WO2017016240A1

WO2017016240A1 - Banknote serial number identification method

Info

Publication number: WO2017016240A1
Application number: PCT/CN2016/078869
Authority: WO
Inventors: 王丹丹; 肖助明; 岳许要; 刘道余
Original assignee: 广州广电运通金融电子股份有限公司
Priority date: 2015-07-24
Filing date: 2016-04-08
Publication date: 2017-02-02
Also published as: CN105261109A; CN105261109B

Abstract

The embodiment of the present invention discloses a banknote serial number identification method for solving the problem in which existing character identification processes cannot distinguish between similar characters. The method comprises: obtaining a serial number image of a banknote (101); performing a cutting process on the serial number image to obtain a plurality of character images (102); scaling all of the character images to a preset uniform size (103); extracting a feature vector of the character image (104); performing character identification on the character image based on the feature vector and a pre-trained classifier model to obtain a preliminary identification result (105); determining whether the preliminary identification result falls within a preset similar character set, and if so, performing a second identification on the character image (108), and if not, outputting the preliminary identification result (107).

Description

Banknote crown number recognition method

The present application claims priority to Chinese Patent Application No. 201510443057.3, entitled "A Method for Recognizing a Banknote Crown Number" on July 24, 2015, the entire contents of which are incorporated herein by reference. .

Technical field

The invention relates to the technical field of banknote recognition, and in particular to a method for identifying a banknote crown number.

Background technique

With the widespread application of optical character recognition technology in human production and life, the identification of banknotes has become an important means of preventing economic crimes in the financial field. The automatic recognition technology of optical characters has attracted more and more attention from researchers.

The crown size of the banknote is generally composed of the numbers 0-9 and the letters A to Z. In the current RMB crown number sequence rule, the first digit is a letter, the second, third, and fourth digits are numbers or letters, and the fifth to tenth digits are numbers.

In character recognition processing, character feature extraction is one of the most important steps, especially in the field of banknote recognition, the similarity of similar characters (O and 0, 1 and I, etc.) is extremely high. However, based on the traditional local structural features or the global statistical features, the problem of similar characters cannot be solved well. Therefore, those skilled in the art need to find a method for recognizing the banknotes of similar characters.

Summary of the invention

The embodiment of the invention provides a method for recognizing a banknote crown number, which can solve the problem that the existing character recognition processing cannot well recognize similar characters.

A banknote crown number recognition method provided by an embodiment of the invention includes:

Obtaining the image of the crown of the banknote;

Performing character cutting processing on the crown image to obtain a plurality of character images;

Scaling all of the character images into a preset same size;

Extracting a feature vector of the character image;

Performing character recognition on the character image according to the feature vector and a pre-trained classifier model to obtain a preliminary recognition result;

Determining whether the preliminary recognition result falls within a preset similar character group, and if so, performing secondary recognition on the character image, and if not, outputting the preliminary recognition result;

The performing secondary recognition on the character image specifically includes the following steps:

Obtaining a preset specific area of the character image according to the preliminary recognition result;

Obtaining a preset stroke template of the character image according to the preliminary recognition result;

Performing sliding matching in the specific area by the stroke template, and using the maximum number of pixels of the character image that is successfully matched as the maximum matching value;

Obtaining, according to the maximum matching value and a preset threshold, a recognition result of the character image in the similar character group as a secondary recognition result;

The secondary recognition result is output.

Optionally, before the sliding matching in the specific area by using the stroke template, the method further includes:

The character image is binarized.

Optionally, the stroke template includes: a stroke horizontal, a stroke vertical, and a stroke point.

Optionally, the similar character group corresponding to the preliminary recognition result includes a first similar character and a second similar character;

The obtaining result of the character image in the similar character group according to the maximum matching value and the preset threshold is specifically:

Determining whether the maximum matching value is greater than or equal to a preset threshold. If yes, the recognition result of the character image is a first similar character, and if not, the recognition result of the character image is a second similar character.

Optionally, before performing the character cutting process on the crown image, the method further includes:

Image preprocessing of the crown image;

The image preprocessing of the image of the crown number specifically includes:

Denoising the crown image;

Or, performing image rectification processing on the crown image.

Optionally, extracting the feature vector of the character image specifically includes:

Calculating a gradient map of the character image to obtain a gradient matrix;

Decomposing the gradient matrix in a standard eight direction to obtain a feature matrix;

Convolving the feature matrix with a preset weight matrix to generate a first feature sub-vector;

Generating a second feature sub-vector according to a direction in which the gradient matrix is most decomposed in a standard eight direction and a maximum number thereof, and a direction in which the decomposition value is accumulated the largest and a maximum accumulated value;

The first feature subvector and the second feature subvector are synthesized into the feature vector.

