WO2007105891A1

WO2007105891A1 - Recognizing the denomination of a note using wavelet transform

Info

Publication number: WO2007105891A1
Application number: PCT/KR2007/001195
Authority: WO
Inventors: Eui Sun Choi
Original assignee: Nautilus Hyosung Inc.
Priority date: 2006-03-13
Filing date: 2007-03-12
Publication date: 2007-09-20
Also published as: KR20070093209A; KR101056666B1

Abstract

The present invention relates to a method of recognizing the denomination of a note, and more particularly, to a method of recognizing a note using a feature vector that is configured by dividing an inputted note image into blocks, performing wavelet transform for each of the blocks, and selecting the entire wavelet transformed image or a block where the performance of recognizing the denomination of the note is maximized. A method of recognizing a denomination of a note comprises the steps of dividing an original image into a predetermined number of blocks; performing wavelet transform for each of the divided images; obtaining wavelet coefficients for each of sub-bands, and dividing each of the sub-bands into a predetermined number of cells; comparing a magnitude of an absolute value, and extracting the number of wavelet coefficients; completing the extracting step for each of the sub-bands; and recognizing the denomination of the note.

Description

RECOGNIZING THE DENOMINATION OF A NOTE USING

WAVELET TRANSFORM

Technical Field

[1] The present invention relates to a method of recognizing the denomination of a note using wavelet transform, and more particularly, to a method of recognizing a note using a feature vector that is configured by dividing an inputted note image into blocks, performing wavelet transform for each of the blocks, and selecting the entire wavelet transformed image or a block where the performance of recognizing the denomination of the note is maximized.

[2]

Background Art

[3] In a conventional method of identifying a note, one-dimensional data

(one-dimensional data array or image) are obtained from a note using a plurality of single element type transmissive and reflective optical sensors, and an image pattern of the note is examined and compared with patterns of other notes in terms of specific regions that are considered to have a lot of distinguishable factors (template method). That is, the denomination of a note is identified by comparing image patterns with one another in terms of a set of specific regions (a template) or by measuring the size of the note.

[4] However, in the method of comparing and examining surface patterns of specific regions, if the type of a note to be identified is changed or a note is replaced by a new type of note, the contents and position of an existing template should be changed. Further, the contents and position of an existing template should be also changed if the position or orientation of a light emitting device or a light receiving device is adjusted. Accordingly, the design of an apparatus employing the method should be frequently changed. Furthermore, since the type of a note is identified only through the surface pattern scheme in the conventional method, it is impossible to determine the position of a portion to be examined so that optimized surface patterns can be obtained for all kinds of notes. This makes it difficult to distinguish all kinds of notes quite precisely.

[5] In order to solve the problem, there has been proposed a method of recognizing the denomination of a note, wherein the denomination of a note is recognized using a feature vector that is configured by scanning the note to obtain an image of the note, performing wavelet transform for the scanned note image, and comparing the magnitudes of the absolute values of wavelet coefficients with a reference value. However, in view of characteristics of the wavelet transform, transformed sub-band images are other expressions of different respective frequencies of the entire image, and thus, feature vectors extracted from the wavelet transformed sub-bands are difficult to express position information on local regions of feature points that are distributed over the entire image. For example, position information on local regions in a state where a given note (a front face or a rear face of the note) is upside down becomes an important variable in determining the denomination of the note. Accordingly, in the proposed method of recognizing the denomination of a note, wherein a feature vector is extracted by performing wavelet transform for an original note image as it is, features are extracted after dividing a wavelet transformed sub-band region into m x n cells, thereby restrictively reflecting position information on local regions of feature points. In the present invention, in order to further effectively incorporate position information on local regions of feature points into a feature vector, a note image is divided into a certain number of blocks, and wavelet features are extracted from each of the divided images. When wavelet features are extracted after a note image is divided into blocks, blocks that a user determines as being unnecessary for recognition of a note can be previously selected and excluded in the process of extracting the features. Thus, the recognition of the denomination of a note has enhanced reliability and accuracy. Further, since the size of an image is decreased, processing time is reduced. [6]

Disclosure of Invention

Technical Problem

[7] The present invention is conceived to solve the aforementioned problems. The present invention enables reduction in processing time required for recognition of the denomination of a note to be identified and correct recognition of the note even though the note is replaced by a new type of note, and makes it easy to identify all kinds of notes quite precisely, using a feature vector that is configured by dividing an inputted note image into blocks, performing wavelet transform for each of the blocks, and selecting the entire wavelet transformed image or a block where the performance of recognizing the denomination of the note is maximized.

