A correcting auxiliary method, device, system, processing equipment and storage medium

Abstract

Embodiments of the present application provide a correcting auxiliary method, device, system, processing equipment and storage medium. An electronic device can acquire an image of a current correcting page collected by an image collection device; identify the image to obtain an identification result; determine projection parameters of an auxiliary correcting mark based on an answer condition of a question in the current correcting page included in the identification result and a teacher correcting condition corresponding to the question; control a projection device to project the auxiliary correcting mark to a region corresponding to the question according to the projection parameters, so that the teacher corrects based on the auxiliary correcting mark. Since the auxiliary correcting mark can be used to represent the answer condition of the question, after the auxiliary correcting mark is projected to the region corresponding to the question, the teacher can determine the answer condition of the question according to the auxiliary correcting mark, and the teacher does not need to remember the standard answer at all times, so that the workload of the teacher in the correcting process can be reduced, and the teacher correcting is facilitated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of correction assistance, in particular to a correction assistance method, device, system, processing device and storage medium. BACKGROUND

[0002] Correction assistance technology is a technology that can assist teachers in correcting examination papers or homework. For example, in the process of correcting an examination paper or homework by a teacher, an image of a page being corrected can be captured in real time by an image acquisition device, a correction symbol of the teacher is determined from the image, and then the correctness or incorrectness of each question is determined according to the correction symbol.

[0003] In the above-mentioned correction assistance method, the correctness or incorrectness of each question can only be counted after the teacher completes the correction, and the teacher needs to remember the standard answer of each question at all times. Therefore, the workload of the teacher is large and not convenient during the correction process. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a correction assistance method, device, system, processing device and storage medium to reduce the workload of teachers during the correction process and increase the convenience of teachers' correction. The specific technical solutions are as follows:

[0005] In a first aspect, the embodiments of the present application provide a correction assistance method applied to a processing device in a correction assistance system, the correction assistance system further comprising an image acquisition device and a projection device, and the method comprises:

[0006] obtaining an image of a current correction page collected by the image acquisition device;

[0007] identifying the image to obtain an identification result;

[0008] determining projection parameters of an auxiliary correction mark based on a situation of an answer to a question of the current correction page included in the identification result and a teacher correction situation corresponding to the question, wherein the auxiliary correction mark is used to represent the situation of the answer to the question to assist the teacher in correcting the current correction page;

[0009] controlling the projection device to project the auxiliary correction mark to a region corresponding to the question according to the projection parameters.

[0010] Optionally, the step of determining the projection parameters of the auxiliary correction mark based on the situation of the answer to the question of the current correction page included in the identification result and the teacher correction situation corresponding to the question comprises:

[0011] determining whether the identification result includes a correction result and an answer to the question corresponding to the question;

[0012] If the answer exists and the correction result does not exist, matching the answer of the question in the current correction page included in the recognition result with the standard answer corresponding to the question to obtain a matching result; determining the projection parameter of the auxiliary correction mark based on the matching result;

[0013] If the correction result and the answer do not exist, determining that the answer result corresponding to the question is an error result, and determining the projection parameter of the auxiliary correction mark based on the error result;

[0014] If the correction result exists, determining the projection parameter of the auxiliary correction mark based on the correction result.

[0015] Optionally, the step of determining the projection parameter of the auxiliary correction mark based on the matching result comprises:

[0016] If the matching result indicates that the answer is the same as the standard answer, determining the projection parameter of the auxiliary correction mark as a first preset parameter;

[0017] If the matching result indicates that the answer is different from the standard answer, determining the projection parameter of the auxiliary correction mark as a second preset parameter;

[0018] The step of determining the projection parameter of the auxiliary correction mark based on the error result comprises:

[0019] Determining the projection parameter of the auxiliary correction mark as the second preset parameter;

[0020] The step of determining the projection parameter of the auxiliary correction mark based on the correction result comprises:

[0021] If the correction result indicates that the answer is correct, determining the projection parameter of the auxiliary correction mark as the first preset parameter;

[0022] If the correction result indicates that the answer is incorrect, determining the projection parameter of the auxiliary correction mark as the second preset parameter.

[0023] Optionally, the step of identifying the image to obtain a recognition result comprises:

[0024] Determining the position of the answer box of the question in the current correction page according to the position offset of the answer box corresponding to the current correction page and the predetermined calibration parameter corresponding to the current correction page, wherein the position offset is the position offset of the answer area corresponding to the question in the current correction page relative to the answer area corresponding to the question in the base map, the calibration parameter is the position of the answer area corresponding to each question in the base map, and the base map is an image collected in advance from the current correction page without correction.

[0025] performing character recognition based on the position of the answer box corresponding to the question to obtain recognition content, and determining a character result in the recognition content as the answer to the question corresponding to the question;

[0026] recognizing the correction trace in the current correction page to obtain correction content;

[0027] if the correction content includes a preset correction trace, determining the position of the correction trace in the base image based on the position offset and the region of the recognized correction trace, and determining the correction result of the question based on the determined position and the position of the question region determined in advance.

[0028] Optionally, before the step of matching the answer to the question in the current correction page included in the recognition result with the standard answer corresponding to the question to obtain a matching result, the method further comprises:

[0029] for each answer box of a question, determining the position of the answer box in the base image based on the position of the answer box and the position offset;

[0030] based on the position of the answer box in the base image and the position of the answer region corresponding to each question in the base image determined in advance, calculating the overlapping area between the region corresponding to the answer box in the base image and the answer region corresponding to each question in the base image;

[0031] if there is an overlapping area greater than a first preset area, determining the question number corresponding to the answer region in the base image corresponding to the overlapping area as the question number of the question according to the corresponding relationship between the answer region in the base image and the question number recorded in advance;

[0032] determining the standard answer corresponding to the question number as the standard answer corresponding to the question according to the corresponding relationship between the question number and the standard answer recorded in advance.

[0033] Optionally, before the step of determining the position of the answer box of the question in the current correction page based on the position offset of the answer box corresponding to the current correction page and the calibration parameter of the current correction page determined in advance, the method further comprises:

[0034] obtaining a target base image identifier and a target translation and rotation matrix corresponding to the image of the current correction page, wherein the target translation and rotation matrix is used to identify the mapping relationship between the image and the base image corresponding to the target base image identifier;

[0035] According to a pre-established corresponding relationship between a base map identifier and a calibration parameter, a target calibration parameter corresponding to the target base map identifier is determined as a calibration parameter corresponding to the current correction page;

[0036] According to the target translation rotation matrix and the calibration parameter corresponding to the current correction page, a position offset of an answer box corresponding to the current correction page is determined.

[0037] Optionally, the step of obtaining the target base map identifier and the target translation rotation matrix corresponding to the image of the current correction page comprises:

[0038] A motion mark corresponding to the current correction page is obtained, wherein the motion mark is used to represent a content change of the current correction page relative to a previous correction page;

[0039] If the motion mark corresponding to the current correction page is a first motion mark, a base map identifier and a translation rotation matrix corresponding to the previous correction page are taken as the target base map identifier and the target translation rotation matrix respectively, wherein the first motion mark represents that a content change degree of the current correction page relative to the previous correction page is less than a first preset degree;

[0040] If the motion mark corresponding to the current correction page is a second motion mark, the base map identifier corresponding to the previous correction page is taken as the target base map identifier, and the target translation rotation matrix is determined according to an image feature of the current correction page and a feature of a base map image corresponding to the target base map identifier, wherein the second motion mark represents that the content change degree of the current correction page relative to the previous correction page is greater than the first preset degree and less than a second preset degree;

[0041] If the motion mark corresponding to the current correction page is a third motion mark, the target translation rotation matrix is determined according to an image feature of the current correction page and a feature of a base map image corresponding to the target base map identifier, and a base map identifier corresponding to a next page of the previous correction page is taken as the target base map identifier, wherein the third motion mark represents that the content change degree of the current correction page relative to the previous correction page is greater than the second preset degree.

[0042] Optionally, the step of determining a correction trace in a position corresponding to the base map based on the position offset and the region where the correction trace is located, and determining a correction result corresponding to the question based on the determined position and a position of a question region predetermined in advance, comprises:

[0043] For each correction trace, a corresponding position of the correction trace in the base map is determined according to a region where the correction trace is located and the position offset;

[0044] Based on the corresponding position of the correction trace in the base map and positions of the predetermined question regions, an overlapping area between a region corresponding to the correction trace in the base map and the question regions in the base map is calculated;

[0045] If there is an overlapping area greater than the second preset area, a correction result corresponding to the correction trace is determined as a correction result corresponding to a question corresponding to the overlapping area according to a pre-recorded corresponding relationship between correction traces and correction results.

[0046] Optionally, before the step of identifying the image to obtain an identification result, the method further comprises:

[0047] According to a predetermined correction matrix, the obtained image is corrected to obtain a corrected image as an image of the current correction page, wherein the correction matrix is used to correct the image from a tilted view to a vertical view;

[0048] The step of controlling the projection device to project the auxiliary correction mark to the region corresponding to the question according to the projection parameter comprises:

[0049] The step of controlling the projection device to project the auxiliary correction mark to the region corresponding to the question according to the projection parameter comprises:

[0050] Optionally, after the step of obtaining the image of the current correction page collected by the image collection device, the method further comprises:

[0051] The preset identity recognition region in the image is identified to obtain identity information;

[0052] After the step of determining the projection parameter of the auxiliary correction mark based on the answer condition of the question of the current correction page included in the identification result and the teacher correction condition corresponding to the question, the method further comprises:

[0053] The answer condition of the question of the current correction page corresponding to the identity information is recorded.

