003-03-31 | 2007-03-01 | Piersol Kurt W | Physical key for accessing a securely stored digital document |
| US7757162B2 (en) * | 2003-03-31 | 2010-07-13 | Ricoh Co. Ltd. | Document collection manipulation |
| US7552381B2 (en) * | 2003-03-31 | 2009-06-23 | Ricoh Co., Ltd. | Check boxes for identifying and processing stored documents |
| US7536638B2 (en) * | 2003-03-31 | 2009-05-19 | Ricoh Co., Ltd. | Action stickers for identifying and processing stored documents |
| US7275159B2 (en) | 2003-08-11 | 2007-09-25 | Ricoh Company, Ltd. | Multimedia output device having embedded encryption functionality |
| US7493322B2 (en) | 2003-10-15 | 2009-02-17 | Xerox Corporation | System and method for computing a measure of similarity between documents |
| US7707039B2 (en) | 2004-02-15 | 2010-04-27 | Exbiblio B.V. | Automatic modification of web pages |
| US8442331B2 (en) | 2004-02-15 | 2013-05-14 | Google Inc. | Capturing text from rendered documents using supplemental information |
| US8799303B2 (en) * | 2004-02-15 | 2014-08-05 | Google Inc. | Establishing an interactive environment for rendered documents |
| US7812860B2 (en) | 2004-04-01 | 2010-10-12 | Exbiblio B.V. | Handheld device for capturing text from both a document printed on paper and a document displayed on a dynamic display device |
| US8521772B2 (en) * | 2004-02-15 | 2013-08-27 | Google Inc. | Document enhancement system and method |
| US20060041484A1 (en) | 2004-04-01 | 2006-02-23 | King Martin T | Methods and systems for initiating application processes by data capture from rendered documents |
| US10635723B2 (en) | 2004-02-15 | 2020-04-28 | Google Llc | Search engines and systems with handheld document data capture devices |
| US7779355B1 (en) | 2004-03-30 | 2010-08-17 | Ricoh Company, Ltd. | Techniques for using paper documents as media templates |
| US9143638B2 (en) | 2004-04-01 | 2015-09-22 | Google Inc. | Data capture from rendered documents using handheld device |
| US20060098900A1 (en) | 2004-09-27 | 2006-05-11 | King Martin T | Secure data gathering from rendered documents |
| US20070300142A1 (en) * | 2005-04-01 | 2007-12-27 | King Martin T | Contextual dynamic advertising based upon captured rendered text |
| US9116890B2 (en) | 2004-04-01 | 2015-08-25 | Google Inc. | Triggering actions in response to optically or acoustically capturing keywords from a rendered document |
| US20100185538A1 (en) * | 2004-04-01 | 2010-07-22 | Exbiblio B.V. | Content access with handheld document data capture devices |
| US9008447B2 (en) | 2004-04-01 | 2015-04-14 | Google Inc. | Method and system for character recognition |
| US8081849B2 (en) | 2004-12-03 | 2011-12-20 | Google Inc. | Portable scanning and memory device |
| US20080313172A1 (en) | 2004-12-03 | 2008-12-18 | King Martin T | Determining actions involving captured information and electronic content associated with rendered documents |
| US8621349B2 (en) | 2004-04-01 | 2013-12-31 | Google Inc. | Publishing techniques for adding value to a rendered document |
| US8146156B2 (en) | 2004-04-01 | 2012-03-27 | Google Inc. | Archive of text captures from rendered documents |
| US9405740B2 (en) * | 2004-04-01 | 2016-08-02 | Google Inc. | Document enhancement system and method |
| US20060081714A1 (en) | 2004-08-23 | 2006-04-20 | King Martin T | Portable scanning device |
| US8793162B2 (en) | 2004-04-01 | 2014-07-29 | Google Inc. | Adding information or functionality to a rendered document via association with an electronic counterpart |
| US7990556B2 (en) | 2004-12-03 | 2011-08-02 | Google Inc. | Association of a portable scanner with input/output and storage devices |