[8]

Technical Solution

[9] To achieve the object described above, a method of recognizing a denomination of a note using wavelet transform according to the present invention comprises the steps of dividing an original image created by scanning the note into a predetermined number of blocks, i.e., M x N blocks, in horizontal and vertical directions; performing wavelet transform for each of the divided images by a predetermined number of times; obtaining wavelet coefficients for each of sub-bands created through the wavelet transform, and dividing each of the sub-bands into a predetermined number of cells, i.e., m x n cells, in the horizontal and vertical directions; comparing a magnitude of an absolute value of each of the wavelet coefficients with a reference value for each of the m x n cells, and extracting the number of wavelet coefficients with the magnitudes larger than or equal to the reference value; completing the extracting step for each of the sub-bands, and configuring a feature vector with a vertical structure; and recognizing the denomination of the note by measuring similarity between the feature vector and a predetermined determination criterion vector. [10]

Advantageous Effects

[11] The present invention relates to a method of recognizing the denomination of a note using wavelet transform, which enables correct recognition of a note even though the note to be identified is replaced by a new type of note, and makes it easy to identify all kinds of notes quite precisely, using a feature vector that is configured by dividing an inputted note image into blocks, performing wavelet transform for each of the blocks, and selecting the entire wavelet transformed image or a block where the performance of recognizing the denomination of the note is maximized.

[12] Further, a note can be stably recognized by excluding error factors such as the degree of contamination of the note or changes in the performance of an object included in a note identifying apparatus.

[13]

Brief Description of the Drawings

[14] Fig. 1 shows a typical wavelet transform process.

[15] Fig. 2 shows results of a general two-dimensional wavelet transform performed on an image.

[16] Fig. 3 is a flowchart illustrating a method of recognizing the denomination of a note using wavelet transform according to the present invention.

[17] Fig. 4 shows an example of an original image created according to the present invention.

[18] Fig. 5 shows results of dividing an image into 2 x 2 blocks.

[19] Fig. 6 shows results of performing wavelet transform for a first block image twice according to the present invention.

[20] Fig. 7 shows an example in which a d2 sub-band in the first block image is divided into m x n cells according to the present invention.

[21] Fig. 8 exemplarily shows a process of extracting a feature vector of the d2 sub-band in the first block image according to the present invention. [22] Fig. 9 exemplarily shows a process of extracting a feature vector by performing wavelet transform for the first block image twice according to the present invention.

[23] Fig. 10 shows a process of extracting a feature vector according to the present invention.

[24] **Explanation of Reference Numerals for Main Portions in Drawings**

[25] S320: Divide image into blocks

[26] S330: Wavelet transform

[27] S350: Divide sub-band into cells

[28] S360: Compare coefficients with reference value by cell

[29] S370: Configure feature vector

[30] S380: Measure similarity

[31]

Best Mode for Carrying Out the Invention

[32] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that like elements are designated by like reference numerals throughout the drawings.

[33] The outline of general wavelet transform will be described before describing the present invention.

[34] The wavelet transform is a process of reconfiguring a signal into very simple basic functions. That is, the wavelet transform can be considered as a method of decomposing data, a function, or an operator into different frequency components and examining each of the components associated with a resolution corresponding to each scale. The fundamental principle of the wavelet transform is similar to that of the Fourier analysis. The use of the wavelet transform for signal processing can restore a weak signal mixed with noise. However, compared with the Fourier analysis in which filters with the same size are used for all frequency bandwidths, the wavelet transform is different in that a narrow window is used for a high frequency bandwidth and a wide window is used for a low frequency bandwidth.

[35] The wavelet transform has been proved particularly to be useful for X-ray or magnetic resonance image processing in the medical field. An image processed in such a method can be processed clearly without a blur in its details. In addition, since the wavelet transform exactly reflects the fact that a person first recognizes an overall outline of a thing and then gradually concentrates on detailed portions, the wavelet transform is suitable for image processing.