[0054] Optionally, the method further comprises:

[0055] In the case that the identity information corresponding to the current correction page is inconsistent with the identity information corresponding to the previous correction page, the projection device is controlled to project the identity information corresponding to the current correction page to a preset region.

[0056] In a second aspect, the embodiments of the present application provide a correcting auxiliary device, the device comprising:

[0057] an image acquisition module, configured to acquire an image of a current correcting page collected by the image collection device;

[0058] an image recognition module, configured to recognize the image to obtain a recognition result;

[0059] a parameter determination module, configured to determine a projection parameter of an auxiliary correcting mark based on a situation of an answer to a question in the current correcting page included in the recognition result and a teacher correcting situation corresponding to the question, wherein the auxiliary correcting mark is used to represent the situation of the answer to the question to assist the teacher in correcting the current correcting page;

[0060] a mark projection module, configured to control the projection device to project the auxiliary correcting mark to a region corresponding to the question according to the projection parameter.

[0061] Optionally, the parameter determination module comprises:

[0062] a result judgment sub-module, configured to judge whether the recognition result includes a correcting result corresponding to the question and an answer to the question;

[0063] a first parameter determination sub-module, configured to, if the answer to the question exists and the correcting result does not exist, match the answer to the question in the current correcting page included in the recognition result with a standard answer corresponding to the question to obtain a matching result, and determine the projection parameter of the auxiliary correcting mark based on the matching result;

[0064] a second parameter determination sub-module, configured to, if the correcting result and the answer to the question both do not exist, determine that a result of the answer to the question is an error result, and determine the projection parameter of the auxiliary correcting mark based on the error result;

[0065] a third parameter determination sub-module, configured to, if the correcting result exists, determine the projection parameter of the auxiliary correcting mark based on the correcting result.

[0066] Optionally, the first parameter determination sub-module comprises:

[0067] a first parameter determination unit, configured to, if the matching result indicates that the answer to the question is the same as the standard answer, determine the projection parameter of the auxiliary correcting mark as a first preset parameter;

[0068] a second parameter determination unit, configured to, if the matching result indicates that the answer to the question is different from the standard answer, determine the projection parameter of the auxiliary correcting mark as a second preset parameter.

[0069] The second parameter determining submodule comprises:

[0070] The third parameter determining unit is configured to determine the projection parameter of the auxiliary correction mark as the second preset parameter.

[0071] The third parameter determining submodule comprises:

[0072] The fourth parameter determining unit is configured to determine the projection parameter of the auxiliary correction mark as the first preset parameter if the correction result indicates that the answer is correct.

[0073] The fifth parameter determining unit is configured to determine the projection parameter of the auxiliary correction mark as the second preset parameter if the correction result indicates that the answer is incorrect.

[0074] Optionally, the image recognition module comprises:

[0075] The answer box position determining submodule is configured to determine the position of the answer box of a question in the current correction page according to a position offset of the answer box of the question in the current correction page and a pre-determined calibration parameter corresponding to the current correction page, wherein the position offset is a position offset of a corresponding answer area of the question in the current correction page relative to a corresponding answer area of the question in a base image, and the calibration parameter is a position of the corresponding answer area of the question in the base image, and the base image is an image collected from the current correction page before correction.

[0076] The answer determining submodule is configured to perform character recognition based on the position of the answer box of the question to obtain recognition content, and determine a character result in the recognition content as the answer of the question.

[0077] The correction trace recognizing submodule is configured to recognize correction traces in the current correction page to obtain correction content.

[0078] The correction result determining submodule is configured to determine a position of the correction trace in the base image based on the position offset and a region of the correction trace obtained through recognition if the correction content comprises a preset correction trace, and determine a correction result of the question based on the determined position and a pre-determined position of a question region.

[0079] Optionally, the device further comprises:

[0080] The answer box position determining module is configured to determine, for each answer box of a question, a corresponding position of the answer box in the base image according to a position of the answer box and the position offset.

[0081] an overlapping area calculation module, configured to calculate an overlapping area between the corresponding area of the answer box in the base image and the corresponding answer area of each question in the base image based on the corresponding position of the answer box in the base image and the pre-determined position of the corresponding answer area of each question in the base image;

[0082] a question title and question number determination module, configured to, if the overlapping area is greater than the first pre-set area, determine, according to a pre-recorded corresponding relationship between the answer area in the base image and the question number, the question number corresponding to the answer area in the base image corresponding to the overlapping area as the question title and question number of the question;

[0083] a standard answer determination module, configured to determine, according to a pre-recorded corresponding relationship between the question number and the standard answer, the standard answer corresponding to the question title and question number as the standard answer corresponding to the question.

[0084] Optionally, the device further comprises:

[0085] an identification and matrix acquisition module, configured to acquire a target base image identification and a target translation and rotation matrix corresponding to the image of the current correction page, wherein the target translation and rotation matrix is used to identify a mapping relationship between the image and a base image image corresponding to the target base image identification;

[0086] a calibration parameter determination module, configured to determine, according to a pre-established corresponding relationship between the base image identification and the calibration parameter, a target calibration parameter corresponding to the target base image identification as the calibration parameter corresponding to the current correction page;

[0087] a position offset amount determination module, configured to determine, according to the target translation and rotation matrix and the calibration parameter corresponding to the current correction page, a position offset amount of the answer box corresponding to the current correction page.

[0088] Optionally, the identification and matrix acquisition module comprises:

[0089] a motion mark acquisition submodule, configured to acquire a motion mark corresponding to the current correction page, wherein the motion mark is used to represent content changes of the current correction page relative to a previous correction page;

[0090] a first identification and matrix determination submodule, configured to, if the motion mark corresponding to the current correction page is a first motion mark, take the base image identification and the translation and rotation matrix corresponding to the previous correction page as the target base image identification and the target translation and rotation matrix respectively, wherein the first motion mark represents that the content changes of the current correction page relative to the previous correction page are less than a first pre-set degree;

[0091] a second identifier and matrix determining submodule, configured to, if the motion marker corresponding to the current correction page is a second motion marker, take the bottom image identifier corresponding to the previous correction page as the target bottom image identifier, and determine the target translation rotation matrix according to the image feature of the current correction page and the feature of the bottom image corresponding to the target bottom image identifier, wherein the second motion marker represents that the content change degree of the current correction page relative to the previous correction page is greater than the first preset degree and less than a second preset degree;

[0092] a third identifier and matrix determining submodule, configured to, if the motion marker corresponding to the current correction page is a third motion marker, determine the target translation rotation matrix according to the image feature of the current correction page and the feature of the bottom image corresponding to the target bottom image identifier, and take the bottom image identifier corresponding to the next page of the previous correction page as the target bottom image identifier, wherein the third motion marker represents that the content change degree of the current correction page relative to the previous correction page is greater than the second preset degree.

[0093] Optionally, the correction result determining submodule includes:

[0094] a correction trace position determining unit, configured to, for each correction trace, determine the corresponding position of the correction trace in the bottom image according to the region where the correction trace is located and the position offset;

[0095] a coincidence area calculating unit, configured to calculate the coincidence area between the region corresponding to the correction trace in the bottom image and each question region in the bottom image based on the corresponding position of the correction trace in the bottom image and the positions of the question regions determined in advance;

[0096] a correction result determining unit, configured to, if there is a coincidence area greater than a second preset area, determine the correction result corresponding to the correction trace as the correction result corresponding to the question corresponding to the coincidence area according to the corresponding relationship between the correction trace and the correction result recorded in advance.

[0097] Optionally, the device further includes:

[0098] an image correction module, configured to correct the acquired image according to a correction matrix to obtain a corrected image as the image of the current correction page, wherein the correction matrix is used to correct the image from a tilted view to a vertical view;

[0099] the identifier projection module includes:

[0100] The identification projection sub-module is configured to control the projection device to perform inverse distortion on the auxiliary correction identification based on the correction matrix according to the projection parameter, and project the inverse-distorted auxiliary correction identification to the region corresponding to the question.

[0101] Optionally, the device further comprises:

[0102] The identity information determination module is configured to identify a preset identity recognition region in the image to obtain identity information.

[0103] The device further comprises:

[0104] The answer condition recording module is configured to record the answer condition of the question in the current correction page corresponding to the identity information.

[0105] Optionally, the device further comprises:

[0106] The identity information projection module is configured to control the projection device to project the identity information corresponding to the current correction page to a preset region when the identity information corresponding to the current correction page is inconsistent with the identity information corresponding to the previous correction page.

[0107] In a third aspect, an embodiment of the present application provides a correction auxiliary system, the correction auxiliary system comprising a processing device, an image acquisition device and a projection device, wherein:

[0108] The image acquisition device is configured to acquire an image of a current correction page.

[0109] The processing device is configured to execute the method of any one of the first aspect.

[0110] The projection device is configured to project an auxiliary correction identification to a region corresponding to a question according to the projection parameter.

[0111] In a fourth aspect, an embodiment of the present application provides a processing device, comprising:

[0112] A memory is configured to store a computer program.

[0113] A processor is configured to execute the program stored in the memory to implement the method of any one of the first aspect.

[0114] In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the method of any one of the first aspect.

