WO2021143058A1

WO2021143058A1 - Image-based information comparison method, apparatus, electronic device, and computer-readable storage medium

Info

Publication number: WO2021143058A1
Application number: PCT/CN2020/099066
Authority: WO
Inventors: 罗林锋
Original assignee: 平安国际智慧城市科技股份有限公司
Priority date: 2020-01-15
Filing date: 2020-06-30
Publication date: 2021-07-22
Also published as: CN111259888B; CN111259888A

Abstract

Provided are an image-based information comparison method and apparatus, and a computer-readable storage medium, said method comprising: receiving an image set to be compared, and performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set (S1); classifying said image block set into images, and on the basis of optical character recognition technology, performing type recognition on the image block set after image classification to obtain a multi-type image set (S2); extracting from a database a standard information image set corresponding to the image set to be compared, and comparing the multi-type image set and the standard information image set to obtain an information comparison result of the image set to be compared (S3). The method can achieve a more accurate information comparison function based on image processing.

Description

Image-based information comparison method, device, electronic equipment and computer readable storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 202010041070.7, and the invention title is "image-based information comparison method, device and computer-readable storage medium" on January 15, 2020. All of them The content is incorporated in the application by reference.

Technical field

This application relates to the field of artificial intelligence technology, and in particular to an information comparison method, device, electronic device, and computer-readable storage medium based on image processing.

Background technique

The inventor realizes that the current image information acquisition mostly relies on manual completion or a small part of the use of machine reading. The machine reading still requires manual cooperation. For example, candidates write multiple-choice answers in a specific answer sheet, and then the machine uses matching The algorithm matches the answers in the answer sheet. Because these matching technologies do not involve image processing, they are not highly intelligent, and recognition errors are prone to occur during the recognition process, that is, the recognition accuracy is not high.

Summary of the invention

This application provides an information comparison method, device, electronic device, and computer-readable storage medium based on image processing. Its main purpose is to solve the problem of low intelligence in image information acquisition and easy recognition errors during the recognition process. problem.

In order to achieve the above objectives, an information comparison method based on image processing provided by this application includes:

Receiving an image set to be compared, and performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

Performing image classification on the image block set, and performing type recognition on the image block set after the image classification according to optical character recognition technology to obtain a multi-type image set;

The standard information image set corresponding to the image set to be compared is extracted from the database, and the multi-type image set is compared with the standard information image set to obtain an information comparison result of the image set to be compared.

In addition, in order to achieve the above object, the present application also provides an electronic device including a memory and a processor, and the memory stores an information comparison program based on image processing that can run on the processor. When the image processing-based information comparison program is executed by the processor, the following steps are implemented:

In addition, in order to achieve the above-mentioned object, the present application also provides a computer-readable storage medium on which is stored an information comparison program based on image processing, and the information comparison program based on image processing can be One or more processors are executed to implement the steps of the image processing-based information comparison method as described below:

In addition, in order to achieve the above object, the present application also provides an information comparison device based on image processing, and the sequence of the information comparison device based on image processing includes:

The data receiving and block cutting module is used to: receive the image set to be compared, and perform a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

The classification module is configured to: perform image classification on the image block set to obtain a classified image block set;

The type recognition module is configured to: perform type recognition on the image block set after the image classification according to the optical character recognition technology to obtain a multi-type image set;

The job correction result output module is used to: extract the standard information image set corresponding to the image set to be compared from the database, compare the multi-type image set and the standard information image set to obtain the The result of comparing the information of the image set.

This application divides the image set into multiple small squares through the tilt correction operation and the image block cutting operation, and under the premise of reducing the pressure of subsequent calculations, it also improves the recognition accuracy of subsequent template matching and optical character recognition. At the same time, it first passes the template matching And optical character recognition, and then through the comparison operation to further improve the degree of intelligence of image information acquisition. Therefore, the image processing-based information comparison method, device, and computer-readable storage medium proposed in this application can achieve the purpose of image information acquisition.

Description of the drawings

FIG. 1 is a schematic flowchart of an information comparison method based on image processing provided by an embodiment of this application;

2 is a schematic diagram of the internal structure of an electronic device provided by an embodiment of the application;

FIG. 3 is a schematic diagram of modules of an information comparison program based on image processing in an information comparison device based on image processing provided by an embodiment of the application.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

This application provides an information comparison method based on image processing. Referring to FIG. 1, it is a schematic flowchart of an information comparison method based on image processing provided by an embodiment of this application. The method can be executed by a device, and the device can be implemented by software and/or hardware.

