Character picture classification method and device and electronic equipment

Abstract

The invention provides a character picture classification method and device and electronic equipment, and the method comprises the steps: carrying out the feature extraction of a character picture, and obtaining feature data; if the picture feature matched with the feature data does not exist in the preset sample library, calculating a current feature value corresponding to the feature data; the current feature value comprises sub-feature values with a preset sequence and preset digits; respectively comparing the sub-feature values with sample feature values corresponding to a plurality of picture classifications with preset digits according to a preset sequence to obtain a comparison result; according to a comparison result, calculating a similarity value of the picture classification corresponding to the current characteristic value; and determining the classification of the to-be-processed character picture according to the similarity value. According to the method, the feature data is divided into the sub-feature values with the preset digits, and then the sub-feature values are compared with the sample feature values corresponding to the various picture classifications with the preset digits according to the preset sequence, so that the classification of the to-be-processed character pictures is determined based on the comparison result, the comparison time is saved, and the classification efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a character image classification method, device and electronic equipment. Background Art

[0002] Currently, character image classification methods typically match the image's feature data with feature data from a pre-set character image library. If a perfect match exists, the character corresponding to the matching feature data in the pre-set character image is assigned the category corresponding to the character image. However, to improve classification accuracy, the number of rows in the pre-set character image library must be continuously expanded, which increases computational complexity and significantly reduces classification efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a character image classification method, device and electronic device to alleviate the technical problem that in order to improve the classification accuracy, the number of rows of the preset character image library needs to be continuously expanded, resulting in an increase in the amount of calculation and a serious decrease in classification efficiency, thereby improving recognition efficiency.

[0004] In a first aspect, an embodiment of the present invention provides a method for classifying character images, comprising: extracting features of an acquired character image to be processed to obtain feature data; matching the feature data with image features in a preset sample library; if no image features matching the feature data exist in the preset sample library, calculating a current feature value corresponding to the feature data; the current feature value includes sub-feature values ​​in a preset order and a preset number of digits; comparing the sub-feature values ​​with sample feature values ​​corresponding to a plurality of image classifications of the preset number of digits in the preset order to obtain a comparison result; calculating a similarity value of the image classification corresponding to the current feature value based on the comparison result; and determining the classification of the character image to be processed based on the similarity value.

[0005] In a preferred embodiment of the present invention, the sample feature values ​​corresponding to the above-mentioned preset number of picture classifications are stored in a feature index table; the above-mentioned feature index table includes: the sample feature values ​​of the above-mentioned preset number of bits and the probability sums corresponding to the above-mentioned sample feature values; the step of comparing the above-mentioned sub-feature values ​​with the sample feature values ​​corresponding to the above-mentioned preset number of picture classifications in the feature index table in the above-mentioned preset order to obtain a comparison result includes: comparing the above-mentioned sub-feature values ​​with the sample feature values ​​of the above-mentioned preset number of bits in the feature index table in the above-mentioned preset order to obtain the above-mentioned probability sums corresponding to each of the above-mentioned sub-feature values; determining the above-mentioned probability sums corresponding to each of the above-mentioned sub-feature values ​​as the above-mentioned comparison result; and the step of calculating the similarity value of the above-mentioned picture classification corresponding to the above-mentioned current feature value based on the above-mentioned comparison result includes: calculating the similarity value of the above-mentioned picture classification corresponding to the above-mentioned current feature value based on the above-mentioned probability sums corresponding to each of the above-mentioned sub-feature values.

[0006] In a preferred embodiment of the present invention, before the step of comparing the above-mentioned sub-feature values ​​with the above-mentioned preset number of sample feature values ​​in the feature index table in the above-mentioned preset order and determining the first probability sum corresponding to the above-mentioned current feature value, the above-mentioned method includes: obtaining sample image features; calculating the sample sub-feature values ​​of each sample image feature and the sub-probability corresponding to the sample sub-feature values; determining the sample feature values ​​of the above-mentioned preset number of bits based on the above-mentioned sample sub-feature values; and summing the sub-probabilities of the sample sub-feature values ​​of the above-mentioned preset number of bits to obtain the above-mentioned probability sum corresponding to the sample feature values ​​of the above-mentioned preset number of bits; and constructing the above-mentioned feature index table based on the sample feature values ​​of the above-mentioned preset number of bits and the above-mentioned probability sum corresponding to the sample feature values ​​of the above-mentioned preset number of bits.

