Answer sheet correction method and device, readable medium and electronic equipment

Abstract

The present disclosure relates to a test paper correction method and device, readable medium and electronic equipment, and relates to the technical field of image processing. The method comprises: obtaining at least one preset template image corresponding to a target page of a test paper to be corrected; correcting the target page by using feature points of each preset template image and feature points of the target page to obtain at least one feature point correction image; determining a target feature point correction image and a target template image corresponding to the target page according to each feature point correction image and the preset template image corresponding to the feature point correction image; correcting the target page by using a positioning block corresponding to the target page and a positioning block corresponding to the target template image to obtain a positioning block correction image corresponding to the target page; and determining a target correction image corresponding to the target page according to the target feature point correction image and the positioning block correction image. In this way, the correction effect of the test paper can be improved, and the accuracy of test paper matching can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of image processing technology, and more specifically, to an answer sheet correction method, apparatus, readable medium, and electronic device. Background Technology

[0002] The intelligent recognition of answer sheets can accurately, quickly, and conveniently achieve fully automatic recognition and grading of student test papers. During the answer sheet grading process, the answer sheet needs to be aligned with the template image. This allows the template image's modeling information to be applied to the answer sheet, thereby completing the correction of the answer sheet.

[0003] In related technologies, keypoint correction techniques are used to correct answer sheets to match the template image. Keypoint correction requires extracting local image feature points and feature description vectors from both the answer sheet and the template image, and then correcting the answer sheet based on these local feature points and feature description vectors. However, answer sheets may contain areas with sparse texture or highly repetitive content. This results in low accuracy of the extracted local image feature points, leading to poor correction and consequently, low matching accuracy. Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Firstly, this disclosure provides a method for correcting answer sheets, the method comprising:

[0006] Obtain at least one preset template image corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images;

[0007] The target page is corrected by using the feature points of each preset template image and the feature points of the target page to obtain at least one feature point corrected image;

[0008] Based on each feature point correction image and the corresponding preset template image, determine the target feature point correction image and the target template image corresponding to the target page;

[0009] The target page is corrected by using the positioning blocks corresponding to the target page and the positioning blocks corresponding to the target template image to obtain the positioning block corrected image of the target page;

[0010] Based on the target feature point correction image and the positioning block correction image, the target correction image corresponding to the target page is determined.

[0011] Secondly, this disclosure provides an answer sheet correction device, the device comprising:

[0012] The template image acquisition module is used to acquire at least one preset template image corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images;

[0013] The first corrected image acquisition module is used to correct the target page by using the feature points of each preset template image and the feature points of the target page, so as to obtain at least one feature point corrected image;

[0014] The second corrected image acquisition module is used to determine the target feature point corrected image and the target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image;

[0015] The third correction image acquisition module is used to correct the target page using the positioning block corresponding to the target page and the positioning block corresponding to the target template image, so as to obtain the positioning block correction image corresponding to the target page;

[0016] The target correction image acquisition module is used to determine the target correction image corresponding to the target page based on the target feature point correction image and the positioning block correction image.

[0017] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the method described in the first aspect of this disclosure.

[0018] Fourthly, this disclosure provides an electronic device, comprising:

[0019] A storage device on which computer programs are stored;

[0020] A processing device for executing the computer program in the storage device to implement the steps of the method described in the first aspect of this disclosure.

[0021] Through the above technical solution, this disclosure first obtains at least one preset template image corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; the target page is corrected by using feature points of each preset template image and feature points of the target page to obtain at least one feature point corrected image; based on each feature point corrected image and the preset template image corresponding to the feature point corrected image, the target feature point corrected image and the target template image corresponding to the target page are determined; the target page is corrected by using the positioning block corresponding to the target page and the positioning block corresponding to the target template image to obtain the positioning block corrected image corresponding to the target page; based on the target feature point corrected image and the positioning block corrected image, the target corrected image corresponding to the target page is determined. This disclosure first obtains the target feature point correction image corresponding to the answer sheet through feature point correction, and then obtains the positioning block correction image corresponding to the answer sheet through positioning block correction. Then, based on the target feature point correction image and the positioning block correction image, the target correction image corresponding to the target page is determined. In this way, the answer sheet can be corrected by combining feature point correction and positioning block correction, which improves the effect of answer sheet correction and thus improves the accuracy of answer sheet matching.