Optionally, the classifier model is composed of an SMO binary classifier, which includes a digital model, an alphabet model, and a digital and alpha model;

The classifier model has a corresponding relationship with the position of the character image on the banknote crown number.

Optionally, the banknote is RMB;

The similar character group includes a first similar character group 0 and D, a second similar character group 8 and B, and a Three similar character groups 1 and I, fourth similar character group 2 and Z, or fifth similar character group O and D;

The first digit of the banknote crown number corresponds to the letter model, the fifth digit to the tenth digit correspond to the digital model, and the second digit to the fourth digit correspond to the number and letter model.

Optionally, the determining whether the preliminary recognition result falls into a preset similar character group is specifically:

It is judged whether the preliminary recognition result is 0, D, 8, B, 1, I, 2, Z or O.

Optionally, scaling all of the character images to a preset same size is specifically:

All of the character images are scaled to a rectangular image of the same size according to interpolation.

It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

In the embodiment of the present invention, first, acquiring a crown image of the banknote; performing character cutting processing on the crown image to obtain a plurality of character images; and scaling all the character images into a preset same size; Determining a feature vector of the character image; performing character recognition on the character image according to the feature vector and a pre-trained classifier model to obtain a preliminary recognition result; and finally, determining whether the preliminary recognition result falls within a preset similar character group If yes, the character image is subjected to secondary recognition, and if not, the preliminary recognition result is output; wherein the secondary recognition of the character image specifically includes the following steps: according to the preliminary recognition result Obtaining a preset specific area of the character image; acquiring a preset stroke template of the character image according to the preliminary recognition result; performing sliding matching in the specific area by the stroke template, and matching the successfully matched character The maximum number of pixels of the image is taken as the maximum matching value; according to the maximum matching value and the preset threshold value Said character image similar to the character recognition result in the group, the secondary recognition result; output of the secondary recognition result. In the embodiment of the present invention, the character image is initially identified according to the feature vector and the pre-trained classifier model, and then the character image falling into the similar character group is secondarily recognized, and the whole is combined. The analysis of the statistical features of the bureau and the characteristics of the local structural feature analysis can identify similar characters in the crown size of the banknote, greatly improving the accuracy of the crown identification of the banknote.

DRAWINGS

1 is a flow chart of an embodiment of a banknote crown number identification method according to an embodiment of the present invention;

2 is a flow chart of another embodiment of a banknote crown number identification method according to an embodiment of the present invention;

3 is a schematic diagram showing the identification of a banknote crown number recognition method according to an embodiment of the present invention;

4 is a schematic exploded perspective view of an embodiment of the present invention;

Figure 5 is a schematic diagram of a stroke template;

FIG. 6 is a schematic diagram of a template allocation area of similar characters in an embodiment of the present invention.

detailed description

The embodiment of the invention provides a method for recognizing a banknote crown number, which is used for solving the problem that the existing character recognition processing cannot identify similar characters well.

In order to make the object, the features and the advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. The described embodiments are only a part of the embodiments of the invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Referring to FIG. 1 , an embodiment of a banknote crown number identification method according to an embodiment of the present invention includes:

101. Obtain an image of the crown of the banknote;

First, you need to get the image of the crown of the banknote.

102. performing character cutting processing on the image of the crown size to obtain a plurality of character images;

After acquiring the crown image of the banknote, the crown image may be subjected to character cutting processing to obtain a plurality of character images.

103. Scale all the character images to a preset same size;

After obtaining a plurality of character images, all of the character images can be scaled to a preset same size.

104. Extract a feature vector of the character image;

After all of the character image is scaled to a preset same size, the feature vector of the character image can be extracted.

105. Perform character recognition on the character image according to the feature vector and the pre-trained classifier model to obtain a preliminary recognition result;

After extracting the feature vector of the character image, the character image may be subjected to character recognition according to the feature vector and the pre-trained classifier model to obtain a preliminary recognition result.

106, determine whether the preliminary recognition result falls into a preset similar character group, and if so, step 108 is performed; if not, step 107 is performed;

After the preliminary recognition result is obtained, it may be determined whether the preliminary recognition result falls within a preset similar character group, and if yes, step 108 is performed, and if not, step 107 is performed.