In this embodiment, the information comparison method based on image processing includes:

S1. Receive an image set to be compared, and perform a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set.

Currently, there are more applications for image information acquisition in smart job corrections. Therefore, the correction request includes the job number and date. For example, the user enters a correction request for the third batch of jobs on September 20, 2019.

Further, the number and date of the homework are in a one-to-one correspondence with the homework stored in the pre-built database. For example, a senior high school simulation test for high school three (1) to high school (9) class according to the class The number is divided into 1-9 job numbers. If the user wants to correct the job of the third grade (6) class, he only needs to enter the job number and the job date of the third grade (6) class.

Preferably, the image set to be compared is in the form of a scanned image version, such as the text test papers of the whole class mock examination of the third grade (6) class, which are all collected and placed in the pre-built database.

Because the image set to be compared is generally obtained through image scanning, and image scanning may cause a certain tilt of the obtained image, first perform the tilt correction operation and the image block cutting operation on the image set to be compared .

In detail, performing the tilt correction operation and the image block cutting operation on the image set to be compared to obtain the image block set includes: constructing a plane coordinate system, and arranging the images in the image set to be compared according to the plane The coordinate system is projected, and the images in the image set to be compared are divided according to the scale of the plane coordinate system to obtain a plurality of matrix blocks, and the barycentric coordinates of the plurality of matrix blocks are calculated in turn, according to the pre-built linear equation Adjust the inclination angles of the multiple work matrix blocks with the coordinates of the center of gravity to complete the inclination correction operation.

Further, the linear equation is:

Y=a+bX

Y=c+dX

Among them, b=tgδ,

a, c is an arbitrary constant, the inclination angle [delta] is compared with the center of gravity coordinates, (X, Y) represents the coordinate of the plane coordinate system, the coordinates of the center of gravity (P _{_i,} P _i). The center of gravity coordinate X=P _{i is} brought into the above linear equation to obtain the Y value, and the tilt angle δ is adjusted by the error _{with P i to complete the tilt correction operation.}

Because the entire image is too large, it has a greater impact on the recognition and calculation pressure of the subsequent model. Therefore, it is necessary to perform an image block cutting operation on the image set to be compared. The image block cutting operation includes: mapping the image set to be compared after the tilt correction operation is completed in the plane coordinate system, and leveling the image set to be compared according to a preset number of squares A plurality of image squares are obtained by dividing the squares in the direction and the vertical direction. According to the optical detection technology, it is determined whether there are characters in the image squares, and the image squares with the characters are retained to obtain the image square set.

The optical detection technology can use the principle of optical character recognition or the principle of refractive index change to determine whether there is text in each square. If there are no texts in some squares, it is a square with a blank area, which has little effect on subsequent smart work corrections. Can be removed directly. The principle of changing the refractive index is to emit light rays with the same incident angle in each picture block, and determine whether the deviation of the refraction angle is greater than a threshold value, thereby determining whether there is text in the block.

Specifically, the representation method of the image block set is:

DDL(I,n,B ₁ ((X ₁ ,Y ₁ ),(L ₁ ,W ₁ ),Attri),B ₂ ((X ₂ ,Y ₂ ),(L ₂ ,W ₂ ),Attri,... ,B _n ((X _n ,Y _n ),(L _n ,W _n ),Attri))

Wherein, I is the block number of each block within the image set, n is the total number of blocks of the image set, X _i for each block within the image block position information set in the horizontal direction; Y _i is the each block within the current image block location information in the vertical direction, L _i is the length of the block; W _i is the width of the block; Attri representation attribute box, when Attri is 0, which indicates the block has a character, Attri 1 , It means that there is no text in the box.

S2. Perform image classification on the image block set, and perform type recognition on the image block set after the image classification according to the optical character recognition technology to obtain a multi-type image set.

Preferably, the subject classification of the image block set can be performed based on a subject recognition model of optical character recognition technology (OCR technology). If the image block set contains different subjects (such as Chinese, mathematics, English, etc.), the subject recognition model is used to classify subjects, and the image block set can be split into a set of Chinese subjects and mathematics subjects. Sets, English subject work sets, and other subject work sets.

In detail, the S2 includes: performing character cutting on the data of the image block set to obtain a multi-character image set, extracting character features in the multi-character image set, and comparing the character features with a pre-built feature template library. The template matching obtains the subject assignment set.