| US7894670B2 (en) | 2004-04-01 | 2011-02-22 | Exbiblio B.V. | Triggering actions in response to optically or acoustically capturing keywords from a rendered document |
| US8713418B2 (en) | 2004-04-12 | 2014-04-29 | Google Inc. | Adding value to a rendered document |
| US8874504B2 (en) | 2004-12-03 | 2014-10-28 | Google Inc. | Processing techniques for visual capture data from a rendered document |
| US8489624B2 (en) | 2004-05-17 | 2013-07-16 | Google, Inc. | Processing techniques for text capture from a rendered document |
| US8620083B2 (en) | 2004-12-03 | 2013-12-31 | Google Inc. | Method and system for character recognition |
| US9460346B2 (en) | 2004-04-19 | 2016-10-04 | Google Inc. | Handheld device for capturing text from both a document printed on paper and a document displayed on a dynamic display device |
| WO2005124579A1 (en) * | 2004-06-17 | 2005-12-29 | Objective Systems Pty Limited | Reproduction of documents into requested forms |
| US8799401B1 (en) * | 2004-07-08 | 2014-08-05 | Amazon Technologies, Inc. | System and method for providing supplemental information relevant to selected content in media |
| US8346620B2 (en) | 2004-07-19 | 2013-01-01 | Google Inc. | Automatic modification of web pages |
| US20100092095A1 (en) * | 2008-10-14 | 2010-04-15 | Exbiblio B.V. | Data gathering in digital and rendered document environments |
| US20110075228A1 (en) * | 2004-12-03 | 2011-03-31 | King Martin T | Scanner having connected and unconnected operational behaviors |
| US7698637B2 (en) * | 2005-01-10 | 2010-04-13 | Microsoft Corporation | Method and computer readable medium for laying out footnotes |
| JP4428266B2 (en) * | 2005-03-22 | 2010-03-10 | 富士ゼロックス株式会社 | Translation apparatus and program |
| JP4626356B2 (en) * | 2005-03-25 | 2011-02-09 | 富士ゼロックス株式会社 | Method, apparatus, and program for editing electronic document including additional information |
| JP2006277103A (en) * | 2005-03-28 | 2006-10-12 | Fuji Xerox Co Ltd | Document translating method and its device |
| US7689620B2 (en) * | 2006-05-24 | 2010-03-30 | Sizhe Tan | Efficiently and systematically searching stock, image, and other non-word-based documents |
| EP2067119A2 (en) | 2006-09-08 | 2009-06-10 | Exbiblio B.V. | Optical scanners, such as hand-held optical scanners |
| JP4539756B2 (en) * | 2008-04-14 | 2010-09-08 | 富士ゼロックス株式会社 | Image processing apparatus and image processing program |
| US20100205529A1 (en) * | 2009-02-09 | 2010-08-12 | Emma Noya Butin | Device, system, and method for creating interactive guidance with execution of operations |
| US9569231B2 (en) * | 2009-02-09 | 2017-02-14 | Kryon Systems Ltd. | Device, system, and method for providing interactive guidance with execution of operations |
| CN105930311B (en) | 2009-02-18 | 2018-10-09 | 谷歌有限责任公司 | Execute method, mobile device and the readable medium with the associated action of rendered document |
| US8447066B2 (en) | 2009-03-12 | 2013-05-21 | Google Inc. | Performing actions based on capturing information from rendered documents, such as documents under copyright |
| WO2010105245A2 (en) | 2009-03-12 | 2010-09-16 | Exbiblio B.V. | Automatically providing content associated with captured information, such as information captured in real-time |
| JP5412916B2 (en) * | 2009-03-27 | 2014-02-12 | コニカミノルタ株式会社 | Document image processing apparatus, document image processing method, and document image processing program |
| US20100299134A1 (en) * | 2009-05-22 | 2010-11-25 | Microsoft Corporation | Contextual commentary of textual images |
| US8918739B2 (en) | 2009-08-24 | 2014-12-23 | Kryon Systems Ltd. | Display-independent recognition of graphical user interface control |