[0115] The embodiments of the present application have the following beneficial effects:

[0116] In the solution provided in this application embodiment, the electronic device can acquire an image of the current grading page captured by an image acquisition device; perform recognition on the image to obtain a recognition result; based on the recognition result including the answers to the questions on the current grading page and the teacher's grading status corresponding to the questions, determine the projection parameters of the auxiliary grading identifier, wherein the auxiliary grading identifier is used to represent the answers to the questions to assist the teacher in grading the current grading page; and control the projection device to project the auxiliary grading identifier onto the area corresponding to the questions according to the projection parameters. Since the auxiliary grading identifier can be used to represent the answers to the target questions, after projecting the auxiliary grading identifier onto the area corresponding to the questions, the teacher can determine the answers to the target questions based on the auxiliary grading identifier, without needing the teacher to constantly remember the standard answers. Therefore, it can reduce the workload of the teacher in the grading process and increase the convenience for the teacher in grading.

[0117] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0118] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0119] Figure 1 A flowchart illustrating a correction assistance method provided in an embodiment of this application;

[0120] Figure 2 for Figure 1 A specific flowchart of step S103 in the illustrated embodiment;

[0121] Figure 3 for Figure 2 A specific flowchart of step S202 in the illustrated embodiment;

[0122] Figure 4 for Figure 2 A specific flowchart of step S204 in the illustrated embodiment;

[0123] Figure 5 for Figure 1 A specific flowchart of step S102 in the illustrated embodiment;

[0124] Figure 6 Based on Figure 2 A flowchart illustrating a method for determining the standard answer in the illustrated embodiment;

[0125] Figure 7 Based on Figure 5A flowchart of the position offset determination manner of the illustrated embodiment;

[0126] Figure 8 For Figure 7 A specific flowchart of step S701 in the illustrated embodiment;

[0127] Figure 9 For Figure 5 A flowchart of the determination manner of the correction result corresponding to the question in the illustrated embodiment;

[0128] Figure 10 An image acquisition device for image acquisition of the correction object;

[0129] Fig. 11(a) is a schematic diagram of an image acquired by the image acquisition device at an inclined viewing angle;

[0130] Fig. 11(b) is a schematic diagram of the corrected image;

[0131] Figure 12 A schematic diagram of the projection device projecting the auxiliary correction mark after the inverse distortion;

[0132] Figure 13 For Figure 1 A flowchart of the determination manner of the identity information corresponding to the current correction page in the illustrated embodiment;

[0133] Figure 14 For Figure 1 A flowchart of the determination manner of the translation rotation matrix and the base map mark corresponding to the current correction page in the illustrated embodiment;

[0134] Figure 15 For Figure 1 A flowchart of the determination manner of the question answering situation corresponding to the question in the current correction page in the illustrated embodiment;

[0135] Figure 16 For Figure 1 A flowchart of the correction assistance in the illustrated embodiment;

[0136] Figure 17 For Figure 16 A specific flowchart of step S1606 in the illustrated embodiment;

[0137] Figure 18 A structural schematic diagram of a correction assistance device provided by the embodiment of the present application;

[0138] Figure 19 A structural schematic diagram of a correction assistance system provided by the embodiment of the present application;

[0139] Figure 20A structural schematic diagram of an electronic device is provided in the embodiments of the present application. DETAILED DESCRIPTION

[0140] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art based on the present application belong to the scope of protection of the present application.

[0141] In order to reduce the workload of teachers in the correction process and increase the convenience for teachers to correct, the embodiments of the present application provide a correction auxiliary method, device, system, processing device, computer readable storage medium and computer program product. First, a correction auxiliary method provided by the embodiments of the present application will be introduced.

[0142] The correction auxiliary method provided by the embodiments of the present application can be applied to any electronic device that needs to assist teachers to correct, for example, a correction auxiliary device, a correction auxiliary system, etc., which is not specifically limited here. In order to describe clearly, the electronic device is called in the following.

[0143] As shown in Figure 1 A correction auxiliary method applied to a processing device in a correction auxiliary system, the correction auxiliary system further comprising an image acquisition device and a projection device, the method comprising:

[0144] S101, acquiring an image of a current correction page collected by the image acquisition device;

[0145] S102, identifying the image to obtain an identification result;

[0146] S103, determining a projection parameter of an auxiliary correction mark based on an answer condition of a question in the current correction page included in the identification result and a teacher correction condition corresponding to the question;

[0147] The auxiliary correction mark is used to represent the answer condition of the question to assist the teacher to correct the current correction page.

[0148] S104, controlling the projection device to project the auxiliary correction mark to a region corresponding to the question according to the projection parameter.

[0149] It can be seen that in the embodiment of the present application, the electronic device can acquire the image of the current correction page collected by the image collection device; identify the image to obtain an identification result; determine the projection parameter of the auxiliary correction mark based on the answer condition of the question in the current correction page included in the identification result and the teacher correction condition corresponding to the question, wherein the auxiliary correction mark is used to represent the answer condition of the question; and control the projection device to project the auxiliary correction mark to the region corresponding to the question according to the projection parameter. Since the auxiliary correction mark can be used to represent the answer condition of the question, after the auxiliary correction mark is projected to the region corresponding to the question, the teacher can determine the answer condition of the question according to the auxiliary correction mark, without the need for the teacher to remember the standard answer at all times, thereby reducing the workload of the teacher in the correction process and increasing the convenience for the teacher to correct.

[0150] In step S101, the image collection device can collect the image of the current correction page, wherein the image collection device can be a camera, the format of the collected image can be NV21, the image resolution can be 3280*2464, and the current correction page can be a homework book page, a exercise book page or a test paper page, etc., which is not limited here.

[0151] In an implementation manner, the image collection device can continuously collect the image of the current correction page at a preset frequency. For example, the image collection device can continuously collect the image of the current correction page at a frequency of 20HZ.

[0152] After the image collection device collects the image of the current correction page, the electronic device can acquire the collected image, identify the image, and further obtain an identification result, that is, step S102 is executed. The identification result includes the answer condition of the question in the current correction page and the teacher correction condition corresponding to the question. Specifically, the answer condition of the question can be the answer of the question or no answer to the question, and the teacher correction condition corresponding to the question can be the correction result corresponding to the question or no correction to the question.

[0153] As an implementation manner, the electronic device can use a character recognition algorithm to identify the image to obtain the identification result. For example, if the current correction page includes questions 1-5, and the teacher has corrected questions 1-3, the electronic device can use a character recognition algorithm to obtain the answer conditions of questions 1-5, which are B, C, D, A and C, respectively, and the correction results of questions 1-3, which are correct, correct and wrong, respectively.

[0154] To project the auxiliary correction mark, after obtaining the recognition result, the electronic device can determine the projection parameter of the auxiliary correction mark based on the recognition result, that is, step S103 is executed. The auxiliary correction mark can be used to represent the answer condition of the question to assist the teacher in correcting the current correction page. For example, the answer condition can be correct or incorrect. The projection parameter includes the color, shape, size, and position of the auxiliary correction mark.

[0155] As an implementation, the color in the projection parameter can reflect the answer condition of the question represented by the auxiliary correction mark. For example, if the auxiliary correction mark corresponding to the question is the border of the question area, and the colors in the projection parameter corresponding to the correct answer and the incorrect answer are green and red, respectively, for the correct answer, the auxiliary correction mark corresponding to the question is a green border, and for the incorrect answer, the auxiliary correction mark corresponding to the question is a red border.

[0156] In the above step S103, the electronic device can also determine the audio parameter of the auxiliary correction audio based on the answer condition of the question in the current correction page included in the recognition result and the teacher's correction condition corresponding to the question. The audio content of the auxiliary correction audio includes the correct or incorrect answer condition of the question in the current correction page. In this way, in step S104, the electronic device can control the audio playback device to play the auxiliary correction audio according to the audio parameter. The auxiliary correction audio can assist the teacher in correcting the current correction page.

[0157] As an implementation, the audio content of the auxiliary correction audio can be the serial number of the question and the standard answer of the question. For example, if the current correction page includes questions 1-5, and the standard answers of questions 1-5 are A, C, D, B, and C, respectively, the audio content of the auxiliary correction audio can be "Question 1 A, Question 2 C, Question 3 D, Question 4 B, Question 5 C". In this way, the teacher can correct the current correction page according to the audio content of the auxiliary correction audio.

[0158] As another implementation, the audio content of the auxiliary correction audio can be the serial number of the question and the answer condition of the question. Continuing the example in the previous implementation, if the answer answers of questions 1-5 are B, C, D, D, and C, respectively, the answer conditions of questions 1 and 4 are incorrect, and the answer conditions of the remaining questions are correct. The audio content of the auxiliary correction audio can be "Question 1 incorrect, Question 2 correct, Question 3 correct, Question 4 incorrect, Question 5 correct". In this way, the teacher can correct the current correction page according to the audio content of the auxiliary correction audio.

[0159] Since the auxiliary correction mark can reflect the answering condition of the question, the electronic device can control the projection device to project the auxiliary correction mark to the region corresponding to the question according to the projection parameter, that is, step S104 is performed. In this way, the teacher can determine the answering condition of the question according to the auxiliary correction mark corresponding to the question in the correction process.

[0160] For example, if the current correction page includes the multiple-choice questions 1-4, and the standard answers corresponding to the multiple-choice questions 1-4 are C, D, A, and C respectively. Then the electronic device can project “C”, “D”, “A”, and “C” to the regions corresponding to the questions 1-4 respectively. In this way, the teacher can correct the current correction page according to the standard answers corresponding to each question projected to the current correction page.