107. Output the preliminary identification result;

If the preliminary recognition result does not fall into the preset similar character group, the preliminary recognition result is output.

108. Acquire a preset specific area of the character image according to the preliminary recognition result;

If the preliminary recognition result falls within a preset similar character group, the character image needs to be secondarily recognized. First, the preset specific region of the character image may be acquired according to the preliminary recognition result.

109. Acquire a preset stroke template of the character image according to the preliminary recognition result;

And, the preset stroke template of the character image can be obtained according to the preliminary recognition result.

110. Perform sliding matching in the specific area by using the stroke template, and use the maximum number of pixels of the character image that is successfully matched as the maximum matching value;

After the specific area and the stroke template are obtained, the stroke matching may be performed in the specific area by the stroke template, and the maximum number of pixels of the character image that is successfully matched is used as the maximum matching value.

Step 111: Obtain a recognition result of the character image in the similar character group according to the maximum matching value and a preset threshold value, as a secondary recognition result;

After the maximum matching value is obtained, the recognition result of the character image in the similar character group may be obtained according to the maximum matching value and the preset threshold value as a secondary recognition result.

112. Output the second recognition result.

Finally, the secondary recognition result is output.

In this embodiment, first, acquiring a crown image of the banknote; performing character cutting processing on the crown image to obtain a plurality of character images; and scaling all the character images into a preset same size; and then extracting the character image a feature vector; performing character recognition on the character image according to the feature vector and the pre-trained classifier model to obtain a preliminary recognition result; finally, determining whether the preliminary recognition result falls within a preset similar character group, and if so, The character image is subjected to secondary recognition, and if not, the preliminary recognition result is output; wherein the secondary recognition of the character image specifically includes the following steps: acquiring a preset specific region of the character image according to the preliminary recognition result; Initially obtaining a preset stroke template of the character image; performing sliding matching in the specific area by using the stroke template, and using the maximum number of pixels of the character image that is successfully matched as a maximum matching value; according to the maximum matching value and the pre- Setting a threshold value to obtain a recognition result of the character image in the similar character group Second recognition result; an output of the secondary recognition result. In this embodiment, according to the feature vector and the pre-trained classification The model model performs preliminary recognition on the character image, and then performs secondary recognition on the character image falling into the similar character group. Combining the analysis of the global statistical feature and the characteristics of the local structural feature analysis, the similar character in the banknote crown number can be identified. Greatly improve the accuracy of the banknote crown identification.

For ease of understanding, a banknote crown number identification method in the embodiment of the present invention is described in detail below. Referring to FIG. 2, another embodiment of the banknote crown number identification method in the embodiment of the present invention includes:

201. Obtain an image of the crown number of the banknote;

First, you can get the image of the crown of the banknote. It can be understood that the image of the crown number of the banknote to be identified can be obtained by image scanning or the like.

It should be noted that the image of the crown number in this embodiment may be a grayscale image formed by a white light source, or may be a grayscale image of a single channel of a color image.

202: Perform image preprocessing on the image of the crown size;

After obtaining the crown image of the banknote, image preprocessing can be performed on the crown image. The image preprocessing of the image of the crown number includes: performing denoising processing on the image of the crown size, or performing image rectification processing on the image of the crown size. It can be understood that the pre-processed crown image can be better cut out characters, avoiding the problem that the cutting characters are offset or error and the recognition result is inaccurate.

203. Perform character cutting processing on the image of the crown size to obtain a plurality of character images.

After image preprocessing of the crown image, character cutting processing may be performed on the crown image to obtain a plurality of character images. It should be noted that the binarized character image can be horizontally and vertically projected, and then each character is cut out.

204. Scale all the character images to a preset same size;

After obtaining a plurality of character images, all of the character images may be scaled to a preset same size, for example, all of the character images are scaled to a rectangular image of the same size W*H according to interpolation, where W is the width of the character image , H is the height of the character image.