Further, the character cutting is to segment the text images in the image block set in units of lines to obtain multiple sets of multi-character image sets in units of lines. Both the character feature extraction method and the character cutting can be completed based on the optical character recognition technology (OCR technology). The template matching may be based on the K-nearest neighbor algorithm for matching.

For example, in homework correction, the question types may include multiple-choice questions, fill-in-the-blank questions, true or false questions, calculation questions, etc., and different question types correspond to different answer forms. For example, multiple-choice questions are written in A, B, C, and D. , True or False questions are judged in the form of right and wrong, so it is extremely necessary to carry out type recognition.

Preferably, the type recognition of the image block set can also be performed based on the type recognition model of the optical character recognition technology (OCR technology). The recognition process of the entire question type is the same as the above S3, and finally a collection of image assignments based on different disciplines is obtained. For example, there are multiple-choice homework image collections and reading comprehension homework image collections under the Chinese language homework collection, and choices under the mathematics homework collection There are multiple-choice homework image collections, judgment homework image collections, etc. under the title homework image collection, calculation homework image collection, and English subject homework collection.

S3. Extract a standard information image set corresponding to the image set to be compared from the database, compare the multi-type image set and the standard information image set to obtain an information comparison result of the image set to be compared .

In detail, the extracting the standard information image set corresponding to the multi-type image set from the answer storage area of the database includes: identifying the question number of the multi-type image set according to the image recognition technology to obtain the question number set, Extracting the same standard information image set as the question number set from a pre-built database according to the question number set.

In detail, the question number set obtained by recognizing the question numbers of the multi-type image set according to the image recognition technology includes: a pre-built projection coordinate system, and performing row-wise segmentation on the multi-type image set to obtain a multi-line image set, The optical character recognition technology is used to recognize the first character at the beginning of each multi-line image set. If the first character is a numeric character, it will be retained, and if the first character is not a numeric character, it will be eliminated until it is recognized. Complete, sum up all the numeric characters to get the question number set.

In a preferred embodiment of the present application, if the fourth question of the homework image set of Chinese subjects with multiple choice questions is matched with the standard information image set of the corresponding question number of the fourth question, if the homework image set of multiple choice questions is the first If the 4th question is selected as C, and the fourth question of the standard information image set is also C, the matching is successful. If the 4th question of the multiple-choice job image set is selected as B, the fourth question of the standard information image set is C, Then the match was unsuccessful.

The above-mentioned inventive method may preferably be based on a GPU. The GPU is an image processor, which is a microprocessor that specializes in image operations on personal computers, workstations and some mobile devices. There are many types of the GPU, such as Titan, RTX, etc. The GPU can speed up the correction of the student's homework.

The application also provides an electronic device. Referring to FIG. 2, it is a schematic diagram of the internal structure of an electronic device provided by an embodiment of this application.

In this embodiment, the electronic device 1 may be a PC (Personal Computer, personal computer), or a terminal device such as a smart phone, a tablet computer, or a portable computer, or a server. The electronic device 1 at least includes a memory 11, a processor 12, a communication bus 13, and a network interface 14.

The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, and the like. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart media card (SMC), or a secure digital (SD) Card, Flash Card, etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can be used not only to store application software and various data installed in the electronic device 1, such as the code of the information comparison program 01 based on image processing, etc., but also to temporarily store data that has been output or will be output.

In some embodiments, the processor 12 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip, for running program codes or processing stored in the memory 11 Data, such as information comparison program 01 based on image processing.

The communication bus 13 is used to realize the connection and communication between these components.

The network interface 14 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), and is usually used to establish a communication connection between the device 1 and other electronic devices.

Optionally, the device 1 may also include a user interface. The user interface may include a display (Display) and an input unit such as a keyboard (Keyboard). The optional user interface may also include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visualized user interface.

FIG. 2 only shows the electronic device 1 with components 11-14 and the information comparison program 01 based on image processing. Those skilled in the art will understand that the structure shown in FIG. 1 does not constitute a limitation on the electronic device 1 It may include fewer or more components than shown, or a combination of some components, or a different component arrangement.

In the embodiment of the apparatus 1 shown in FIG. 2, the memory 11 stores an information comparison program 01 based on image processing; when the processor 12 executes the information comparison program 01 stored in the memory 11, the following steps are implemented:

Step 1: Receive an image set to be compared, and perform a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set.