[0161] It can be seen that, in the embodiment of the present application, since the auxiliary correction mark can be used to represent the answering condition of the question, after the auxiliary correction mark is projected to the region corresponding to the question, the teacher can determine the answering condition of the question according to the auxiliary correction mark, without the teacher remembering the standard answer at all times, so that the workload of the teacher in the correction process can be reduced, and the teacher's correction is facilitated.

[0162] As an implementation manner of the embodiment of the present application, as shown in Figure 2 The step of determining the projection parameter of the auxiliary correction mark based on the answering answer condition of the question included in the recognition result and the teacher correction condition corresponding to the question can include:

[0163] S201, determining whether the recognition result includes the correction result and the answering answer corresponding to the question; if the answering answer exists and the correction result does not exist, performing step S202; if neither the correction result nor the answering answer exists, performing step S203; if the correction result exists, performing step S204;

[0164] In the case where the correction result exists, the electronic device can determine the projection parameter of the auxiliary correction mark according to the answering condition indicated by the correction result. In the case where the correction result does not exist, the electronic device can determine the projection parameter of the auxiliary correction mark according to the answering condition. In order to determine the projection parameter of the auxiliary correction mark, the electronic device can determine whether the recognition result includes the correction result and the answering answer corresponding to the question.

[0165] S202, matching the answering answer of the question of the current correction page included in the recognition result with the standard answer corresponding to the question to obtain a matching result; determining the projection parameter of the auxiliary correction mark based on the matching result;

[0166] If the answer exists and the correction result does not exist, it indicates that the student completes the answer and the teacher does not correct. In order to determine the answer of the question, the electronic device can match the answer of the question in the current correction page with the standard answer corresponding to the question to obtain a matching result.

[0167] The matching result can be matching success or matching failure. If the answer is consistent with the standard answer, the matching success is obtained; if the answer is inconsistent with the standard answer, the matching failure is obtained. After obtaining the matching result, the electronic device can determine the projection parameter of the auxiliary correction mark based on the matching result.

[0168] For example, if the auxiliary correction marks corresponding to the correct answer and the wrong answer are the green frame of the question area and the red frame of the question area respectively. For the question with the matching success, the auxiliary correction mark is the green frame of the question area; for the question with the matching failure, the auxiliary correction mark is the red frame of the question area.

[0169] S203, determining that the answer result corresponding to the question is an error result, and determining the projection parameter of the auxiliary correction mark based on the error result;

[0170] If the correction result and the answer both do not exist, it indicates that the student does not answer and the teacher does not correct. Since the student does not answer, the electronic device can determine that the answer result corresponding to the question is an error result. Further, the electronic device can determine the projection parameter of the auxiliary correction mark based on the error result.

[0171] For example, if the auxiliary correction mark corresponding to the wrong answer is the red frame of the question area, for the question with the correction result and the answer both not existing, the auxiliary correction mark is the red frame of the question area.

[0172] S204, determining the projection parameter of the auxiliary correction mark based on the correction result.

[0173] If the correction result exists, the electronic device will determine the projection parameter of the auxiliary correction mark based on the correction result.

[0174] For example, if the auxiliary correction marks corresponding to the correct answer and the wrong answer are the green frame of the question area and the red frame of the question area respectively. For the question with the corresponding correction result being the correct answer, the auxiliary correction mark is the green frame of the question area; for the question with the corresponding correction result being the wrong answer, the auxiliary correction mark is the red frame of the question area.

[0175] It can be seen that in the embodiments of the present application, the electronic device can determine whether the recognition result includes the correction result corresponding to the question and the answer; if the answer exists and the correction result does not exist, the answer of the question in the current correction page included in the recognition result is matched with the standard answer corresponding to the question to obtain a matching result; the projection parameter of the auxiliary correction mark is determined based on the matching result; if the correction result and the answer do not exist, it is determined that the answer result corresponding to the question is an error result, and the projection parameter of the auxiliary correction mark is determined based on the error result; if the correction result exists, the projection parameter of the auxiliary correction mark is determined based on the correction result. Since in the case where the correction result exists, the electronic device can determine the projection parameter of the auxiliary correction mark according to the answer indicated by the correction result. In the case where the correction result does not exist, the electronic device can determine the projection parameter of the auxiliary correction mark according to the answer. Therefore, in order to determine the projection parameter of the auxiliary correction mark, the electronic device can determine whether the recognition result includes the correction result corresponding to the question and the answer. Then, according to whether the correction result and the answer exist, the projection parameter of the auxiliary correction mark is determined. In this way, the projection parameter of the auxiliary correction mark can be accurately determined.

[0176] As an embodiment of the present application, as shown in Figure 3 The step of determining the projection parameter of the auxiliary correction mark based on the matching result can include:

[0177] S301, determining whether the matching result indicates that the answer and the standard answer are the same; if the matching result indicates that the answer and the standard answer are the same, step S302 is performed; if the matching result indicates that the answer and the standard answer are different, step S303 is performed;

[0178] After the electronic device matches the answer of the question with the standard answer corresponding to the question to obtain a matching result, the electronic device can determine whether the matching result indicates that the answer and the standard answer are the same, and then determine the projection parameter of the auxiliary correction mark.

[0179] S302, determining that the projection parameter of the auxiliary correction mark is a first preset parameter;

[0180] If the matching result indicates that the answer and the standard answer are the same, it means that the answer is correct, and the electronic device can determine that the projection parameter of the auxiliary correction mark is a first preset parameter. The first preset parameter includes the color, shape, size and position of the auxiliary correction mark. For example, in the auxiliary parameters of the auxiliary correction mark, the shape can be a rectangle, the position can be the position of the question, the size can be the same as the area occupied by the question, and the color can be green.

[0181] S303, determine the projection parameter of the auxiliary correction mark as a second preset parameter;

[0182] If the matching result indicates that the answer is different from the standard answer, it means that the answer is wrong, and the electronic device can determine the projection parameter of the auxiliary correction mark as a second preset parameter. The second preset parameter includes the color, shape, size, and position of the auxiliary correction mark. For example, in the auxiliary parameters of the auxiliary correction mark, the shape can be a rectangle, the position can be the position of the question, the size can be the same as the area occupied by the question, and the color can be red.

[0183] As can be seen, in the embodiments of the present application, if the matching result indicates that the answer is the same as the standard answer, the electronic device can determine the projection parameter of the auxiliary correction mark as a first preset parameter; if the matching result indicates that the answer is different from the standard answer, the electronic device can determine the projection parameter of the auxiliary correction mark as a second preset parameter. Since the electronic device can determine whether the projection parameter is the first preset parameter or the second preset parameter according to the matching result, the electronic device can quickly and accurately determine the projection parameter of the auxiliary correction mark in the case where the answer exists and the correction result does not exist.

[0184] As an implementation manner of the embodiments of the present application, the step of determining the projection parameter of the auxiliary correction mark based on the error result can include:

[0185] determining the projection parameter of the auxiliary correction mark as the second preset parameter.

[0186] After the electronic device determines that the answer result of the question is an error result, since the auxiliary correction mark projected according to the second preset parameter can indicate that the answer result is an error result, the electronic device can determine the projection parameter of the auxiliary correction mark as the second preset parameter.

[0187] As can be seen, in the embodiments of the present application, the electronic device can determine the projection parameter of the auxiliary correction mark as the second preset parameter. Since the auxiliary correction mark projected according to the second preset parameter can indicate that the answer result is an error result, the electronic device can determine the projection parameter of the auxiliary correction mark as the second preset parameter. In this way, the electronic device can quickly and accurately determine the projection parameter of the auxiliary correction mark in the case where the correction result and the answer do not exist.

[0188] As an implementation manner of the embodiments of the present application, as shown in Figure 4 the step of determining the projection parameter of the auxiliary correction mark based on the correction result can include:

[0189] S401, determine whether the correction result indicates that the answer is correct; if the correction result indicates that the answer is correct, perform step S402; if the correction result indicates that the answer is incorrect, perform step S403;

[0190] In the case where the correction result exists, the electronic device can determine the projection parameter of the auxiliary correction mark based on the correction result. Specifically, the electronic device can determine whether the correction result indicates that the answer is correct, and then determine the projection parameter of the auxiliary correction mark according to whether the correction result is correct.

[0191] S402, determine that the projection parameter of the auxiliary correction mark is the first preset parameter;

[0192] If the correction result indicates that the answer is correct, since the auxiliary correction mark projected according to the first preset parameter can indicate that the answer result is a correct result, the electronic device can determine that the projection parameter of the auxiliary correction mark is the first preset parameter.

[0193] S403, determine that the projection parameter of the auxiliary correction mark is the second preset parameter.

[0194] If the correction result indicates that the answer is incorrect, since the auxiliary correction mark projected according to the second preset parameter can indicate that the answer result is an incorrect result, the electronic device can determine that the projection parameter of the auxiliary correction mark is the second preset parameter.

[0195] It can be seen that in the embodiments of the present application, if the correction result indicates that the answer is correct, the electronic device can determine that the projection parameter of the auxiliary correction mark is the first preset parameter; if the correction result indicates that the answer is incorrect, the electronic device can determine that the projection parameter of the auxiliary correction mark is the second preset parameter. Since the electronic device can determine whether the projection parameter is the first preset parameter or the second preset parameter according to the correction result, the electronic device can quickly and accurately determine the projection parameter of the auxiliary correction mark in the case where the correction result exists.