205. Extract a feature vector of the character image.

After all of the character image is scaled to a preset same size, the feature vector of the character image can be extracted. The extracting the feature vector of the character image may specifically include:

A. Calculating a gradient map of the character image to obtain a gradient matrix;

B. Decomposing the gradient matrix in a standard eight direction to obtain a feature matrix;

C. Convolving the feature matrix with a preset weight matrix to generate a first feature sub-vector;

D, generating a second feature sub-vector according to the direction in which the gradient matrix is most decomposed in the standard eight directions and the maximum number thereof, and the direction in which the decomposition value is accumulated the largest and the maximum accumulated value;

E. Combining the first feature subvector and the second feature subvector into the feature vector.

206. Perform character recognition on the character image according to the feature vector and the pre-trained classifier model to obtain a preliminary recognition result;

It should be noted that the classifier model is composed of an SMO two classifier, which includes a digital model and a letter model, and the classifier model has a corresponding relationship with the position of the character image on the banknote crown number. For example, assuming that the banknote is RMB, the similar character group includes a first similar character group 0 and D, a second similar character group 8 and B, a third similar character group 1 and I, and a fourth similar character group 2 and Z, Or a fifth similar character group O and D; the first digit of the banknote crown number corresponds to the letter model, the fifth to tenth digits correspond to the digital model, the second digit to the fourth digit and the number and letter model correspond.

207, it is determined whether the preliminary recognition result falls into a preset similar character group, and if so, step 209 is performed, and if not, step 208 is performed;

After obtaining the preliminary identification result, it may be determined whether the preliminary recognition result falls within a preset similar character group, and if yes, step 209 is performed, and if no, step 208 is performed. By taking the example of the above step 206, it can be known that step 207 is equivalent to determining whether the preliminary recognition result is 0, D, 8, B, 1, I, 2, Z or O, and if yes, executing step 209, if no Then, step 208 is performed.

208. Output the preliminary identification result.

If the preliminary recognition result does not fall into the preset similar character group, the preliminary recognition result may be considered to be accurate, there is no approximation, and the preliminary recognition result is output as the final recognition result.

209. Perform binarization processing on the character image.

If the preliminary recognition result falls within a preset similar character group, the preliminary recognition result may be considered to be suspicious, there may be an approximation, and secondary recognition is required. First, the character image is binarized.

210. Acquire a preset specific area of the character image according to the preliminary recognition result;

After the character image is binarized, the preset specific region of the character image may be acquired according to the preliminary recognition result. It can be understood that the preset specific area is determined for the preliminary recognition result, for example, if the preliminary recognition result is the number 1, the specific area is the upper position of "1".

211. Acquire a preset stroke template of the character image according to the preliminary recognition result.

The preset stroke region of the character image may be acquired according to the preliminary recognition result, while the preset specific region of the character image is acquired according to the preliminary recognition result. It can be understood that the stroke template is determined according to the preliminary recognition result, for example, if the preliminary recognition result is D, due to 0 and D It is a similar character, and D has a vertical and 0 is not, so at this time the stroke template selects the stroke vertical. The stroke template may include: a stroke stroke, a stroke vertical, and a stroke point.

212. Perform sliding matching in the specific area by using the stroke template, and use the maximum number of pixels of the character image that is successfully matched as the maximum matching value;

After the specific region corresponding to the preliminary recognition result and the stroke template are obtained, the stroke matching may be performed in the specific region by using the stroke template, and the maximum number of pixels of the character image that is successfully matched is used as the maximum matching value.

213. Obtain a recognition result of the character image in the similar character group according to the maximum matching value and a preset threshold value, as a secondary recognition result;

It should be noted that, if the similar character group corresponding to the preliminary recognition result includes the first similar character and the second similar character, the character image is obtained in the similar character group according to the maximum matching value and the preset threshold. The recognition result is specifically as follows:

It is determined whether the maximum matching value is greater than or equal to a preset preset. If yes, the recognition result of the character image is a first similar character, and if not, the recognition result of the character image is a second similar character.

214. Output the second recognition result.

After the secondary recognition result is obtained, since the case of similar characters has been excluded, the secondary recognition result can be considered to be accurate and reliable, and the secondary recognition result is output as the final recognition result.

For ease of understanding, according to the embodiment described in FIG. 2, the method for identifying the crown number of the banknote in the embodiment of the present invention is described below in a practical application scenario, as shown in FIG. 3.

Step 1: Read the grayscale image of the crown size area;

Step 2: Pre-processing such as image denoising and image rotation correction on the crown size area;

Step 3: Horizontally and vertically project the binarized character image, cut out each character, and use the interpolation method to scale the image to a uniform size W*H.

Step 4: Extract the feature vector;

Step 4-1: Calculate the character gradient map to obtain a gradient matrix;

Calculating the gradient matrix of the normalized character image using the Sobe operator,

Step 4-2: Feature matrix extraction, the gradient matrix G is decomposed in the standard eight directions, as shown in FIG.