[36] Basic operations of the wavelet transform are applied to discrete signals having n samples. A pair of filters are applied to a signal to separate the signal into a low frequency bandwidth and a high frequency bandwidth. Since each of the bandwidths is sub-sampled with a factor of 2, it contains n/2 samples.

[37] An example of the wavelet transform will be explained with reference to Fig. 1.

When signals are extracted from an image using low band pass filters (LPF) and high band pass filters (HPF) in spatial X- and Y-axis directions and then subjected to wavelet transform, four sub-bands LL 110, LH 120, HL 130 and HH 140 are created for each frequency bandwidth.

[38] At this time, the sub-bands LL, LH, HL, and HH are differentiated according to the filters applied to the image as shown in Fig. 1. The LL sub-band 110 comprises coefficients in which high frequency components are excluded from the image by applying low pass filters to the original image in the horizontal and vertical directions. The HH sub-band 140 for which high pass filters are applied to the original image in the horizontal and vertical directions contains only high frequency components contrary to the LL sub-band 110.

[39] The HL sub-band 130 for which a high pass filter is applied in the vertical direction contains error components of a frequency in the vertical direction, and the LH sub- band 120 for which a high pass filter is applied in the horizontal direction contains error components of a frequency in the horizontal direction. The LH sub-band and the HL sub-band have an effect obtained by employing edge detection for horizontal and vertical components from the original image, and the HH sub-band has an effect obtained by employing edge detection for diagonal components.

[40] Then, the wavelet transform is recursively performed over a plurality of steps, not limited to a first transform, and thus, the respective steps have different resolutions (multi-resolutions) and frequency characteristics (scalability). A specific example of the two-dimensional wavelet transform will be explained with reference to Fig. 2. Four sub-bands shown in Fig. 2 (b) (hereinafter, referred to as LL region 220, HL region 222, LH region, 224, and HH region 226) are created by performing wavelet transform once. If the LL region 220 is subjected once more to wavelet transform, four sub-bands of LL region 230, LH2 region, 234, HL2 region 232, and HH2 region 236 are created, and thus, the original image is decomposed into total seven sub-bands (LL 230, LHl 224, HLl 222, HHl 226, LH2 234, HL2 232, and HH2 236).

[41] The reason why the LL regions 220, 230, 240 and 250 are decomposed is that each

LL region contains important information on the image. The decomposition is repeated as many times as a certain decomposition value until desired information is obtained. The LL regions 220, 230, 240 and 250 are recursively decomposed, thereby obtaining a new processing target image.

[42] The wavelet transform is repeated as many times as the decomposition value to reduce the width of a low frequency bandwidth, and thus, a doubled spatial resolution is obtained. The decomposition value provided as a criterion for determining the number of recursive wavelet transforms is determined as an appropriate value in consideration of a loss of information and the size of a feature vector.

[43] In the present invention, high speed Haar wavelet transform is used to extract features from a note image. The method of recognizing the denomination of a note according to the present invention allows any kind of wavelet transform to be used. The high speed Haar wavelet transform is advantageous in expressing a wide area of continuous colors, easy to implement, and speedy in transforming. In addition, the high speed Haar wavelet transform satisfies conditions of uniqueness, completeness, invariance, sensitivity and abstraction that are characteristics of a system for expressing an image.

[44] Fig. 3 is a flowchart illustrating a method of recognizing the denomination of a note using wavelet transform according to the present invention.

[45] In order to recognize the demolition of a note according to the present invention, a note desired to be recognized is first scanned (S310) so that an original image 410 is created by as shown in Fig. 4. The original image 410 is divided into M x N blocks in horizontal and vertical directions as shown in Fig. 5. The division of the original image into blocks is to divide the image into non-overlapped rectangular fragments, which means division of the image into a predetermined number of blocks, i.e., M x N blocks, in the horizontal and vertical directions.

[46] When the preprocessed original image is divided into blocks and subjected to wavelet transform, further more information can be obtained as compared with performing wavelet transform for the entire image, thereby obtaining further correct information. Since only important blocks are selected and processed, processing time required for recognition of the denomination of a note can be reduced. For example, as shown in Fig. 5, if the preprocessed original image is divided into blocks by setting M to 2 and N to 2, the image is divided into two cells in the horizontal direction and into two cells in the vertical direction, resulting in total four blocks 510, 512, 514 and 516.