[0196] As an implementation manner of the embodiments of the present application, as shown in Figure 5 The step of identifying the image to obtain an identification result can include:

[0197] S501, determining the position of the answer box of a question in the current correction page according to the position offset of the answer box corresponding to the current correction page and the predetermined calibration parameter corresponding to the current correction page;

[0198] The position offset is a position offset of a corresponding answer area of a question in the current correction page relative to a corresponding answer area of the question in the bottom map, the calibration parameter is a position of the corresponding answer area of each question in the bottom map, and the bottom map is an image collected in advance from the current correction page without correction.

[0199] Since the position of the answer box of the question in the bottom map is determined in advance, and the position of the answer area in the current correction page has a position offset relative to the position of the answer area in the bottom map, the electronic device can determine the position of the answer box of the question in the current correction page according to the position offset of the answer box corresponding to the current correction page and the calibration parameter corresponding to the current correction page.

[0200] S502, performing character recognition based on the position of the answer box corresponding to the question to obtain recognition content, and determining a character result in the recognition content as an answer corresponding to the question if the recognition content includes the character result;

[0201] Since the student writes the answer in the answer area when answering, the electronic device can perform character recognition based on the position of the answer box corresponding to the question to obtain recognition content. The area of the answer box corresponding to the question covers the answer area corresponding to the question.

[0202] In an embodiment, the recognition content obtained by character recognition includes a character result. It indicates that the student has completed the answer to the question, and the electronic device can determine the character result as the answer corresponding to the question. For example, if the recognition content corresponding to the question is “B”, since the recognition content includes a character result, the electronic device can determine “B” as the answer corresponding to the question.

[0203] In another embodiment, the recognition content obtained by character recognition does not include a character result. It indicates that the student has not answered the question, and the answer corresponding to the question does not exist.

[0204] S503, recognizing correction traces in the current correction page to obtain correction content;

[0205] In order to determine the correction content of the teacher in the current correction page, the electronic device can recognize the correction traces in the current correction page to obtain the correction content. The correction trace is the handwriting content of the teacher in the current correction page.

[0206] S504, if the correction content includes a preset correction trace, determining a position of the correction trace in the bottom map based on the position offset and a region where the recognized correction trace is located, and determining a correction result corresponding to the question based on the determined position and a position of a preset question region.

[0207] If the correction content includes the preset correction trace, it indicates that the teacher has performed the correction. In order to determine the position where the correction trace should be in the base map, the electronic device can determine the position of the correction trace in the base map corresponding position based on the position offset and the region where the identified correction trace is located. Since the distance between the position of the correction trace and the position of the question region corresponding to the correction trace is close, the electronic device can determine the correction result of the question corresponding to the position based on the determined position and the position of the question region.

[0208] In an embodiment, the preset correction trace includes a correct mark and an incorrect mark. In this way, the teacher can draw a correct mark or an incorrect mark near the question region according to the correct or incorrect answer of the question during the correction process.

[0209] It can be seen that in the embodiments of the present application, the electronic device can determine the position of the answer box of the question in the current correction page according to the position offset of the answer box corresponding to the current correction page and the predetermined calibration parameter corresponding to the current correction page; perform text recognition based on the position of the answer box corresponding to the question to obtain the recognition content, and determine the answer of the question corresponding to the text result as the answer of the question corresponding to the text result if the recognition content includes the text result; recognize the correction trace in the current correction page to obtain the correction content; and if the correction content includes the preset correction trace, determine the position of the correction trace in the base map corresponding position based on the position offset and the region where the identified correction trace is located, and determine the correction result of the question corresponding to the position based on the determined position and the predetermined position of the question region. Since the position of the answer box in the base map is predetermined, the electronic device can determine the position of the answer box in the current correction page according to the position offset and the position of the answer box of the question in the base map, and then perform text recognition on the position of the answer box to obtain the answer condition. Since the position of the question region in the base map is predetermined, the electronic device can determine the position of the correction trace in the base map according to the position offset, and then compare the position with the position of the question region in the base map to determine the question corresponding to the correction trace. In this way, the recognition result can be quickly and accurately determined.

[0210] As an embodiment of the present application, as shown in Figure 6 Before the step of matching the answer of the question in the current correction page including the recognition result with the standard answer corresponding to the question to obtain a matching result, the above method can further include:

[0211] S601, for each answer box of a question, determining the position of the answer box in the base map corresponding position according to the position of the answer box and the position offset;

[0212] Since the position of the answer box corresponding to the question number in the base map is known, and the standard answer corresponding to the question number is also known, in order to determine the question number corresponding to the answer box in the current correction page, and then determine the standard answer according to the question number, the electronic device can determine the position of the answer box in the base map according to the position of the answer box and the position offset for each question.

[0213] S602, based on the position of the answer box in the base map and the position of the answer area corresponding to each question in the base map, calculate the overlapping area between the area corresponding to the answer box in the base map and the answer area corresponding to each question in the base map.

[0214] If the overlapping area between the area where the answer box of the question in the current correction page should be in the base map and the answer area corresponding to the question in the base map is large, it means that the question in the current correction page and the question in the base map are the same question. Therefore, the electronic device can calculate the overlapping area between the area corresponding to the answer box in the base map and the answer area corresponding to each question in the base map.

[0215] For example, if the questions in the base map are question 1-question 5, the electronic device can calculate the overlapping area between the area corresponding to the answer box in the base map and the answer area corresponding to the selected question 1-selected question 5 in the base map, which is 20 pixels, 2100 pixels, 50 pixels, 15 pixels and 30 pixels respectively.

[0216] S603, if there is an overlapping area greater than the first preset area, according to the pre-recorded corresponding relationship between the answer area in the base map and the question number, the question number corresponding to the answer area in the base map corresponding to the overlapping area is taken as the question number of the question;

[0217] In order to determine the question number according to the answer area, the corresponding relationship between the answer area in the base map and the question number can be recorded before matching the answer answer with the standard answer.

[0218] If the overlapping area is greater than the first preset area, it means that the question in the base map corresponding to the overlapping area and the question in the current correction page are the same question. Therefore, the electronic device can take the question number corresponding to the answer area in the base map corresponding to the overlapping area as the question number of the question according to the above corresponding relationship.

[0219] If the first preset area is 2000 pixels in the example in the receiving step S602, the overlapping area between the answer area in the base map corresponding to the question 2 and the area in the base map corresponding to the answer box in the current grading page is greater than the first preset area, the electronic device can take the question number corresponding to the answer area in the base map corresponding to the overlapping area, i.e., 2, as the question number of the question.

[0220] S604, according to the corresponding relationship between the question number and the standard answer recorded in advance, the standard answer corresponding to the question number is determined as the standard answer corresponding to the question.

[0221] In order to determine the standard answer according to the question number, the corresponding relationship between the question number and the standard answer can be recorded before matching the answer with the standard answer.

[0222] After determining the question number of the question, the electronic device can determine the standard answer corresponding to the question number as the standard answer corresponding to the question according to the above corresponding relationship.

[0223] In the example in the step S603, if the standard answers corresponding to the questions 1-5 are A, B, D, C, and A respectively, and the question number is 2, the standard answer corresponding to the question number can be determined as "B".

[0224] It can be seen that in the embodiment of the present application, the electronic device can determine the position of the answer box in the base map according to the position of the answer box and the position offset for each question; calculate the overlapping area between the area in the base map corresponding to the answer box and the answer area corresponding to each question in the base map based on the position of the answer box in the base map and the position of the answer area corresponding to each question in the base map determined in advance; if there is an overlapping area greater than the first preset area, according to the corresponding relationship between the answer area in the base map and the question number recorded in advance, the question number corresponding to the answer area in the base map corresponding to the overlapping area is taken as the question number of the question; according to the corresponding relationship between the question number and the standard answer recorded in advance, the standard answer corresponding to the question number is determined as the standard answer corresponding to the question. If the area in the base map where the answer box of the question in the current grading page should be located is large, the overlapping area between the answer area corresponding to the question in the base map and the answer area corresponding to the question in the base map is large, which means that the question in the current grading page is the same question as the question in the base map. Therefore, the electronic device can calculate the overlapping area between the area in the base map corresponding to the answer box and the answer area corresponding to each question in the base map. The question number corresponding to the answer area in the base map corresponding to the overlapping area greater than the first preset area is taken as the question number. Further, the standard answer corresponding to the question number is taken as the standard answer. In this way, the standard answer corresponding to the question can be quickly and accurately determined.

[0225] As an implementation of an embodiment of the present application, as shown in the above step of determining the position of the answer box of the question in the current correction page according to the position offset of the answer box corresponding to the current correction page and the predetermined calibration parameter corresponding to the current correction page, the above method can further include: Figure 7

[0226] S701, obtaining a target base map identifier and a target translation rotation matrix corresponding to an image of the current correction page;

[0227] The target translation rotation matrix is used to identify the mapping relationship between the image and the base map image corresponding to the target base map identifier.

[0228] The electronic device can obtain a target base map identifier and a target translation rotation matrix corresponding to an image of the current correction page. The target base map identifier can be the page number of the current correction page. The target translation rotation matrix can be determined according to the positions of the corresponding feature points in the base map image corresponding to the target base map identifier.

[0229] S702, determining a target calibration parameter corresponding to the target base map identifier as the calibration parameter corresponding to the current correction page according to the correspondence between the base map identifier and the calibration parameter established in advance;

[0230] In order to determine the calibration parameter corresponding to the base map identifier, the position of the answer box of the base map corresponding to each base map identifier, i.e. the calibration parameter, can be determined before determining the position of the answer box of the question in the current correction page, and then the correspondence between the base map identifier and the calibration parameter is established.