[0007] In a preferred embodiment of the present invention, the step of calculating the similarity value of the above-mentioned image classification corresponding to the above-mentioned current eigenvalue based on the above-mentioned probability sum corresponding to each of the above-mentioned sub-eigenvalues ​​includes: summing the above-mentioned probability sums to obtain a summation result; and determining the above-mentioned summation result as the similarity value of the above-mentioned image classification corresponding to the above-mentioned current eigenvalue.

[0008] In a preferred embodiment of the present invention, before extracting features from the acquired character image to be processed and obtaining feature data, the method includes: normalizing the acquired character image to be processed to obtain the character image to be processed with a preset number of pixels.

[0009] In a preferred embodiment of the present invention, the above-mentioned step of extracting features from the acquired character image to be processed to obtain feature data includes: binarizing the above-mentioned character image to be processed; determining the feature value of each pixel point based on the pixel value of the above-mentioned character image to be processed after binarization; and splicing the above-mentioned feature values ​​of all pixels line by line to obtain the feature data of the above-mentioned character image to be processed.

[0010] In a preferred embodiment of the present invention, the step of determining the category of the character image to be processed based on the similarity value includes: classifying the image with the largest similarity value as the category of the character image to be processed.

[0011] In a second aspect, an embodiment of the present invention further provides a character image classification device, comprising: a feature extraction module, configured to perform feature extraction on an acquired character image to be processed to obtain feature data; a matching module, configured to match the feature data with image features in a preset sample library; a similarity determination module, configured to calculate a current feature value corresponding to the feature data if no image feature matching the feature data exists in the preset sample library; the current feature value includes sub-feature values ​​in a preset order and a preset number of digits; the sub-feature values ​​are compared with sample feature values ​​corresponding to a plurality of image classifications of the preset number of digits in the preset order to obtain a comparison result; based on the comparison result, a similarity value of the image classification corresponding to the current feature value is calculated; and a classification result output module, configured to determine the classification of the character image to be processed based on the similarity value.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the character image classification method.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the character image classification method.

[0014] The embodiment of the present invention provides a method, device and electronic device for character image classification, including: extracting features from an acquired character image to be processed to obtain feature data; matching the feature data with the image features in a preset sample library; if there is no image feature matching the feature data in the preset sample library, calculating the current feature value corresponding to the feature data; the current feature value includes a sub-feature value of a preset order and a preset number of digits; comparing the sub-feature values ​​with the sample feature values ​​corresponding to the preset number of digits of multiple image classifications in the preset order to obtain a comparison result; calculating the similarity value of the image classification corresponding to the current feature value based on the comparison result; and determining the classification of the character image to be processed based on the similarity value. The method divides the feature data into sub-feature values ​​of a preset number of digits, and then compares the sub-feature values ​​with the sample feature values ​​corresponding to the preset number of digits of multiple image classifications in the preset order to obtain a comparison result, thereby saving comparison time and improving classification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flowchart of a character image classification method provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of a flow chart of another character image classification method provided by an embodiment of the present invention;

[0018] Figure 3 A schematic structural diagram of a character image classification device provided by an embodiment of the present invention;

[0019] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0020] Icon: 31 - feature extraction module; 32 - matching module; 33 - similarity determination module; 34 - classification result output module; 41 - processor; 42 - memory; 43 - bus; 44 - communication interface. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0022] The existing technology generally extracts features from the acquired character image to be processed to obtain feature data, then calculates the current feature value corresponding to the feature data, and finally compares each bit of the current feature value with the sample feature values ​​corresponding to multiple preset image classifications to obtain a comparison result; based on the comparison result, calculates the similarity value of the image classification corresponding to the current feature value; and based on the similarity value, determines the classification of the character image to be processed. However, in order to improve the classification accuracy, it is necessary to continuously expand the number of rows in the preset character image library, thereby expanding the sample feature values ​​corresponding to the multiple preset image classifications, resulting in an increase in the amount of calculation and a serious decrease in classification efficiency.

[0023] Based on this, an embodiment of the present invention provides a character image classification method, device and electronic device, which can improve computing efficiency. In order to facilitate understanding of the embodiment of the present invention, the character image classification method is first introduced.

[0024] Example 1

[0025] In an embodiment of the present invention, Figure 1 A flowchart of a character image classification method provided by an embodiment of the present invention.

[0026] Depend on Figure 1 As can be seen, the method includes:

[0027] Step S101: extracting features from the acquired character image to be processed to obtain feature data.

[0028] Step S102: Match the above feature data with the image features in the preset sample library.