[0022] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0023] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0024] Figure 1 This is a flowchart illustrating an answer sheet correction method according to an exemplary embodiment;

[0025] Figure 2 This is a flowchart illustrating another answer sheet correction method according to an exemplary embodiment;

[0026] Figure 3 This is a schematic diagram of the structure of an answer sheet correction device according to an exemplary embodiment;

[0027] Figure 4 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0030] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0033] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0034] Figure 1 This is a flowchart illustrating an answer sheet correction method according to an exemplary embodiment, such as... Figure 1 As shown, the method may include:

[0035] S101. Obtain at least one preset template image corresponding to the target page of the answer sheet to be corrected.

[0036] The answer sheet can be a student's completed answer sheet, and can include at least one page. The preset template image can be a blank answer sheet when no answers are given, and different pages of the answer sheet correspond to different preset template images. The target page can be any page of the answer sheet, and this disclosure does not limit it.

[0037] In this step, at least one preset template image corresponding to the answer sheet can be pre-stored. If the answer sheet has multiple pages, a preset template image corresponding to each page of the answer sheet can be pre-stored. If there are multiple preset template images pre-stored, the preset template image corresponding to the target page of the answer sheet cannot be directly determined. Therefore, when it is necessary to correct the target page of the answer sheet, at least one preset template image corresponding to the target page of the answer sheet to be corrected can be obtained first.

[0038] S102. The target page is corrected by using the feature points of each preset template image and the feature points of the target page to obtain at least one feature point corrected image.

[0039] In this step, after obtaining at least one preset template image corresponding to the target page of the answer sheet to be corrected, feature points of each preset template image can be obtained. Then, the target page can be corrected using existing feature point correction methods based on the feature points of the preset template image and the feature points of the target page, thus obtaining the feature point correction model corresponding to the target page. For example, the feature points can be SIFT features, SURF features, AKAZE features, or ORB features, or other image feature points based on deep learning in existing technologies. This disclosure does not limit the type of feature points.

[0040] S103. Based on the corrected image of each feature point and the preset template image corresponding to the corrected image of that feature point, determine the corrected image of the target feature point and the target template image corresponding to the target page.

[0041] In this step, after obtaining at least one feature point corrected image corresponding to the target page, the similarity between the feature point corrected image and the preset template image corresponding to the feature point corrected image can be determined for each feature point corrected image. The feature point corrected image with the highest similarity is taken as the target feature point corrected image, and the preset template image corresponding to the target feature point corrected image is taken as the target template image.

[0042] In one possible implementation, for each feature point correction image, the matching value between the feature point correction image and the preset template image corresponding to the feature point correction image can be obtained. The feature point correction image with the largest matching value is taken as the target feature point correction image corresponding to the target page, and the preset template image corresponding to the target feature point correction image is taken as the target template image corresponding to the target page.

[0043] S104. The target page is corrected by using the positioning blocks corresponding to the target page and the positioning blocks corresponding to the target template image to obtain the positioning block corrected image corresponding to the target page.

[0044] In this step, after obtaining the target feature point correction image and the target template image corresponding to the target page, the positioning block corresponding to the target page and the positioning block corresponding to the target template image can be obtained. Using the existing positioning block correction method, the target page is corrected according to the positioning block corresponding to the target page and the positioning block corresponding to the target template image to obtain the positioning block correction image corresponding to the target page.

[0045] S105. Based on the target feature point correction image and the positioning block correction image, determine the target correction image corresponding to the target page.