[0231] After obtaining the target base map identifier, the electronic device can determine the target calibration parameter corresponding to the target base map identifier according to the above correspondence, and take the target calibration parameter as the calibration parameter corresponding to the current correction page.

[0232] S703, determining the position offset of the answer box corresponding to the current correction page according to the target translation rotation matrix and the calibration parameter corresponding to the current correction page.

[0233] ​Because the electronic device can map the calibration parameters corresponding to the current grading page according to the mapping relationship indicated by the target translation and rotation matrix, it can obtain the position of the answer box for each question on the current grading page. Thus, the electronic device can determine the position offset of the answer box corresponding to the current grading page based on the position of the answer box for each question on the current grading page and the position of the answer area for each question on the corresponding background page. Therefore, the electronic device can determine the position offset of the answer box corresponding to the current grading page based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page.

[0234] As can be seen, in this embodiment, the electronic device can obtain the target base map identifier and the target translation and rotation matrix corresponding to the image of the current grading page. The target translation and rotation matrix is ​​used to identify the mapping relationship between the image and the base map image corresponding to the target base map identifier. Based on the pre-established correspondence between the base map identifier and the calibration parameters, the target calibration parameters corresponding to the target base map identifier are determined as the calibration parameters corresponding to the current grading page. Based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page, the position offset of the answer box corresponding to the current grading page is determined. Since the electronic device can map the calibration parameters corresponding to the current grading page according to the mapping relationship indicated by the target translation and rotation matrix, the position of the answer box corresponding to each question in the current grading page is obtained. Based on the position of the answer box corresponding to each question in the current grading page, and the position of the answer area corresponding to each question in the base map page corresponding to the current grading page, the position offset of the answer box corresponding to the current grading page is determined. Therefore, the electronic device can determine the position offset of the answer box corresponding to the current grading page based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page. This allows for quick and accurate determination of the position offset of the answer box on the current grading page.

[0235] As one implementation method of this application, such as Figure 8 As shown, the steps described above for obtaining the target base map identifier and target translation / rotation matrix corresponding to the image of the current editing page may include:

[0236] S801, obtain the motion marker corresponding to the current revision page; if the motion marker corresponding to the current revision page is the first motion marker, execute step S802; if the motion marker corresponding to the current revision page is the second motion marker, execute step S803; if the motion marker corresponding to the current revision page is the third motion marker, execute step S804.

[0237] The motion marker is used to characterize the content changes of the current edited page relative to the previous edited page.

[0238] Electronic devices can extract features from the image of the currently edited page and the image of the previously edited page, match the extracted features, and determine motion markers based on the matching results. Since the features extracted from the page image can reflect the page content, the matching result between the features of the currently edited page image and the features of the previously edited page image can reflect the content changes of the currently edited page relative to the previous edited page.

[0239] In order to determine the target base map identifier and target translation and rotation matrix corresponding to the current revision page based on the content changes of the current revision page relative to the previous revision page, the electronic device can obtain the motion markers corresponding to the current revision page.

[0240] S802, the base image identifier and translation / rotation matrix corresponding to the previous batch of modified pages are respectively used as the target base image identifier and the target translation / rotation matrix;

[0241] The first motion marker indicates that the content change of the current edited page relative to the previous edited page is less than a first preset degree.

[0242] Typically, when the object being graded by the teacher is not moving or is moving very little, the movement is marked as the first movement mark, meaning that the change in the content of the current grading page relative to the previous grading page is less than the first preset level.

[0243] Since the content of the current revision page is relatively unchanged from the previous revision page, the base map identifier and translation / rotation matrix corresponding to the current revision page are the same as those of the previous revision page. The electronic device can use the base map identifier and translation / rotation matrix corresponding to the previous revision page as the target base map identifier and the target translation / rotation matrix, respectively.

[0244] S803, the base image identifier corresponding to the previous modified page is used as the target base image identifier; the target translation and rotation matrix is ​​determined based on the image features of the current modified page and the features of the base image corresponding to the target base image identifier.

[0245] The second motion marker indicates that the degree of content change of the current edit page relative to the previous edit page is greater than the first preset degree, and the degree of content change is less than the second preset degree.

[0246] Typically, when the teacher's hand is moving on the object being graded, i.e. when the teacher is grading, or when the object being graded has shifted or rotated to some extent, the movement is marked as the second movement mark. This means that the degree of change in the content of the current grading page relative to the previous grading page is greater than the first preset degree, but less than the second preset degree.

[0247] Since the change in content on the current grading page compared to the previous grading page is caused by the teacher's hand movements, the background image identifiers for the current and previous grading pages are the same. Therefore, the electronic device can use the background image identifier from the previous grading page as the target background image identifier. For example, if the motion marker on the current grading page is the second motion marker, and the background image identifier on the previous grading page is 15, then the electronic device can use 15 as the target background image identifier.

[0248] Since the content of the current revision page has changed compared to the previous revision page, the electronic device can determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base image corresponding to the target base image identifier.

[0249] S804, determine the target translation and rotation matrix based on the image features of the current modified page and the features of the base image corresponding to the target base image identifier; and use the base image identifier corresponding to the next page of the previous modified page as the target base image identifier.

[0250] The third motion marker indicates that the degree of content change of the current edit page relative to the previous edit page is greater than the second preset degree.

[0251] Typically, when a teacher flips through pages of the object being graded, the motion marker is the third motion marker, meaning that the change in content of the current grading page relative to the previous grading page is greater than the second preset level.

[0252] Since the content of the current revision page has changed significantly compared to the previous revision page, the electronic device can determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base image corresponding to the target base image identifier.

[0253] If the current page being modified is the first frame image captured by the image acquisition device, then there is no previous page being modified as a reference. Since the image features corresponding to the same page have a high degree of matching, the electronic device can extract the image features of the current page being modified, match these features with the pre-extracted image features of each base image page, and use the base image identifier corresponding to the base image page with a matching degree greater than a preset matching degree as the target base image identifier.

[0254] If the current correction page is not the first frame image captured by the image acquisition device, since the base image identifier corresponding to the previous correction page has been determined, and teachers usually turn pages backward, the electronic device can use the base image identifier corresponding to the next page of the previous correction page as the target base image identifier.

[0255] For example, if the motion marker corresponding to the current modified page is the third motion marker, and the base map marker corresponding to the previous modified page is 12, then the electronic device can use the base map marker corresponding to the next page of the previous modified page, i.e., 13, as the target base map marker.

[0256] As can be seen, in this embodiment, when the motion marker is a first motion marker or a second motion marker, the electronic device can use the base map identifier corresponding to the previous modified page as the target base map identifier. When the motion marker is a first motion marker, the electronic device can use the translation and rotation matrix corresponding to the previous modified page as the target translation and rotation matrix. When the motion marker is a third motion marker, the electronic device can use the base map identifier corresponding to the next page after the previous modified page as the target base map identifier. Since the electronic device can determine the base map identifier and translation and rotation matrix corresponding to the current modified page based on the motion marker, the base map identifier corresponding to the previous modified page, and the translation and rotation matrix, it can quickly and accurately determine the target base map identifier and the target translation and rotation matrix.

[0257] As one implementation method of this application, such as Figure 9 As shown, the steps described above, which determine the position of the correction mark on the base map based on the position offset and the identified area of ​​the correction mark, and determine the correction result corresponding to the question based on the determined position and the pre-determined position of the question area, may include:

[0258] S901, for each correction mark, determine the position of the correction mark in the base map based on the area where the correction mark is located and the position offset;

[0259] In order to determine the question corresponding to each correction mark, the electronic device can determine the position of each correction mark in the base map based on the area where the correction mark is located and the position offset.

[0260] In this way, since the question area in the base map page is predetermined, the position of the correction mark in the base map can be determined, and then the question corresponding to the correction mark can be determined based on the overlapping area between the determined position and each question area in the base map page.

[0261] S902, based on the position of the correction mark on the base map and the predetermined position of each question area, calculate the overlapping area between the area of ​​the correction mark on the base map and each question area on the base map;

[0262] Since the overlapping area between the area of ​​the correction mark and the area of ​​the question corresponding to the correction mark is usually large, and the question area in the background page is predetermined, the electronic device can calculate the overlapping area between the area of ​​the correction mark in the background and the question area in the background based on the position of the correction mark in the background and the position of each question area.

[0263] For example, if the base map includes questions 1-5, then the overlapping area of ​​the correction marks in the corresponding area of ​​the base map and the area of ​​question 1-question 5 can be calculated, and the overlapping areas are 310 pixels, 50 pixels, 2300 pixels, 30 pixels and 10 pixels respectively.

[0264] S903, if there is an overlapping area larger than the second preset area, the grading result corresponding to the grading mark is determined according to the correspondence between the pre-recorded grading marks and grading results, and is used as the grading result corresponding to the question corresponding to the overlapping area.

[0265] To determine whether a teacher's marking marks correspond to a correct or incorrect answer, the correspondence between the marking marks and the results can be recorded before determining the specific result for each question. For example, a checkmark could correspond to a correct answer, and an error mark to an incorrect answer.

[0266] For correction marks corresponding to overlapping areas larger than the second preset area, the electronic device can determine the correction result corresponding to the correction mark based on the above correspondence, and use the correction result as the correction result corresponding to the question corresponding to the overlapping area.

[0267] In one implementation, if the number of overlapping areas larger than the second preset area is one, the electronic device can determine the correction result corresponding to the correction mark based on the pre-recorded correspondence between the correction mark and the correction result, and use it as the correction result corresponding to the question corresponding to the overlapping area.