| US9098313B2 (en) * | 2009-08-24 | 2015-08-04 | Kryon Systems Ltd. | Recording display-independent computerized guidance |
| US9405558B2 (en) * | 2009-08-24 | 2016-08-02 | Kryon Systems Ltd. | Display-independent computerized guidance |
| US9081799B2 (en) | 2009-12-04 | 2015-07-14 | Google Inc. | Using gestalt information to identify locations in printed information |
| US9323784B2 (en) | 2009-12-09 | 2016-04-26 | Google Inc. | Image search using text-based elements within the contents of images |
| US8484218B2 (en) * | 2011-04-21 | 2013-07-09 | Google Inc. | Translating keywords from a source language to a target language |
| US9349202B1 (en) * | 2012-10-01 | 2016-05-24 | Amazon Technologies, Inc. | Digital conversion of imaged content |
| JP2015069365A (en) * | 2013-09-27 | 2015-04-13 | シャープ株式会社 | Information processing equipment and control program |
| EP3324305A4 (en) * | 2015-07-13 | 2018-12-05 | Teijin Limited | Information processing apparatus, information processing method, and computer program |
| CN117099107A (en) * | 2021-02-12 | 2023-11-21 | 艾可品牌公司 | System and method for facilitating information extraction and organization from paper and other physical writing surfaces |
Family Cites Families (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3126886A1 (en) * | 1981-07-08 | 1983-01-27 | Olympia Werke Ag | DEVICE FOR TEXT PROCESSING AND TEXT PROCESSING |
| JPS58103266A (en) * | 1981-12-15 | 1983-06-20 | Toshiba Corp | Character image processor |
| EP0120334B1 (en) * | 1983-03-01 | 1989-12-06 | Nec Corporation | Letter pitch detection system |
| JPH0750483B2 (en) * | 1985-05-22 | 1995-05-31 | 株式会社日立製作所 | How to store additional information about document images |
| JPH0797373B2 (en) * | 1985-08-23 | 1995-10-18 | 株式会社日立製作所 | Document matching system |
| JPH0797798B2 (en) * | 1985-12-26 | 1995-10-18 | 株式会社リコー | Multi-color image forming apparatus with translation function |
| US5050218A (en) * | 1986-08-26 | 1991-09-17 | Nec Corporation | Apparatus for recognizing address appearing on mail article |
| US4972349A (en) * | 1986-12-04 | 1990-11-20 | Kleinberger Paul J | Information retrieval system and method |
| JPS63158678A (en) * | 1986-12-23 | 1988-07-01 | Sharp Corp | Inter-word space detecting method |
| US4965763A (en) * | 1987-03-03 | 1990-10-23 | International Business Machines Corporation | Computer method for automatic extraction of commonly specified information from business correspondence |
| US4985930A (en) * | 1987-09-24 | 1991-01-15 | Hitachi, Ltd. | Image data filing system and image data correcting method |
| US4994987A (en) * | 1987-11-20 | 1991-02-19 | Minnesota Mining And Manufacturing Company | Image access system providing easier access to images |
| JPH01144171A (en) * | 1987-11-30 | 1989-06-06 | Toshiba Corp | Electronic filing device |
| US5195032A (en) * | 1987-12-24 | 1993-03-16 | Sharp Kabushiki Kaisha | Device for designating a processing area for use in a translation machine |
| JP2683008B2 (en) * | 1988-02-16 | 1997-11-26 | 株式会社リコー | Rectangle shape internal filling method |
| JP2783558B2 (en) * | 1988-09-30 | 1998-08-06 | 株式会社東芝 | Summary generation method and summary generation device |
| CA1318404C (en) * | 1988-10-11 | 1993-05-25 | Michael J. Hawley | Method and apparatus for indexing files in a computer system |
| CA1318403C (en) * | 1988-10-11 | 1993-05-25 | Michael J. Hawley | Method and apparatus for extracting keywords from text |
| US4996707A (en) * | 1989-02-09 | 1991-02-26 | Berkeley Speech Technologies, Inc. | Text-to-speech converter of a facsimile graphic image |