[0029] Step S103: If there is no image feature matching the feature data in the preset sample library, calculate the current feature value corresponding to the feature data; the current feature value includes sub-feature values ​​of a preset order and a preset number of digits; compare the sub-feature values ​​with the sample feature values ​​corresponding to the preset number of digits of the plurality of image classifications in the preset order to obtain a comparison result; and calculate the similarity value of the image classification corresponding to the current feature value based on the comparison result.

[0030] In this embodiment, the comparison results are obtained by comparing the above-mentioned sub-eigenvalues ​​with the sample eigenvalues ​​corresponding to the preset number of bits of the multiple image classifications in the above-mentioned preset order, rather than comparing each bit of the above-mentioned current eigenvalue with the sample eigenvalues ​​corresponding to the preset multiple image classifications to obtain the comparison results, thereby significantly improving the calculation efficiency.

[0031] Step S104: determining the classification of the character image to be processed according to the similarity value.

[0032] Here, the step S104 includes: classifying the image with the largest similarity value as the category of the character image to be processed.

[0033] In one embodiment, before extracting features from the acquired character image to be processed and obtaining feature data, the method includes: normalizing the acquired character image to be processed to obtain the character image to be processed with a preset number of pixels.

[0034] Furthermore, the step of extracting features from the acquired character image to be processed to obtain feature data includes: binarizing the above-mentioned character image to be processed; determining the feature value of each pixel point based on the pixel value of the above-mentioned character image to be processed after binarization; and splicing the above-mentioned feature values ​​of all pixels line by line to obtain the feature data of the above-mentioned character image to be processed.

[0035] An embodiment of the present invention provides a method for classifying character images, comprising: extracting features from an acquired character image to be processed to obtain feature data; matching the feature data with image features in a preset sample library; if no image features matching the feature data exist in the preset sample library, calculating a current feature value corresponding to the feature data; the current feature value includes sub-feature values ​​of a preset order and a preset number of digits; comparing the sub-feature values ​​with sample feature values ​​corresponding to a plurality of image classifications of a preset number of digits in the preset order to obtain a comparison result; calculating a similarity value of the image classification corresponding to the current feature value based on the comparison result; and determining the classification of the character image to be processed based on the similarity value. The method divides the feature data into sub-feature values ​​of a preset number of digits, and then compares the sub-feature values ​​with sample feature values ​​corresponding to a plurality of image classifications of a preset number of digits in a preset order to obtain a comparison result, thereby saving comparison time and improving classification efficiency.

[0036] Example 2

[0037] Based on the above embodiments, Figure 2A schematic diagram of a flow chart of another character image classification method provided by an embodiment of the present invention;

[0038] Step S201: extracting features from the acquired character image to be processed to obtain feature data.

[0039] Step S202: Match the above feature data with the image features in the preset sample library.

[0040] Step S203: If there is no image feature matching the feature data in the preset sample library, calculate the current feature value corresponding to the feature data; the current feature value includes sub-feature values ​​of a preset order and a preset number of digits; the sample feature values ​​corresponding to the multiple image classifications of the preset number of digits are stored in a feature index table; the feature index table includes: the sample feature values ​​of the preset number of digits and the probability sums corresponding to the sample feature values; compare the sub-feature values ​​with the sample feature values ​​of the preset number of digits in the feature index table in the preset order to obtain the probability sums corresponding to each of the sub-feature values; determine the probability sums corresponding to each of the sub-feature values ​​as the comparison results; and calculate the similarity values ​​of the image classifications corresponding to the current feature value based on the probability sums corresponding to each of the sub-feature values.

[0041] Step S204: determining the classification of the character image to be processed according to the similarity value.

[0042] In actual operation, before comparing the above sub-feature values ​​with the sample feature values ​​of the above preset number of digits in the feature index table in the above preset order and determining the first probability sum corresponding to the above current feature value, the above method includes: obtaining sample image features; calculating the sample sub-feature values ​​of each sample image feature and the sub-probability corresponding to the sample sub-feature values; determining the sample feature values ​​of the above preset number of digits based on the above sample sub-feature values; and summing the sub-probabilities of the sample sub-feature values ​​of the above preset number of digits to obtain the above probability sum corresponding to the sample feature values ​​of the above preset number of digits; constructing the above feature index table based on the sample feature values ​​of the above preset number of digits and the above probability sum corresponding to the sample feature values ​​of the above preset number of digits. In order to facilitate understanding of the embodiment of the present invention, the following Table 1 provides a feature index table for the embodiment of the present invention:

[0043] Table 1

[0044]

[0045] As can be seen from Table 1 above, the preset number of bits is 4.