[0268] Following the example in step S902, if the second preset area is 2000 pixels and the correction mark is a checkmark, then the electronic device can consider the answer as correct and take it as the correction result for question 3 corresponding to 2300 pixels.

[0269] In another implementation, if there are multiple overlapping areas larger than the second preset area, the electronic device can determine the correction result corresponding to the correction mark based on the pre-recorded correspondence between the correction mark and the correction result, and use it as the correction result corresponding to the question corresponding to the overlapping area larger than the second preset area.

[0270] For example, if the answers to questions 1-3 are all correct, the teacher may mark a checkmark on the area corresponding to question 1-3. This checked area overlaps with the area corresponding to question 1-3, and the overlapping area is greater than a second preset area. The electronic device can then confirm that the answers to questions 1-3 are all correct.

[0271] As can be seen, in this embodiment, the electronic device can determine the position of each correction mark in the background image based on the area where the correction mark is located and its positional offset. Based on the position of the correction mark in the background image and the predetermined positions of each question area, it calculates the overlapping area between the area corresponding to the correction mark in the background image and each question area in the background image. If there is an overlapping area larger than a second preset area, the correction result corresponding to the correction mark is determined according to the pre-recorded correspondence between correction marks and correction results, and this is used as the correction result for the question corresponding to the overlapping area. Since the overlapping area between the area of ​​the correction mark and the area of ​​the question corresponding to the correction mark is usually large, and the question areas in the background image are predetermined, the electronic device can calculate the overlapping area between the area corresponding to the correction mark in the background image and each question area in the background image based on the position of the correction mark in the background image and the position of each question area. Therefore, the electronic device can use the correction result corresponding to the correction mark as the correction result for the question corresponding to the overlapping area larger than the second preset area. This allows for quick and accurate determination of the correction result for the question.

[0272] As one embodiment of this application, before the step of recognizing the image and obtaining the recognition result, the method may further include:

[0273] The acquired image is corrected according to a predetermined correction matrix to obtain a corrected image, which is used as the image of the current revise page. The correction matrix is ​​used to correct the image from a tilted view to a vertical view.

[0274] When an image acquisition device acquires an image of the object to be corrected at an angle, a correction matrix can be determined before image recognition is performed, based on the mapping relationship between the features of the image acquired at the angle and the features of the image acquired at a perpendicular frontal angle.

[0275] A schematic diagram of the image acquisition device acquiring images of the object being reviewed can be shown as follows: Figure 10 As shown, there is a certain angle between the optical axis of the image acquisition device 1001 and the object being modified 1002, so the acquired image is from a tilted perspective.

[0276] In order to correct an image from a tilted viewpoint to a vertical viewpoint, the electronic device can correct the image according to a correction matrix to obtain a corrected image, and use the corrected image as the image of the current page to be corrected.

[0277] A schematic diagram of an image acquired by an image acquisition device from an oblique perspective is shown in Figure 11(a), where the object being corrected is a workbook. Because the image acquisition device acquires the image of the workbook at an oblique angle, the workbook in the image is viewed from an oblique perspective. To convert the oblique perspective image into a vertical perspective image, the electronic device can correct the oblique perspective image shown in Figure 11(a) according to a pre-determined correction matrix, obtaining a corrected image. A schematic diagram of the corrected image is shown in Figure 11(b), where the workbook in the image is viewed from a vertical perspective.

[0278] In one embodiment, the step of controlling the projection device to project the auxiliary correction mark onto the area corresponding to the question according to the projection parameters may include:

[0279] The projection device is controlled to perform anti-distortion on the auxiliary correction mark according to the projection parameters and the correction matrix, and the anti-distortion auxiliary correction mark is projected onto the area corresponding to the question.

[0280] Since the projection device projects the auxiliary correction labels at an angle, it is necessary to correct the distortion of the auxiliary correction labels, projecting them from a vertical perspective onto an angled perspective. Because the angle between the projection device and the object being corrected is the same as the angle between the image acquisition device and the object being corrected, the electronic device can correct the distortion of the auxiliary correction labels based on a correction matrix, and then project the corrected auxiliary correction labels onto the area corresponding to the question.

[0281] A schematic diagram of how a projection device projects the distorted auxiliary correction marks can be shown as follows: Figure 12 As shown, the standard answers for questions 1-6 and 9 are projected onto the corresponding question numbers. The standard answers for questions 1-6 and 9 are C, B, B, C, D, C, and D, respectively. The actual answers for questions 1-6 and 9 are A, B, B, C, C, C, and D, respectively. Question 1 is a question that has already been graded by the teacher, and the grading marks are indicated by diagonal lines. If the grading result corresponding to the diagonal line indicates an incorrect answer, the electronic device can determine that the answer to question 1 is incorrect.

[0282] For questions 2-6 and 9, by comparing the answers to the questions with the standard answers, the electronic device can determine that the answer to question 5 is incorrect, while the answers to questions 2, 3, 4, 6 and 9 are correct.

[0283] The electronic device can determine the projection parameters of the auxiliary marking marks based on the answers to each question. The auxiliary marking marks for questions 1-6 and question 9 are the first auxiliary marking mark 1201, the second auxiliary marking mark 1202, the third auxiliary marking mark 1203, the fourth auxiliary marking mark 1204, the fifth auxiliary marking mark 1205, the sixth auxiliary marking mark 1206, and the seventh auxiliary marking mark 1207, respectively.

[0284] If the color of the auxiliary marking indicator for a question with a correct answer is green, and the color of the auxiliary marking indicator for a question with an incorrect answer is red, then the first auxiliary marking indicator 1201 and the fifth auxiliary marking indicator 1205 will be red question boxes, while the second auxiliary marking indicator 1202, the third auxiliary marking indicator 1203, the fourth auxiliary marking indicator 1204, the sixth auxiliary marking indicator 1206, and the seventh auxiliary marking indicator 1207 will be green question boxes.

[0285] Because the answers to questions 7 and 8 on the current grading page are obscured by the teacher's hand, the image acquisition device cannot determine the answers to these two questions, and therefore cannot determine the projection information of the auxiliary grading labels corresponding to these two questions.

[0286] As can be seen, in this embodiment, the electronic device can correct the acquired image according to a predetermined correction matrix to obtain a corrected image, which serves as the image of the current correction page. The projection device is controlled to perform anti-distortion on the auxiliary correction label based on the correction matrix and projection parameters, and then project the anti-distorted auxiliary correction label onto the area corresponding to the question. To correct the image from a tilted viewpoint to a vertical viewpoint, the electronic device can correct the image according to the correction matrix. Since the projection device projects at a tilted angle, it is necessary to perform anti-distortion on the auxiliary correction label, projecting the vertically oriented auxiliary correction label from a tilted viewpoint. Since the tilt angle between the projection device and the object being corrected is the same as the tilt angle between the image acquisition device and the object being corrected, the electronic device can perform anti-distortion on the auxiliary correction label based on the correction matrix, and then project the anti-distorted auxiliary correction label onto the area corresponding to the question. In this way, the auxiliary correction label can be accurately projected to the corresponding position.

[0287] As one embodiment of this application, after the step of acquiring the image of the current revision page captured by the image acquisition device, the method may further include:

[0288] The image is identified by a preset identity recognition region to obtain identity information;

[0289] To determine the identity information corresponding to the current grading page, the electronic device can identify a preset identity recognition area to obtain the identity information. This identity information can be used to identify the student corresponding to the current grading page. For example, ... Figure 12 As shown, if the identity information corresponding to the current grading page is student A, then the teacher can place a card with "student A" written on it in the preset identity recognition area 1208 so that the electronic device can recognize the preset identity recognition area 1208 and obtain the identity information "student A" corresponding to the current grading page.

[0290] As one implementation method, electronic devices can use text recognition algorithms to recognize text in a preset identity recognition area of ​​an image, obtain text content, and use the text content as identity information.

[0291] In one implementation, after the step of determining the projection parameters of the auxiliary grading identifier based on the identification results including the answers to the questions on the current grading page and the teacher's grading information corresponding to the questions, the method may further include:

[0292] Corresponding to the identity information, the answers to the questions on the current grading page are recorded.

[0293] To determine the student whose answers correspond to the questions on the current grading page, the electronic device records the answers to the questions on the current grading page based on the student's identity information. For example, if the current page contains questions 1-5, and the answers to questions 1-5 are correct, incorrect, correct, correct, and incorrect respectively, and the student's identity information for the current grading page is student A, then the electronic device can record the answers to questions 1-5 as correct, incorrect, correct, correct, and incorrect, respectively, for student A.

[0294] As can be seen, in this embodiment, the electronic device can identify a preset identity recognition area in an image to obtain identity information; corresponding to the identity information, it records the answers to the questions on the current grading page. To determine the student corresponding to the answers to the questions on the current grading page, the electronic device can identify the identity information corresponding to the current grading page, and then, after determining the answers to the questions on the current grading page, record the correspondence between the identity information and the answers to the questions on the current grading page. In this way, the answers to each student can be accurately determined.

[0295] As one embodiment of this application, the above method may further include:

[0296] If the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page, the projection device is controlled to project the identity information corresponding to the current revision page onto a preset area.

[0297] If the identity information on the current grading page is inconsistent with the identity information on the previous grading page, it means that the student on the current grading page is different from the student on the previous grading page. To allow teachers to verify the accuracy of the identity information on the current grading page, electronic devices can control a projector to project the identity information from the current grading page onto a preset area.