Get the feature matrix

Where pi is the decomposition value of (gx, gy) in direction i.

Step 4-3: Feature matrix processing, setting the weight matrix

w _i,j represents the weight of the feature. This embodiment selects

That is, the average filtering is performed on each of the eight directions of P.

Convolution of the feature matrix P with the weight W generates a feature sub-vector F1,

Calculate the direction D_max_project with the largest number of decompositions in 8 directions, and its maximum number N_max_project, and the direction D_max_grad with the largest cumulative value of the decomposition values in 8 directions, and the maximum accumulated value V__max_grad. For the calculation method, see Equation (1)-(4).

Where n _{d, (i, j)} is the number of gradients of the pixel (i, j) decomposed into the d direction, and D_max_project is the direction in which N_max_project takes the maximum value.

Where p _{d, (i, j)} is the decomposition value of the gradient of the pixel (i, j) in the d direction. D_max_grad is the direction in which V_max_grad takes the maximum value.

D_max_project, N_max_projec, D_max_grad, V_max_grad generate a feature sub-vector F2. F1 and F2 synthesize feature vectors F.

Step 5: Identification of non-similar characters and similar characters

The classifier model used in this step consists of a pre-trained SMO binary classifier. The features of all digital and alpha training samples are extracted as described in step 4. Each character is tagged, and the number of the tags is 0 to 9 according to the numerical value, and the letters (except V) are sequentially sorted according to the order of 10 to 35. Two different characters train one SMO two classifier, and the second classifier model includes positive and negative sample labels: pos and neg, threshold b and weight array A. All two classifiers with pos and neg less than 10 form a digital model; all two classifiers with pos and neg greater than or equal to 10 form a letter model; all two classifiers form a digital and alphabetic model.

The product of the feature vector F of the character to be recognized and the weight class array A of the two classifiers is calculated, and the value S, S summed with the threshold b is greater than 0 to return the positive label pos, and otherwise, the negative label neg is returned. Each of the two classifiers casts 1 vote for the character class represented by the returned tag, and all the two classifiers constituting the classifier model vote for the recognized characters in turn, and finally counts the number of votes for each class, and the class with the most votes is the character to be recognized. Category.

According to the renminbi crown number sequence rule, the first digit is a letter, the last six digits are numbers, and the second, third, and fourth digits are numbers or letters. In order to improve the recognition rate and the classification speed, a digital model, an alphabet model or a numerical and alphabetic model is selected according to the position of the character to be recognized in the crown number sequence. The first digit uses the alphabet model, the last six digits use the numeric model, and the second, third, and fourth digits use the numeric and alphabetic model.

For non-similar characters, the SMO recognition result is the category with the final recognized character. If the recognition result is a character in a similar character group, it needs to be recognized again by using the stroke template matching.

Step 6: Similar character recognition

When the result of using the digital and alphanumeric model is a character in a similar character group, the template corresponding to the set of characters is used to perform template matching in the matching area, and the matching result is the final recognition result. The method involved in this step includes:

1. Binarization

The character image is binarized using the Otsu algorithm.

2, construct stroke template

In the banknote crown, similar characters include O (or 0) and D, 8 and B, 1 and I, 2 and Z, and the like. A stroke template is a rectangular area that is similar in size to the stroke of a character and is used to distinguish between strokes with similar characters. For example, in the character images of O and D, D has a stroke vertical and O is not, so a rectangular area similar to the vertical dimension of the stroke of D can be set as a vertical template of the stroke. By analogy, you can construct a template for strokes and strokes. As shown in Figure 5. Template 1 represents the stroke of the stroke, template 2 represents the stroke vertical, and template 3 represents the stroke point. The size of the template m, Wm*Hm (m=1, 2, 3), depends on the size of the normalized character stroke.

3, set the template matching area

The template matching area of each group of similar characters is set according to the position and size of the area where the similar characters are different. O and D, 8 and B are different in the left half, 2 and Z are different in the upper half, and 1 and I are different in the upper half. As shown in Fig. 6, the separable domains of O and D, 8 and B are left half images. The separable domains of 2 and Z are the upper 1/3 images, and the separable domains of 1 and I are the upper intermediate positions.

4, template matching

When the stroke template matching is performed, the preset stroke template and the matching area corresponding to the similar characters are selected according to the initial recognition result of the characters described above. Assuming that the recognition result is 2 and Z, the stroke template 1 is selected, and the matching area is the upper half of the character. When the template is matched, the stroke template slides from the upper left corner to the lower right corner of the matching area corresponding to the character, calculates the matching result of each sliding, and counts the maximum matching value max_I of the template m in the matching area, as shown in equation (5). .