[0046] Further, the step of calculating the similarity value of the image classification corresponding to the current eigenvalue according to the sum of probabilities corresponding to each of the above sub-eigenvalues includes: calculating the sum of the sum of probabilities to obtain a sum result; and determining the sum result as the similarity value of the image classification corresponding to the current eigenvalue.

[0047] Here, if the first, second, third, and fourth digits of the sample eigenvalue corresponding to the character "yue" are 0, 0, 0, and 0 respectively, the eigenvalues of the first, second, third, and fourth digits are combined to obtain "0000"; further, the probability that the first digit is 0, the probability that the second digit is 0, the probability that the third digit is 0, and the probability that the fourth digit is 0 are added together to obtain 2.2.

[0048] In this way, the eigenvalues of the character to be recognized are also grouped in groups of 4 bits, and 1024 bits can be divided into 256 groups, thus greatly improving the calculation efficiency.

[0049] An embodiment of the present invention provides a method for classifying character images, including: extracting features from the obtained character image to be processed to obtain feature data; matching the feature data with the image features in a preset sample library; if there is no image feature in the preset sample library that matches the feature data, calculating the current eigenvalue corresponding to the feature data; the current eigenvalue includes sub-eigenvalues in a preset order and a preset number of bits; the sample eigenvalues corresponding to various image classifications of the preset number of bits are stored in a feature index table; the feature index table includes: the sample eigenvalues of the preset number of bits and the sum of probabilities corresponding to the sample eigenvalues; comparing the sub-eigenvalues with the sample eigenvalues of the preset number of bits in the feature index table in the preset order to obtain the sum of probabilities corresponding to each sub-eigenvalue; determining the sum of probabilities corresponding to each sub-eigenvalue as the comparison result; calculating the similarity value of the image classification corresponding to the current eigenvalue according to the sum of probabilities corresponding to each sub-eigenvalue; and determining the classification of the character image to be processed according to the similarity value. This method divides the feature data into sub-eigenvalues of a preset number of bits, and then compares the sub-eigenvalues with the sample eigenvalues corresponding to various image classifications of the preset number of bits in the feature index table in a preset order to obtain the sum of probabilities corresponding to each sub-eigenvalue, so as to determine the classification of the character image to be processed based on the sum of probabilities corresponding to each sub-eigenvalue, further saving the comparison time and improving the classification efficiency.

[0050] Embodiment 3

[0051] On the basis of the above embodiment, Figure 3 This is a schematic structural diagram of a character image classification device provided by an embodiment of the present invention.

[0052] Depend on Figure 3 As can be seen, the device includes:

[0053] The feature extraction module 31 is used to extract features from the acquired character image to be processed to obtain feature data.

[0054] The matching module 32 is used to match the above feature data with the image features in the preset sample library.

[0055] The similarity determination module 33 is used to calculate the current feature value corresponding to the feature data if no image feature matching the feature data exists in the preset sample library; the current feature value includes sub-feature values ​​in a preset order and a preset number of digits; compare the sub-feature values ​​with the sample feature values ​​corresponding to the preset number of digits of the plurality of image classifications in the preset order to obtain a comparison result; and calculate the similarity value of the image classification corresponding to the current feature value based on the comparison result.

[0056] The classification result output module 34 is used to determine the classification of the character image to be processed according to the similarity value.

[0057] Among them, the feature extraction module 31, the matching module 32, the similarity determination module 33 and the classification result output module 34 are connected in sequence.

[0058] The character image classification device provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned character image classification method embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the above-mentioned character image classification device, reference can be made to the corresponding content in the aforementioned method embodiment.

[0059] The embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, it is a structural diagram of the electronic device, wherein the electronic device includes a processor 41 and a memory 42, the memory 42 stores machine executable instructions that can be executed by the processor 41, and the processor 41 executes the machine executable instructions to implement the above-mentioned character image classification method.

[0060] exist Figure 4 In the illustrated embodiment, the electronic device further includes a bus 43 and a communication interface 44 , wherein the processor 41 , the communication interface 44 and the memory 42 are connected via the bus.

[0061] The memory 42 may include a high-speed random access memory (RAM) and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is achieved through at least one communication interface 44 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus may be an ISA bus, a PCI bus, or an EISA bus. The above-mentioned bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0062] Processor 41 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 41. The above processor 41 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory, and the processor 41 reads the information in the memory 42 and completes the steps of the character image classification method of the above embodiment in combination with its hardware.

[0063] An embodiment of the present invention also provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by the processor, the machine-executable instructions prompt the processor to implement the above-mentioned character image classification method. The specific implementation can be found in the aforementioned method embodiment, which will not be repeated here.