[0046] In this step, after determining the target feature point correction image and the positioning block correction image corresponding to the target page, the correction image most similar to the target template image can be determined from the target feature point correction image and used as the target correction image corresponding to the target page. For example, if the target feature point correction image is most similar to the target template image, then the target feature point correction image can be determined as the target correction image.

[0047] In one possible implementation, a first matching value can be determined between the target feature point correction image and the target template image, a second matching value can be determined between the localization block correction image and the target template image, and the correction image corresponding to the largest matching value among the first and second matching values ​​can be used as the target correction image corresponding to the target page.

[0048] Using the above method, the target feature point correction image corresponding to the answer sheet is obtained through feature point correction, and the positioning block correction image corresponding to the answer sheet is obtained through positioning block correction. Then, based on the target feature point correction image and the positioning block correction image, the target correction image corresponding to the target page is determined. In this way, the answer sheet can be corrected by combining feature point correction and positioning block correction, which improves the effect of answer sheet correction and thus improves the accuracy of answer sheet matching.

[0049] Figure 2 This is a flowchart illustrating another answer sheet correction method according to an exemplary embodiment, such as... Figure 2 As shown, the method may include:

[0050] S201. Obtain at least one preset template image corresponding to the target page of the answer sheet to be corrected.

[0051] The answer sheet can be a student's completed answer sheet, and can include at least one page. The preset template image can be a blank answer sheet when no answers are given, and different pages of the answer sheet correspond to different preset template images. The target page can be any page of the answer sheet, and this disclosure does not limit it.

[0052] S202. The target page is corrected by using the feature points of each preset template image and the feature points of the target page to obtain at least one feature point corrected image.

[0053] S203. For each feature point correction image, obtain the matching value between the feature point correction image and the corresponding preset template image.

[0054] In this step, after obtaining at least one feature point corrected image corresponding to the target page, the number of first pixels corresponding to the printed image in the preset template image can be determined. Based on the feature point corrected image and the preset template image corresponding to the feature point corrected image, the number of second pixels corresponding to the printed image in the feature point corrected image is determined. The ratio of the number of second pixels to the number of first pixels is determined, and the ratio is used as the matching value between the feature point corrected image and the preset template image corresponding to the feature point correction.

[0055] Before determining the number of first pixels corresponding to the printed text image in the preset template image and the number of second pixels corresponding to the printed text image in the feature point correction image, Gaussian filtering can be applied to the preset template image and the feature point correction image. Then, dilation operation can be performed on the Gaussian-filtered preset template image and the feature point correction image to remove noise from them.

[0056] After removing noise from the preset template image and the feature point correction image, the number of first pixels corresponding to the printed image in the preset template image can be determined using existing techniques. Then, the preset template image corresponding to the feature point correction image can be binarized to obtain a binarized template image. The feature point correction image can be binarized to obtain a binarized correction image. The binarized template image can be inverted to obtain a binarized inverse template image. The binarized correction image can be inverted to obtain a binarized inverse correction image. The intersection image between the binarized inverse template image and the binarized inverse correction image can be determined, and the number of pixels corresponding to the intersection image can be used as the number of second pixels.

[0057] It should be noted that after inverting the binarized template image, the printed image in the target template image can be placed as the foreground, and the blank image in the target template image can be placed as the background, resulting in the binarized inverse template image. In the binarized inverse template image, the printed image is white (255 pixels), and the blank image is black (0 pixels). Similarly, following the processing method of the binarized template image, the printed image or answer note texture in the binarized corrected image can be placed as the foreground, and the blank image in the binarized corrected image can be placed as the background, resulting in the binarized inverse corrected image. In the binarized inverse corrected image, the printed image and answer note texture are white (255 pixels), and the blank image is black (0 pixels). Next, a bitwise AND operation can be performed on the binarized inverse template image and the binarized inverse corrected image to obtain their intersection image. This intersection image is the intersection of the white pixels in both images, and this intersection of white pixels represents the printed text image in the binarized inverse corrected image. Finally, the number of pixels corresponding to the printed text image in the binarized inverse corrected image can be determined using existing techniques. This number of pixels represents the second number of pixels corresponding to the printed text image in the feature point corrected image.