Further, the linear equation is:

Y=a+bX

Y=c+dX

Among them, b=tgδ,

The optical detection technology can use the principle of optical character recognition or the principle of refractive index change to determine whether there is text in each square. If there are no texts in some squares, it is a square with a blank area, which has little effect on subsequent smart work corrections. Can be removed directly. The principle of changing the refractive index is to emit light with the same incident angle in each picture block, and determine whether the deviation of the refraction angle is greater than a threshold value, thereby determining whether there are text in the block.

Specifically, the representation method of the image block set is:

Step 2: Perform image classification on the image block set, and perform type recognition on the image block set after the image classification according to the optical character recognition technology to obtain a multi-type image set.

In detail, the second step includes: cutting the data of the image block set to obtain a multi-character image set, extracting character features in the multi-character image set, and combining the character features with a pre-built feature template library Perform template matching to get the subject assignment set.

Preferably, the type recognition of the image block set can also be performed based on the type recognition model of the optical character recognition technology (OCR technology). The recognition process of the entire question type is the same as the above S3, and finally a collection of image assignments based on different disciplines is obtained. For example, there are multiple-choice homework image collections and reading comprehension homework image collections under the Chinese language homework collection, and choices under the mathematics homework collection There are multiple-choice homework image collections, judgment homework image collections, etc. under the task homework image collection, calculation homework image collection and English subject homework collection.

Step 3: Extract the standard information image set corresponding to the image set to be compared from the database, compare the multi-type image set and the standard information image set to obtain the information comparison of the image set to be compared result.

Optionally, in other embodiments, the image processing-based information comparison program can also be divided into one or more modules, and the one or more modules are stored in the memory 11 and run by one or more processors ( This embodiment is executed by the processor 12) to complete this application. The module referred to in this application refers to a series of computer program instruction segments that can complete specific functions, and is used to describe the image processing-based information comparison program in an electronic device. The implementation process.

For example, referring to FIG. 3, a schematic diagram of the program modules of the image processing-based information comparison program in an embodiment of the image processing-based information comparison apparatus of this application. In this embodiment, the image processing-based information comparison program The program can be divided into a data receiving and block cutting module 10, a classification module 20, a type recognition module 30, and an information result output module 40. Illustratively:

The data receiving and classification module 10 is configured to receive an image set to be compared, and perform a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set.

The classification module 20 is configured to: perform image classification on the image block set to obtain a classified image block set.

The type recognition module 30 is configured to perform type recognition on the image block set after the image classification according to the optical character recognition technology to obtain a multi-type image set.

The job correction result output module 40 is configured to: extract a standard information image set corresponding to the image set to be compared from the database, compare the multi-type image set and the standard information image set, to obtain the The information comparison result of the image set to be compared.

The functions or operation steps implemented by the program modules such as the data receiving and square cutting module 10, the classification module 20, the type identification module 30, and the information result output module 40 when executed are substantially the same as those in the foregoing embodiment, and will not be repeated here.

In addition, the embodiment of the present application also proposes a computer-readable storage medium. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium stores image processing-based An information comparison program, the image processing-based information comparison program can be executed by one or more processors to implement the following operations:

The image set to be compared is received, and the image set to be compared is subjected to a tilt correction operation and an image block cutting operation to obtain an image block set.

Image classification is performed on the image block set to obtain a classified image block set.

According to the optical character recognition technology, the image block set after the classification of the image is type-recognized to obtain a multi-type image set.

It should be noted that the serial numbers of the foregoing embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. And the terms "include", "include" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, but also includes those elements that are not explicitly included. The other elements listed may also include elements inherent to the process, device, article, or method. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, device, article, or method that includes the element.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including several instructions to make a terminal device (can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims

An information comparison method based on image processing, wherein the method includes:

Receiving an image set to be compared, and performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

Performing image classification on the image block set, and performing type recognition on the image block set after the image classification according to optical character recognition technology to obtain a multi-type image set;

The standard information image set corresponding to the image set to be compared is extracted from the database, and the multi-type image set is compared with the standard information image set to obtain an information comparison result of the image set to be compared.
3. The information comparison method based on image processing according to claim 1, wherein said performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set comprises:

Construct a plane coordinate system, project the images in the image set to be compared according to the plane coordinate system, and divide the images in the image set to be compared according to the scale of the plane coordinate system to obtain multiple matrices piece;

Sequentially calculating the coordinates of the center of gravity of the plurality of matrix blocks;

Adjusting the inclination angles of the multiple operation matrix blocks according to the pre-built linear equation and the center of gravity coordinates to complete the inclination correction operation;

Mapping the image set to be compared on which the tilt correction operation is completed in the plane coordinate system;