[0064] The computer program product of the character image classification method, character image classification device and electronic device provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the above program code can be used to execute the above-mentioned character image classification method in the previous method embodiment. The specific implementation can be referred to the method embodiment and will not be repeated here.

[0065] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0066] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0067] Finally, it should be noted that the above embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention rather than to limit it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field should understand that any technician familiar with this technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention.

Claims

1. A character image classification method, characterized in that: include: Extract features from the acquired character image to be processed to obtain feature data; Matching the feature data with the image features in a preset sample library; If there is no picture feature matching the feature data in the preset sample library, calculating a current feature value corresponding to the feature data; The current feature value includes sub-feature values ​​of a preset order and a preset number of digits; Compare the sub-feature values ​​with the preset sample feature values ​​corresponding to the preset number of digits of the plurality of picture classifications in the preset order to obtain a comparison result; and calculate the similarity value of the picture classification corresponding to the current feature value according to the comparison result; According to the similarity value, the classification of the character image to be processed is determined.

2. The character image classification method according to claim 1, characterized in that: The sample feature values ​​corresponding to the preset number of image classifications are stored in a feature index table; The feature index table includes: the sample feature values ​​of the preset number of digits and the probability sums corresponding to the sample feature values; the steps of comparing the sub-feature values ​​with the sample feature values ​​corresponding to the preset number of digits of multiple picture classifications in the feature index table in the preset order to obtain comparison results include: Compare the sub-feature values ​​with the sample feature values ​​of the preset number of digits in the feature index table respectively in the preset order to obtain the probability sum corresponding to each sub-feature value; Determine the probability sum corresponding to each of the sub-feature values ​​as the comparison result; The step of calculating the similarity value of the image classification corresponding to the current feature value according to the comparison result includes: According to the probability sum corresponding to each of the sub-feature values, a similarity value of the image classification corresponding to the current feature value is calculated.

3. The character image classification method according to claim 2, characterized in that: Before the step of comparing the sub-eigenvalues ​​with the sample eigenvalues ​​of the preset number of bits in the feature index table in the preset order to determine the first probability sum corresponding to the current eigenvalue, the method includes: Obtain sample image features; Calculate the sample sub-feature value of each sample image feature and the sub-probability corresponding to the sample sub-feature value; Determine the sample characteristic values ​​of the preset number of digits according to the sample sub-characteristic values; and sum the sub-probabilities of the sample sub-characteristic values ​​of the preset number of digits to obtain the probability sum corresponding to the sample characteristic values ​​of the preset number of digits; The feature index table is constructed according to the sample feature values ​​of the preset number of bits and the probabilities and corresponding to the sample feature values ​​of the preset number of bits.

4. The character image classification method according to claim 2, characterized in that: The step of calculating the similarity value of the image classification corresponding to the current feature value according to the probability sum corresponding to each of the sub-feature values ​​comprises: Performing sum calculation on the probability sum to obtain a sum result; The summation result is determined as the similarity value of the image classification corresponding to the current feature value.

5. The character image classification method according to claim 1, characterized in that: Before extracting features from the acquired character image to be processed to obtain feature data, the method includes: The acquired character image to be processed is normalized to obtain the character image to be processed with a preset number of pixels.

6. The character image classification method according to claim 1, characterized in that: The step of extracting features from the acquired character image to be processed to obtain feature data includes: Binarization is performed on the character image to be processed; and a feature value of each pixel is determined according to the pixel value of the character image to be processed after the binarization; The characteristic values ​​of all pixels are concatenated row by row to obtain characteristic data of the character image to be processed.

7. The character image classification method according to claim 1, characterized in that: The step of determining the classification of the character image to be processed according to the similarity value comprises: The picture with the largest similarity value is classified and determined as the category of the character picture to be processed.

8. A character image classification device, characterized in that: include: A feature extraction module is used to extract features from the acquired character image to be processed to obtain feature data; A matching module, used to match the feature data with the image features in a preset sample library; A similarity determination module, configured to calculate a current feature value corresponding to the feature data if there is no picture feature matching the feature data in the preset sample library; The current feature value includes sub-feature values ​​of a preset order and a preset number of digits; Compare the sub-feature values ​​with the preset sample feature values ​​corresponding to the preset number of digits of the plurality of picture classifications in the preset order to obtain a comparison result; and calculate the similarity value of the picture classification corresponding to the current feature value according to the comparison result; The classification result output module is used to determine the classification of the character image to be processed according to the similarity value.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the character image classification method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the character image classification method as described in any one of claims 1 to 7.

Images