[47] Next, each of the blocked images is wavelet transformed as many times as a decomposition value (S330). The wavelet transform is to apply conventional wavelet transform to recognition of a note. If each of the blocked images is wavelet transformed, LL, LH, HL and HH regions are created. Next, the LL region is recursively wavelet transformed as many times as the certain decomposition value, resulting in created LH, HL and HH regions.

[48] The recursive wavelet transforms of the LL region are performed as many times as the decomposition value. In order to determine an appropriate decomposition value in case of the note recognition, reference data that are stored as representative feature vectors by denomination are compared with vectors of a given note image so as to determine whether such feature vectors can be clearly identified. That is, corre- spondence between two vectors is calculated through one-to-one comparison of the reference data with a given feature vector, and the LL region is then recursively wavelet transformed several times until each note can be identified according to the results of the calculation.

[49] For example, if the wavelet transform of a first block image is repeated twice as shown in Fig. 6, the first block image 510 is decomposed into LL region 520, LH region 524, HL region 522, and HH region 526 through the first wavelet transform as shown in Fig. 6 (b). If the LL region 520 is decomposed once more through the second wavelet transform, LL region 530, LHl region 524, HLl region 522, HHl region 526, LH2 region 534, HL2 region 532 and HH2 region 536 are created as shown in Fig. 6 (c). Hereinafter, description will be made in connection with an example in which the decomposition value is set to 'J level'.

[50] An example in which the wavelet transforms are applied to recognition of a note up to J level as the decomposition value will be described in detail. When the first block image 510 is wavelet transformed as many times as the decomposition value, it is decomposed into 3 J + 1 regions. Through the decomposition, 3 J (dl to d3j) regions can be obtained, except the LL region 530 that is created in the last transform. For example, if the J level is set to two, as shown in Fig. 6 (c), the first block image 510 is decomposed into seven (3 x 2 + 1) regions, and six regions of dl region 522, d2 region 524, d3 region 526, d4 region 532, d5 region 534, and d6 region 536 can be obtained.

[51] If the wavelet transforms are completed as many times as the value of J level, each of the regions dl to d6 (when J is two) is configured with wavelet coefficients having features of each band using differences in information of neighboring regions (S340). As for the wavelet coefficient, the LL region 530 for which low pass filters are applied in the horizontal and vertical directions is configured with approximate coefficient values of the image, and d5 region 534 and d2 region 524, i.e., LH regions for which a high pass filter is applied in the horizontal direction, are respectively configured with coefficient values of horizontal components of the image.

[52] In addition, d4 region 532 and dl region 522, i.e., HL regions for which a high pass filter is applied in the vertical direction, are respectively configured with coefficient values of vertical components of the image, and d6 region 536 and d3 region 526, i.e., HH regions for which high pass filters are applied in the horizontal and vertical directions, are respectively configured with coefficient values of diagonal components of the image.

[53] Next, a feature vector is configured according to each of the M x N x 3J regions

(e.g., regions dl to d6 of M x N blocks if J level is two) created by the wavelet transform. At this time, all of the M x N x 3J regions do not need to participate in configuring the feature vectors. Similarily to determining the decomposition value of the wavelet transform, it is possible to determine the positions and number of regions for maximizing the performance of recognition of the denomination of a note. In this case, an optimal combination of the regions can be obtained by examining the recognition performance of all combinations of the regions (full search, binary tree search, and the like).

[54] The feature vector is a vector value configured by comparing the magnitudes of the absolute values of the extracted wavelet coefficients with a predetermined reference value. For example, obtaining feature vectors of the first block image, i.e., d2 region 524, will be described. First, d2 region 524 is divided into m x n cells in the horizontal and vertical directions as shown in Fig. 7 (S350). For the respective m x n cells, the magnitudes of the absolute values of wavelet coefficients are compared with a reference value (S360) to extract the number of wavelet coefficients of which the magnitudes are equal to or larger than the reference value, thereby configuring a first vector (S370).