Dividing the image set to be compared in a horizontal direction and a vertical direction to obtain a plurality of image squares according to the preset number of squares;

According to the optical detection technology, it is determined whether there are texts in the image blocks, and the image blocks with texts are retained to obtain the image block set.
The method for comparing information based on image processing according to claim 2, wherein the linear equation is:

Y=a+bX

Y=c+dX

Among them, b=tgδ,
a and c are arbitrary constants, δ is the inclination angle corresponding to the center of gravity coordinate, and (X, Y) represents the coordinates in the plane coordinate system.
The information comparison method based on image processing according to claim 3, wherein the coordinates of the center of gravity are (P i , P i ). The center of gravity coordinate X=P i is brought into the above linear equation to obtain the Y value, and the tilt angle δ is adjusted by the error with P i to complete the tilt correction operation.
8. The information comparison method based on image processing according to claim 1, wherein said classifying said image block set comprises:

Performing character cutting on the data of the image block set to obtain a multi-character image set;

Extracting character features in the multi-character image set;

Perform template matching of the character features with a pre-built feature template library to complete the image classification.
The information comparison method based on image processing according to any one of claims 1 to 5, wherein said extracting a standard information image set corresponding to said image set to be compared from said database, and comparing said The multi-type image set and the standard information image set include:

A pre-built projection coordinate system, segmenting the multi-type image set by rows to obtain a multi-row image set;

Using the optical character recognition technology to recognize the first character at the beginning of each multi-line image set;

If the first character is a numeric character, it will be reserved, and if the first character is not a numeric character, it will be removed until the recognition is completed, and all the numeric characters will be collected to obtain a question number set;

Extracting from the answer storage area of the database according to the question number set the same standard information image set as the question number set;

The standard information image set and the multi-type image are compared according to the optical character recognition technology.
An electronic device, wherein the electronic device includes a memory and a processor, the memory stores an information comparison program based on image processing that can be run on the processor, and the information comparison program based on image processing The following steps are implemented when the program is executed by the processor:

Receiving an image set to be compared, and performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

Performing image classification on the image block set, and performing type recognition on the image block set after the image classification according to optical character recognition technology to obtain a multi-type image set;

The standard information image set corresponding to the image set to be compared is extracted from the database, and the multi-type image set is compared with the standard information image set to obtain an information comparison result of the image set to be compared.
8. The electronic device according to claim 7, wherein said performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set comprises:

Construct a plane coordinate system, project the images in the image set to be compared according to the plane coordinate system, and divide the images in the image set to be compared according to the scale of the plane coordinate system to obtain multiple matrices piece;

Sequentially calculating the coordinates of the center of gravity of the plurality of matrix blocks;

Adjusting the inclination angles of the multiple operation matrix blocks according to the pre-built linear equation and the center of gravity coordinates to complete the inclination correction operation;

Mapping the image set to be compared on which the tilt correction operation is completed in the plane coordinate system;

Dividing the image set to be compared in a horizontal direction and a vertical direction to obtain a plurality of image squares according to the preset number of squares;

According to the optical detection technology, it is determined whether there are texts in the image blocks, and the image blocks with texts are retained to obtain the image block set.
The electronic device according to claim 8, wherein the linear equation is:

Y=a+bX

Y=c+dX

Among them, b=tgδ,
a and c are arbitrary constants, δ is the inclination angle corresponding to the center of gravity coordinate, and (X, Y) represents the coordinates in the plane coordinate system.
The electronic device according to claim 9, wherein the coordinates of the center of gravity are (P i , P i ). The center of gravity coordinate X=P i is brought into the above linear equation to obtain the Y value, and the tilt angle δ is adjusted by the error with P i to complete the tilt correction operation.
8. The electronic device according to claim 7, wherein said classifying said image block set into images comprises:

Performing character cutting on the data of the image block set to obtain a multi-character image set;

Extracting character features in the multi-character image set;

Perform template matching of the character features with a pre-built feature template library to complete the image classification.
The electronic device according to any one of claims 7 to 11, wherein said extracting a standard information image set corresponding to said image set to be compared from said database, and comparing said multi-type image set with all The set of standard information images, including:

A pre-built projection coordinate system, segmenting the multi-type image set by rows to obtain a multi-row image set;

Using the optical character recognition technology to recognize the first character at the beginning of each multi-line image set;

If the first character is a numeric character, it will be reserved, and if the first character is not a numeric character, it will be removed until the recognition is completed, and all the numeric characters will be collected to obtain a question number set;

Extracting from the answer storage area of the database according to the question number set the same standard information image set as the question number set;