[0058] Furthermore, after determining the number of first pixels corresponding to the printed image in the preset template image and the number of second pixels corresponding to the printed image in the feature point correction image, the ratio of the number of second pixels to the number of first pixels can be calculated, and the ratio can be used as the matching value between the feature point correction image and the preset template image corresponding to the feature point correction.

[0059] S204. Use the corrected image of the feature point with the largest matching value as the corrected image of the target feature point corresponding to the target page.

[0060] In this step, after obtaining the matching value between each feature point correction image and the corresponding preset template image, the feature point correction image with the largest matching value can be determined and used as the target feature point correction image corresponding to the target page.

[0061] S205. Use the preset template image corresponding to the corrected image of the target feature points as the target template image corresponding to the target page.

[0062] S206. The target page is corrected by using the positioning blocks corresponding to the target page and the positioning blocks corresponding to the target template image to obtain the positioning block corrected image corresponding to the target page.

[0063] S207. Determine the first matching value between the corrected image of the target feature points and the target template image.

[0064] In this step, the method of obtaining the matching value between the feature point correction image and the corresponding preset template image in step S203 can be referred to to determine the first matching value between the target feature point correction image and the target template image, which will not be elaborated here.

[0065] S208. Determine the second matching value between the corrected image of the positioning block and the target template image.

[0066] In this step, the method of obtaining the matching value between the feature point correction image and the preset template image corresponding to the feature point correction image in step S203 can be referred to to determine the second matching value between the positioning block correction image and the target template image, which will not be elaborated here.

[0067] S209. The corrected image corresponding to the largest matching value among the first matching value and the second matching value is taken as the target corrected image corresponding to the target page.

[0068] In this step, after obtaining the first matching value between the corrected image of the target feature points and the target template image, and the second matching value between the corrected image of the localization block and the target template image, the first matching value and the second matching value can be compared to determine the largest matching value. The corrected image corresponding to the largest matching value is then used as the target corrected image corresponding to the target page. For example, if the largest matching value is the first matching value, the corrected image of the target feature points corresponding to the first matching value can be used as the target corrected image corresponding to the target page; if the largest matching value is the second matching value, the corrected image of the localization block corresponding to the second matching value can be used as the target corrected image corresponding to the target page.

[0069] Using the above method, the target feature point correction image corresponding to the answer sheet is obtained through feature point correction, and the positioning block correction image corresponding to the answer sheet is obtained through positioning block correction. Then, the correction image with the highest matching degree between the target feature point correction image and the positioning block correction image is used as the target correction image corresponding to the target page. In this way, the answer sheet can be corrected by combining feature point correction and positioning block correction, which improves the correction effect of the answer sheet and thus improves the accuracy of answer sheet matching.

[0070] Figure 3 This is a schematic diagram of the structure of an answer sheet correction device according to an exemplary embodiment, such as... Figure 3 As shown, the device may include:

[0071] The template image acquisition module 301 is used to acquire at least one preset template image corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images;

[0072] The first corrected image acquisition module 302 is used to correct the target page by using the feature points of each preset template image and the feature points of the target page, so as to obtain at least one feature point corrected image;

[0073] The second corrected image acquisition module 303 is used to determine the target feature point corrected image and the target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image;

[0074] The third correction image acquisition module 304 is used to correct the target page by using the positioning block corresponding to the target page and the positioning block corresponding to the target template image to obtain the positioning block correction image corresponding to the target page;

[0075] The target correction image acquisition module 305 is used to determine the target correction image corresponding to the target page based on the target feature point correction image and the positioning block correction image.