[55] For example, in a case where the reference value is 7, d2 region 524 is divided into m x n (l l x 4) cells as shown in Fig. 8, and the number of coefficients of which the magnitudes are larger than the reference value 7 is counted among coefficients in first cell mini 810. That is, it is understood that the number of coefficients of which the magnitudes are larger than the reference value 7 is 35 in cell mini 810 comprising coefficients of {5, 7, 9, 10, 11, 9, ..., 9, 9, 8, 7, 7, 6}, and the number 35 becomes a feature vector 812 of cell mini. Subsequently, the number of coefficients of which the magnitudes are larger than the reference value 7 is counted among coefficients in a second cell m2nl 820, and the counted number 27 becomes a feature vector 822 of cell m2nl. If the extraction process is completed up to cell mmnn 830, a first vector 840 having m x n elements is created. Likewise, it is understood that if the process of creating a feature vector is repeated for all of the six (J = 2) sub-band regions (dl to d6) shown in Fig. 9, 6 x m x n feature vectors of region d2 are created.

[56] Fig. 9 shows values obtained when J of a block is 2. If the values are expressed as a formula, a feature vector having a vertical structure of total MN3Jmn bits, i.e. number of blocks in a row (M) x number of blocks in a column (N) x 3 x wavelet transform level (J) x number of cells in a row (m) x number of cells in a column (n), is extracted as shown in Fig. 10.

[57] Based on the characteristics of the wavelet transform, each of the aforementioned M x N (3 x J + 1) wavelet sub-band regions is another expression of a specific frequency resolution for the image of a corresponding block. In addition, division of a sub-band region into m x n cells implies that the image of each block is divided into m x n portions. Accordingly, by extracting a feature vector on a block combination basis and on a cell basis, position information on local regions of feature points in the entire image can be maximally expressed.

[58] Next, similarity between the configured feature vector and a predetermined determination criterion vector is measured (S380), thereby performing the process of recognizing the denomination of the note (S390). In order to verify the two feature vectors, final similarity is determined using a shortest distance distribution that is obtained using a conventional method, such as a shortest distance technique or the like.

[59] The present invention has been described in connection with a method of recognizing a typical note. However, the present invention is not limited to the recognition of such a typical note but can be applied to recognition of general types of notes having certain printed patterns or watermark images, such as securities, a variety of paper money guaranties, and checks. Therefore, the scope of the present invention should not be defined by the embodiment described above but apparently defined by the invention of the appended claims and equivalents thereof.

[60]

Industrial Applicability

[61] According to the present invention, the denomination of a note can be recognized using a feature vector that is configured by dividing a note image into blocks, performing wavelet transform for each of the blocks, and selecting the entire wavelet transformed image or a block where the performance of recognizing the denomination of the note is maximized. Thus, the present invention can be widely applied to recognition of not only typical notes but also general types of notes having certain printed patterns or watermark images, such as securities, a variety of paper money guaranties, and checks.

[62]

Claims

[1] A method of recognizing a denomination of a note using wavelet transform, comprising the steps of: dividing an original image created by scanning the note into M x N blocks in horizontal and vertical directions; performing wavelet transform for each of the divided images by a predetermined number of times; obtaining wavelet coefficients for each of sub-bands created through the wavelet transform, and dividing each of the sub-bands into m x n cells in the horizontal and vertical directions; comparing a magnitude of an absolute value of each of the wavelet coefficients with a reference value for each of the m x n cells, and extracting the number of wavelet coefficients with the magnitudes larger than or equal to the reference value; completing the extracting step for each of the sub-bands, and configuring a feature vector with a vertical structure; and recognizing the denomination of the note by measuring similarity between the feature vector and a predetermined determination criterion vector.

[2] The method as claimed in claim 1, wherein the wavelet transform comprises a high speed Haar wavelet transform method.

[3] The method as claimed in claim 1, wherein the wavelet coefficient has features of each of the sub-bands by using a difference in information of neighboring sub- bands according to each of sub-band images.

[4] The method as claimed in claim 1, wherein the step of configuring the feature vector comprises configuring the feature vector in a vertical structure of total MN3Jmn bits that is number of blocks in a row (M) x number of blocks in a column (N) x 3 x wavelet transform level (J) x number of cells in a row (m) x number of cells in a column (n).

[5] The method as claimed in claim 1, wherein the step of measuring the similarity comprises determining final similarity using shortest distance distribution obtained through a conventional shortest distance method.