The standard information image set and the multi-type image are compared according to the optical character recognition technology.
A computer-readable storage medium, wherein an information comparison program based on image processing is stored on the computer-readable storage medium, and the information comparison program based on image processing can be executed by one or more processors to The steps to implement the information comparison method based on image processing as described below:

Receiving an image set to be compared, and performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

Performing image classification on the image block set, and performing type recognition on the image block set after the image classification according to optical character recognition technology to obtain a multi-type image set;

The standard information image set corresponding to the image set to be compared is extracted from the database, and the multi-type image set is compared with the standard information image set to obtain an information comparison result of the image set to be compared.
15. The computer-readable storage medium according to claim 13, wherein said performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set comprises:

Construct a plane coordinate system, project the images in the image set to be compared according to the plane coordinate system, and divide the images in the image set to be compared according to the scale of the plane coordinate system to obtain multiple matrices piece;

Sequentially calculating the coordinates of the center of gravity of the plurality of matrix blocks;

Adjusting the inclination angles of the multiple operation matrix blocks according to the pre-built linear equation and the center of gravity coordinates to complete the inclination correction operation;

Mapping the image set to be compared on which the tilt correction operation is completed in the plane coordinate system;

Dividing the image set to be compared in a horizontal direction and a vertical direction to obtain a plurality of image squares according to the preset number of squares;

According to the optical detection technology, it is determined whether there are texts in the image blocks, and the image blocks with texts are retained to obtain the image block set.
The computer-readable storage medium of claim 14, wherein the linear equation is:

Y=a+bX

Y=c+dX

Among them, b=tgδ,
a and c are arbitrary constants, δ is the inclination angle corresponding to the center of gravity coordinate, and (X, Y) represents the coordinates in the plane coordinate system.
The computer-readable storage medium of claim 15, wherein the center of gravity coordinates are (P i , P i ). The center of gravity coordinate X=P i is brought into the above linear equation to obtain the Y value, and the tilt angle δ is adjusted by the error with P i to complete the tilt correction operation.
15. The computer-readable storage medium of claim 13, wherein said classifying said image block set into images comprises:

Performing character cutting on the data of the image block set to obtain a multi-character image set;

Extracting character features in the multi-character image set;

Perform template matching of the character features with a pre-built feature template library to complete the image classification.
The computer-readable storage medium according to any one of claims 13 to 17, wherein said extracting a standard information image set corresponding to said image set to be compared from said database, and comparing said multiple types of images The set and the standard information image set include:

A pre-built projection coordinate system, segmenting the multi-type image set by rows to obtain a multi-row image set;

Using the optical character recognition technology to recognize the first character at the beginning of each multi-line image set;

If the first character is a numeric character, it will be reserved, and if the first character is not a numeric character, it will be removed until the recognition is completed, and all the numeric characters will be collected to obtain a question number set;

Extracting from the answer storage area of the database according to the question number set the same standard information image set as the question number set;

The standard information image set and the multi-type image are compared according to the optical character recognition technology.
An information comparison device based on image processing, wherein the information comparison device based on image processing includes:

The data receiving and block cutting module is configured to: receive the image set to be compared, and perform a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set;

The classification module is configured to: perform image classification on the image block set to obtain a classified image block set;

The type recognition module is configured to: perform type recognition on the image block set after the image classification according to the optical character recognition technology to obtain a multi-type image set;

The job correction result output module is used to: extract the standard information image set corresponding to the image set to be compared from the database, compare the multi-type image set and the standard information image set to obtain the The result of comparing the information of the image set.
21. The information comparison device based on image processing according to claim 19, wherein said performing a tilt correction operation and an image block cutting operation on the image set to be compared to obtain an image block set comprises:

Construct a plane coordinate system, project the images in the image set to be compared according to the plane coordinate system, and divide the images in the image set to be compared according to the scale of the plane coordinate system to obtain multiple matrices piece;

Sequentially calculating the coordinates of the center of gravity of the plurality of matrix blocks;

Adjusting the inclination angles of the multiple operation matrix blocks according to the pre-built linear equation and the center of gravity coordinates to complete the inclination correction operation;

Mapping the image set to be compared on which the tilt correction operation is completed in the plane coordinate system;

Dividing the image set to be compared in a horizontal direction and a vertical direction to obtain a plurality of image squares according to the preset number of squares;

According to the optical detection technology, it is determined whether there are texts in the image blocks, and the image blocks with texts are retained to obtain the image block set.