[0076] Accordingly, the second corrected image acquisition module 303 is specifically used for:

[0077] For each feature point corrected image, obtain the matching value between the feature point corrected image and the preset template image corresponding to the feature point corrected image;

[0078] The feature point image with the largest matching value is used as the target feature point image corresponding to the target page;

[0079] The preset template image corresponding to the target feature point correction image is used as the target template image corresponding to the target page.

[0080] Accordingly, the second corrected image acquisition module 303 is further configured to:

[0081] Determine the number of first pixels corresponding to the printed image in the preset template image;

[0082] Based on the feature point corrected image and the preset template image corresponding to the feature point corrected image, determine the number of second pixels corresponding to the printed image in the feature point corrected image;

[0083] Determine the ratio of the number of the second pixel to the number of the first pixel, and use the ratio as the matching value between the feature point corrected image and the preset template image corresponding to the feature point correction.

[0084] Accordingly, the second corrected image acquisition module 303 is further configured to:

[0085] The preset template image corresponding to the feature point correction image is binarized to obtain a binarized template image;

[0086] The feature point corrected image is binarized to obtain a binarized corrected image;

[0087] The binarized template image is inverted to obtain a binarized inverse template image, and the binarized corrected image is inverted to obtain a binarized inverse corrected image.

[0088] Determine the intersection image between the binarized inverse template image and the binarized inverse correction image;

[0089] The number of pixels corresponding to the intersection image is taken as the second number of pixels.

[0090] Accordingly, the target correction image acquisition module 305 is specifically used for:

[0091] Determine a first matching value between the target feature point corrected image and the target template image;

[0092] Determine a second matching value between the corrected image of the positioning block and the target template image;

[0093] The corrected image corresponding to the largest matching value among the first matching value and the second matching value is taken as the target corrected image corresponding to the target page.

[0094] Using the aforementioned device, a corrected image of the target feature points corresponding to the answer sheet is obtained through feature point correction, and a corrected image of the positioning blocks corresponding to the answer sheet is obtained through positioning block correction. Then, based on the corrected image of the target feature points and the corrected image of the positioning blocks, the corrected image of the target page is determined. In this way, the answer sheet can be corrected by combining feature point correction and positioning block correction, which improves the effect of answer sheet correction and thus increases the accuracy of answer sheet matching.

[0095] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0096] The following is for reference. Figure 4 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 1The diagram below shows the structure of the terminal device or server 400. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0097] like Figure 4 As shown, electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processing device 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0098] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0099] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined in the methods of embodiments of this disclosure.

[0100] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0101] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0102] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0103] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire at least one preset template image corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; correct the target page using feature points of each preset template image and feature points of the target page to obtain at least one feature point corrected image; determine a target feature point corrected image and a target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image; correct the target page using positioning blocks corresponding to the target page and positioning blocks corresponding to the target template image to obtain a positioning block corrected image corresponding to the target page; and determine a target corrected image corresponding to the target page based on the target feature point corrected image and the positioning block corrected image.

[0104] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0106] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules are not necessarily limiting in certain circumstances; for example, a template image acquisition module can also be described as "acquiring at least one preset template image corresponding to the target page of the answer sheet to be corrected".

[0107] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0108] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0109] According to one or more embodiments of this disclosure, Example 1 provides an answer sheet correction method, comprising: acquiring at least one preset template image corresponding to a target page of an answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; correcting the target page using feature points of each preset template image and feature points of the target page to obtain at least one feature point corrected image; determining a target feature point corrected image and a target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image; correcting the target page using positioning blocks corresponding to the target page and positioning blocks corresponding to the target template image to obtain a positioning block corrected image corresponding to the target page; and determining a target corrected image corresponding to the target page based on the target feature point corrected image and the positioning block corrected image.

[0110] According to one or more embodiments of this disclosure, Example 2 provides the method of Example 1, wherein determining the target feature point correction image and the target template image corresponding to the target page based on each feature point correction image and the preset template image corresponding to the feature point correction image includes: for each feature point correction image, obtaining a matching value between the feature point correction image and the preset template image corresponding to the feature point correction image; taking the feature point correction image with the largest matching value as the target feature point correction image corresponding to the target page; and taking the preset template image corresponding to the target feature point correction image as the target template image corresponding to the target page.