| US5291592A (en) * | 1989-05-15 | 1994-03-01 | Sharp Kabushiki Kaisha | System having document scanner for optically scanning information whereby a first information contains control information indicating a number of sheets to be scanned |
| US5048109A (en) * | 1989-12-08 | 1991-09-10 | Xerox Corporation | Detection of highlighted regions |
| JP2758952B2 (en) * | 1989-12-28 | 1998-05-28 | 富士通株式会社 | Display Method for Japanese Document Reading and Translation System at Correction |
| US5048099A (en) * | 1990-05-21 | 1991-09-10 | Eastman Kodak Company | Polygon-based method for automatic extraction of selected text in a digitized document |
| JPH0477965A (en) * | 1990-07-20 | 1992-03-12 | Ricoh Co Ltd | Digital copying machine |
| US5175684A (en) * | 1990-12-31 | 1992-12-29 | Trans-Link International Corp. | Automatic text translation and routing system |
| US5495581A (en) * | 1992-02-25 | 1996-02-27 | Tsai; Irving | Method and apparatus for linking a document with associated reference information using pattern matching |
-
1992
- 1992-09-16 CA CA002078423A patent/CA2078423C/en not_active Expired - Fee Related
- 1992-11-12 JP JP30272792A patent/JP3289968B2/en not_active Expired - Lifetime
- 1992-11-16 EP EP92310435A patent/EP0544434B1/en not_active Expired - Lifetime
- 1992-11-16 DE DE69226611T patent/DE69226611T2/en not_active Expired - Fee Related
-
1994
- 1994-07-11 US US08/272,452 patent/US5748805A/en not_active Expired - Lifetime
Also Published As
| Publication number | Publication date |
|---|---|
| EP0544434B1 (en) | 1998-08-12 |
| EP0544434A3 (en) | 1993-12-22 |
| JP3289968B2 (en) | 2002-06-10 |
| CA2078423A1 (en) | 1993-05-20 |
| DE69226611D1 (en) | 1998-09-17 |
| JPH05250408A (en) | 1993-09-28 |
| DE69226611T2 (en) | 1999-01-28 |
| EP0544434A2 (en) | 1993-06-02 |
| US5748805A (en) | 1998-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2078423C (en) | Method and apparatus for supplementing significant portions of a document selected without document image decoding with retrieved information | |
| CA2077274C (en) | Method and apparatus for summarizing a document without document image decoding | |
| EP0544433B1 (en) | Method and apparatus for document image processing | |
| CA2077604C (en) | Method and apparatus for determining the frequency of words in a document without document image decoding | |
| EP0544431B1 (en) | Methods and apparatus for selecting semantically significant images in a document image without decoding image content | |
| EP0543598B1 (en) | Method and apparatus for document image processing | |
| US7756871B2 (en) | Article extraction | |
| EP1271355A2 (en) | Auto-index method | |
| US20040034835A1 (en) | Method and apparatus for generating a summary from a document image | |
| EP1304625B1 (en) | Method and apparatus for forward annotating documents and for generating a summary from a document image | |
| JPH05158401A (en) | Document fast reading support/display system and document processor and document retrieving device | |
| JPH06259424A (en) | Document display device and document summary device and digital copying device | |
| JP3142986B2 (en) | Document information retrieval device | |
| JP3841318B2 (en) | Icon generation method, document search method, and document server | |
| Bloomberg et al. | Document image summarization without OCR | |
| JP3206600B2 (en) | Document generation device | |
| JPH10198705A (en) | Device, method for processing document image, and information recording medium | |
| Setlur et al. | Creation of Multi-Lingual data resources and evaluation tool for | |
| Liu | Identification of headers and footers in noisy documents | |
| JPH087776B2 (en) | Document reader |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| MKLA | Lapsed |