Among them, x_Start, x_End, y_Start, y_End are four vertices that can be divided into domains. Max_I table Shows the largest match value.

Comparing the magnitude of max_I with the empirical threshold T(m), it is determined whether there is a stroke represented by the template in the matching region, as in equation (6). For example, for characters 2 and Z, if there is a stroke in the matching area, the character to be recognized is considered to be Z, otherwise it is 2.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided by the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. in. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that The technical solutions described in the embodiments are modified, or the equivalents of the technical features are replaced by the equivalents of the technical solutions of the embodiments of the present invention.

Claims

A method for identifying a banknote crown number, characterized in that it comprises:

Obtaining the image of the crown of the banknote;

Performing character cutting processing on the crown image to obtain a plurality of character images;

Scaling all of the character images into a preset same size;

Extracting a feature vector of the character image;

Performing character recognition on the character image according to the feature vector and a pre-trained classifier model to obtain a preliminary recognition result;

Determining whether the preliminary recognition result falls within a preset similar character group, and if so, performing secondary recognition on the character image, and if not, outputting the preliminary recognition result;

The performing secondary recognition on the character image specifically includes the following steps:

Obtaining a preset specific area of the character image according to the preliminary recognition result;

Obtaining a preset stroke template of the character image according to the preliminary recognition result;

Performing sliding matching in the specific area by the stroke template, and using the maximum number of pixels of the character image that is successfully matched as the maximum matching value;

Obtaining, according to the maximum matching value and a preset threshold, a recognition result of the character image in the similar character group as a secondary recognition result;

The secondary recognition result is output.
The banknote crown number recognition method according to claim 1, wherein before the sliding matching in the specific area by the stroke template, the method further comprises:

The character image is binarized.
The banknote crown number recognition method according to claim 1, wherein the stroke template comprises: a stroke horizontal, a stroke vertical, and a stroke point.
The banknote crown number recognition method according to claim 1, wherein the similar character group corresponding to the preliminary recognition result comprises a first similar character and a second similar character;

The obtaining result of the character image in the similar character group according to the maximum matching value and the preset threshold is specifically:

Determining whether the maximum matching value is greater than or equal to a preset threshold, and if yes, the recognition result of the character image is a first similar character, and if not, the recognition result of the character image is a second similar word symbol.
The method for identifying a crown number of a banknote according to claim 1, wherein before the character cutting process is performed on the crown image, the method further comprises:

Image preprocessing of the crown image;

The image preprocessing of the image of the crown number specifically includes:

Denoising the crown image;

Or, performing image rectification processing on the crown image.
The method for identifying a crown number of a banknote according to claim 1, wherein the extracting the feature vector of the character image comprises:

Calculating a gradient map of the character image to obtain a gradient matrix;

Decomposing the gradient matrix in a standard eight direction to obtain a feature matrix;

Convolving the feature matrix with a preset weight matrix to generate a first feature sub-vector;

Generating a second feature sub-vector according to a direction in which the gradient matrix is most decomposed in a standard eight direction and a maximum number thereof, and a direction in which the decomposition value is accumulated the largest and a maximum accumulated value;

The first feature subvector and the second feature subvector are synthesized into the feature vector.
The banknote crown number recognition method according to claim 1, wherein the classifier model is composed of an SMO two classifier, and includes a digital model, an alphabet model, and a numeric and alphabet model;

The classifier model has a corresponding relationship with the position of the character image on the banknote crown number.
The banknote crown number identifying method according to claim 7, wherein the banknote is RMB;

The similar character group includes a first similar character group 0 and D, a second similar character group 8 and B, a third similar character group 1 and I, a fourth similar character group 2 and Z, or a fifth similar character group O and D;

The first digit of the banknote crown number corresponds to the letter model, the fifth digit to the tenth digit correspond to the digital model, and the second digit to the fourth digit correspond to the number and letter model.
The banknote crown number recognition method according to claim 8, wherein the determining whether the preliminary recognition result falls within a preset similar character group is:

It is judged whether the preliminary recognition result is 0, D, 8, B, 1, I, 2, Z or O.
A banknote crown number identifying method according to any one of claims 1 to 9, characterized in that Therefore, scaling all of the character images to a preset same size is specifically:

All of the character images are scaled to a rectangular image of the same size according to interpolation.