[0111] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 2, wherein obtaining the matching value between the feature point corrected image and the preset template image corresponding to the feature point corrected image includes: determining the number of first pixels corresponding to the printed image in the preset template image; determining the number of second pixels corresponding to the printed image in the feature point corrected image based on the feature point corrected image and the preset template image corresponding to the feature point corrected image; determining the ratio of the number of second pixels to the number of first pixels, and using the ratio as the matching value between the feature point corrected image and the preset template image corresponding to the feature point correction.

[0112] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 3, wherein determining the number of second pixels corresponding to the printed image in the feature point corrected image based on the feature point corrected image and the preset template image corresponding to the feature point corrected image includes: performing binarization processing on the preset template image corresponding to the feature point corrected image to obtain a binarized template image; performing binarization processing on the feature point corrected image to obtain a binarized corrected image; performing an inverted operation on the binarized template image to obtain a binarized inverse template image, and performing an inverted operation on the binarized corrected image to obtain a binarized inverse corrected image; determining the intersection image between the binarized inverse template image and the binarized inverse corrected image; and taking the number of pixels corresponding to the intersection image as the number of second pixels.

[0113] According to one or more embodiments of this disclosure, Example 5 provides a method for any of Examples 1 to 4, wherein determining the target corrected image corresponding to the target page based on the target feature point corrected image and the positioning block corrected image includes: determining a first matching value between the target feature point corrected image and the target template image; determining a second matching value between the positioning block corrected image and the target template image; and taking the corrected image corresponding to the largest matching value among the first matching value and the second matching value as the target corrected image corresponding to the target page.

[0114] According to one or more embodiments of this disclosure, Example 6 provides an answer sheet correction device, comprising: a template image acquisition module, configured to acquire at least one preset template image corresponding to a target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; a first correction image acquisition module, configured to correct the target page by using feature points of each preset template image and feature points of the target page to obtain at least one feature point correction image; a second correction image acquisition module, configured to determine a target feature point correction image and a target template image corresponding to the target page based on each feature point correction image and the preset template image corresponding to the feature point correction image; a third correction image acquisition module, configured to correct the target page by using a positioning block corresponding to the target page and a positioning block corresponding to the target template image to obtain a positioning block correction image corresponding to the target page; and a target correction image acquisition module, configured to determine a target correction image corresponding to the target page based on the target feature point correction image and the positioning block correction image.

[0115] According to one or more embodiments of this disclosure, Example 7 provides the apparatus of Example 6, wherein the second corrected image acquisition module is specifically configured to: for each feature point corrected image, acquire a matching value between the feature point corrected image and a preset template image corresponding to the feature point corrected image; use the feature point corrected image with the largest matching value as the target feature point corrected image corresponding to the target page; and use the preset template image corresponding to the target feature point corrected image as the target template image corresponding to the target page.

[0116] According to one or more embodiments of this disclosure, Example 8 provides an apparatus of Example 6 or Example 7, wherein the target correction image acquisition module is specifically configured to: determine a first matching value between the target feature point correction image and the target template image; determine a second matching value between the positioning block correction image and the target template image; and use the correction image corresponding to the largest matching value among the first matching value and the second matching value as the target correction image corresponding to the target page.

[0117] According to one or more embodiments of the present disclosure, Example 9 provides a computer-readable medium having a computer program stored thereon that, when executed by a processing device, implements the steps of the methods described in Examples 1 to 5.

[0118] According to one or more embodiments of this disclosure, Example 10 provides an electronic device including: a storage device having a computer program stored thereon; and a processing device for executing the computer program in the storage device to implement the steps of the methods described in Examples 1 to 5.

[0119] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0120] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0121] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A method for correcting answer sheets, characterized in that, The method includes: Obtain multiple preset template images corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; The target page is corrected by using the feature points of each preset template image and the feature points of the target page to obtain multiple feature point corrected images; Based on each feature point correction image and the corresponding preset template image, determine the target feature point correction image and the target template image corresponding to the target page; The target page is corrected by using the positioning blocks corresponding to the target page and the positioning blocks corresponding to the target template image to obtain the positioning block corrected image of the target page; Based on the target feature point correction image and the positioning block correction image, determine the target correction image corresponding to the target page; The step of determining the target feature point corrected image and target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image includes: For each feature point corrected image, obtain the matching value between the feature point corrected image and the preset template image corresponding to the feature point corrected image; The feature point image with the largest matching value is used as the target feature point image corresponding to the target page; The preset template image corresponding to the target feature point correction image is used as the target template image corresponding to the target page.

2. The method according to claim 1, characterized in that, The step of obtaining the matching value between the feature point corrected image and the preset template image corresponding to the feature point corrected image includes: Determine the number of first pixels corresponding to the printed image in the preset template image; Based on the feature point corrected image and the preset template image corresponding to the feature point corrected image, determine the number of second pixels corresponding to the printed image in the feature point corrected image; Determine the ratio of the number of the second pixel to the number of the first pixel, and use the ratio as the matching value between the feature point corrected image and the preset template image corresponding to the feature point correction.

3. The method according to claim 2, characterized in that, The step of determining the number of second pixels corresponding to the printed image in the feature point corrected image based on the feature point corrected image and the preset template image corresponding to the feature point corrected image includes: The preset template image corresponding to the feature point correction image is binarized to obtain a binarized template image; The feature point corrected image is binarized to obtain a binarized corrected image; The binarized template image is inverted to obtain a binarized inverse template image, and the binarized corrected image is inverted to obtain a binarized inverse corrected image. Determine the intersection image between the binarized inverse template image and the binarized inverse correction image; The number of pixels corresponding to the intersection image is taken as the second number of pixels.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the target corrected image corresponding to the target page based on the target feature point corrected image and the positioning block corrected image includes: Determine a first matching value between the target feature point corrected image and the target template image; Determine a second matching value between the corrected image of the positioning block and the target template image; The corrected image corresponding to the largest matching value among the first matching value and the second matching value is taken as the target corrected image corresponding to the target page.

5. An answer sheet correction device, characterized in that, The device includes: The template image acquisition module is used to acquire multiple preset template images corresponding to the target page of the answer sheet to be corrected, wherein different pages of the answer sheet correspond to different preset template images; The first corrected image acquisition module is used to correct the target page by using the feature points of each preset template image and the feature points of the target page to obtain multiple feature point corrected images; The second corrected image acquisition module is used to determine the target feature point corrected image and the target template image corresponding to the target page based on each feature point corrected image and the preset template image corresponding to the feature point corrected image; The third correction image acquisition module is used to correct the target page using the positioning block corresponding to the target page and the positioning block corresponding to the target template image, so as to obtain the positioning block correction image corresponding to the target page; The target correction image acquisition module is used to determine the target correction image corresponding to the target page based on the target feature point correction image and the positioning block correction image; The second corrected image acquisition module is specifically used for: For each feature point corrected image, obtain the matching value between the feature point corrected image and the preset template image corresponding to the feature point corrected image; The feature point image with the largest matching value is used as the target feature point image corresponding to the target page; The preset template image corresponding to the target feature point correction image is used as the target template image corresponding to the target page.

6. The apparatus according to claim 5, characterized in that, The target correction image acquisition module is specifically used for: Determine a first matching value between the target feature point corrected image and the target template image; Determine a second matching value between the corrected image of the positioning block and the target template image; The corrected image corresponding to the largest matching value among the first matching value and the second matching value is taken as the target corrected image corresponding to the target page.

7. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by the processing device, the program implements the steps of the method described in any one of claims 1-4.

8. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-4.

Images