[0298] In this way, teachers can compare the identity information corresponding to the current grading page with the identity information projected on the screen. If the identity information corresponding to the current grading page is inconsistent with the identity information projected on the screen, it means that the electronic device has made a mistake in recognizing the identity information on the current grading page. Teachers can correct the electronic device's recognition result of the identity information on the current grading page by manually entering the information.

[0299] For example, if the identity information corresponding to the current grading page is student B, but the identity information projected by the projector is student C, the teacher can change the electronic device's recognition result of the identity information corresponding to the current grading page, i.e., student C, to student B, because the electronic device has misidentified the identity information.

[0300] As one implementation method, if the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page, the electronic device can control the display screen to show the identity information corresponding to the current revision page.

[0301] As another implementation method, if the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page, the electronic device can control the audio playback device to broadcast the identity information corresponding to the current revision page.

[0302] In one implementation, a flowchart illustrating the method for determining the identity information corresponding to the current modification page can be as follows: Figure 13 As shown. Specifically, it may include the following steps:

[0303] S1301, Obtaining correction marks

[0304] Electronic devices can acquire censorship tags to determine whether the censorship tag is an identity verification request.

[0305] S1302, Determine whether it is an identity verification request; if yes, proceed to step S1303; if no, proceed to step S1304.

[0306] Upon receiving a modification tag, the electronic device can determine whether the modification tag is an identity verification request.

[0307] S1303, invoke the identity recognition algorithm;

[0308] If the correction mark is an identity verification request, the electronic device can invoke an identity verification algorithm. Specifically, the electronic device can perform text recognition on a preset identity verification area.

[0309] S1304, Correction Recognition;

[0310] If the markup is not an identity verification request, then the electronic device can perform markup verification.

[0311] S1305, Obtain the recognition result;

[0312] After recognizing the identity information corresponding to the current grading page, the electronic device can obtain the recognition result. The recognition result may contain the identity information or be empty. The identity information can be student ID, name, etc., without specific limitations.

[0313] S1306, Determine if identity information exists; if yes, proceed to step S1307; if no, proceed to step S1308.

[0314] After obtaining the recognition results, the electronic device can determine whether identity information exists in the recognition results.

[0315] S1307, Get the list of students in the class;

[0316] If identity information exists, the electronic device can access the class student list. This list includes the names or student IDs of the students in the class.

[0317] S1308, no recognition result is returned, and the client does not perform any processing;

[0318] If no identity information is available, the electronic device may return a "no identification" result. Since no identity information is available, the client will not perform any processing.

[0319] S1309, Match identity information with the student list;

[0320] To determine whether a student whose identity information corresponds to a class, electronic devices can match the identity information with a list of students.

[0321] S1310, Determine if there is a matching result; if yes, proceed to step S1311; if no, return to step S1308;

[0322] After matching the identity information with the student list, the electronic device can determine whether a match exists.

[0323] S1311, Determine if the student information matches the previous identification information; if yes, proceed to step S1312; if no, proceed to step S1313.

[0324] If a match is found, it means the student corresponding to that identity information belongs to that class. If the student on the current grading page is different from the student on the previous grading page, it means the teacher has changed the grading target, and the answers of the student on the previous grading page and the corresponding student need to be uploaded to the database. To determine whether the teacher has changed the grading target, the electronic device can check whether the identity information is consistent with the student information identified in the last grading.

[0325] S1312 returns the currently identified student information; the client does not perform any processing.

[0326] If the student information matches the previous identification, it means the teacher has not changed the student being graded, so the client will not process the information.

[0327] S1313: Write the student grading record from the last identity verification into the database;

[0328] If the student information is inconsistent with the previous identification, it means that the teacher has changed the student being graded. The electronic device can then write the student's grading record from the previous identification into the database.

[0329] S1314, returns the currently identified student information, and the client prompts for an update and displays the student information.

[0330] To enable teachers to verify the accuracy of the student information retrieved from the current grading page, the electronic device can return the currently identified student information, and the client will prompt for an update and display that student information.

[0331] As can be seen, in this embodiment, the electronic device can control the projection device to project the identity information corresponding to the current grading page onto a preset area when the identity information on the current grading page is inconsistent with the identity information on the previous grading page. To allow teachers to verify the accuracy of the identity information on the current grading page, the electronic device can control the projection device to project the identity information onto the preset area. In this way, teachers can compare the identity information on the current grading page with the projected identity information. If the identity information on the current grading page is inconsistent with the projected identity information, the teacher can correct the recognition result of the electronic device. This improves the accuracy of identity information determination.

[0332] In one implementation, a flowchart illustrating the method for determining the translation / rotation matrix and base map identifier corresponding to the current revision page can be shown as follows: Figure 14 As shown. Specifically, it may include the following steps:

[0333] S1401, Image FIFO;

[0334] To reduce noise in the acquired images, electronic devices can perform FIFO (First In First Out, mean filtering) on ​​the acquired images.

[0335] S1402, Determine whether the identity recognition area is moving; if yes, proceed to step S1403; if no, proceed to step S1404.

[0336] In order to determine whether the identity information corresponding to the current revision page is the same as the identity information corresponding to the previous revision page, the electronic device can determine whether the identity recognition area is moving.

[0337] S1403, Identity Recognition Area Cropping;

[0338] If there is movement, it means that the identity information corresponding to the current editing page may be different from the identity information corresponding to the previous editing page. Therefore, the electronic device can crop the identity recognition area.

[0339] S1404, determine the motion mark in the correction area of ​​the paper; if the motion mark is the mark corresponding to the whole page change image, execute step S1406; if the motion mark is the mark corresponding to the gesture motion image, execute step S1407; if the motion mark is the mark corresponding to the almost unchanged image, execute step S1408.

[0340] If there is no movement, it means that the identity information corresponding to the current correction page is the same as the identity information corresponding to the previous correction page. To determine the base map identifier and translation / rotation matrix corresponding to the current correction page, the electronic device can determine the motion markers of the correction area. These motion markers indicate the degree of content change on the current correction page compared to the previous correction page.

[0341] S1405, Identity verification request (<10Hz);

[0342] After cropping the identification area, the electronic device can issue an identification request. In this step, the image acquisition device acquires images at a frequency of less than 10Hz.

[0343] S1406, Page retrieval and translation / rotation matrix generation (<10Hz);

[0344] If the motion marker corresponds to the marker of the entire page change image, it means that the background image identifier of the current page being revised is different from that of the previous page being revised. The electronic device can search the page and extract the features corresponding to the page. This feature is matched with the image features corresponding to each background page in the page background image structured data 1411, and then the background image identifier of the background image page with a matching degree greater than a preset matching degree is used as the background image identifier of the current page being revised.

[0345] Since the content of the current revision page has changed significantly compared to the previous revision page, the electronic device can determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base map image corresponding to the base map identifier in the page base map structured data 1411.

[0346] In this step, the image acquisition device acquires images at a frequency of less than 10Hz.

[0347] S1407, Translation and rotation matrix generation (<10Hz);

[0348] If the motion marker corresponds to the gesture motion image, it indicates that the teacher is currently grading and has not turned the page. Since the teacher is not turning the page, the background image marker for the current grading page is the same as the background image marker for the previous grading page.

[0349] Since the content of the current revision page has changed compared to the previous revision page, the electronic device can determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base map image corresponding to the base map identifier in the page base map structured data 1411.

[0350] In this step, the image acquisition device acquires images at a frequency of less than 10Hz.

[0351] S1408, Determine the translation and rotation matrix and base map identifier;

[0352] If the motion marker corresponds to the marker of an almost unchanging image, it means that the content of the current page being edited has changed little compared to the previous page, and the base map markers and translation / rotation matrices corresponding to the current and previous pages are the same. The electronic device can use the base map markers and translation / rotation matrices corresponding to the previous page as the base map markers and translation / rotation matrices corresponding to the current page, respectively.

[0353] The electronic device can obtain the base map identifier and translation / rotation matrix determined in step S1406, as well as the calibration parameters corresponding to each base page in the structured data 1411. Then, the electronic device can call the page separation algorithm, inputting the double-page image, the base map identifier, and the translation / rotation matrix, to obtain the position offset of the single-page image and the answer box.

[0354] S1409, Page Separation;

[0355] In order to identify the answer separately for each page in a two-page image, the electronic device can call a page separation algorithm to separate the pages in the two-page image, thereby obtaining two single-page images.

[0356] S1410, Answer Recognition.

[0357] After separating the two-page image, the electronic device can identify the answer in the current grading page based on the position offset of the answer box determined in step S1408 and the calibration parameters corresponding to the base image page.

[0358] In one implementation, the flowchart for determining the answer status of the questions corresponding to the questions on the current grading page can be as follows: Figure 15 As shown. Specifically, it may include the following steps:

[0359] S1501, Obtaining correction marks;

[0360] Electronic devices can acquire censorship tags to determine whether the censorship tag is an identity verification request.

[0361] S1502, Determine whether it is an identity verification request; if yes, proceed to step S1503; if no, proceed to step S1504.

[0362] To determine whether to perform identity verification, electronic devices can judge whether the tamper mark is an identity verification request.

[0363] S1503, Identity Recognition;

[0364] If the censorship mark is an identity verification request, then the electronic device can perform identity verification.

[0365] S1504, retrieve a small image of the student's answer record;

[0366] If the grading mark is not an identity verification request, the electronic device can determine the location of the answer box on the current grading page based on the position offset corresponding to the current grading page and the calibration parameters corresponding to the base image page. The small image of the student's answer record represents the answer box corresponding to the question.

[0367] S1505, obtain its question number based on the coordinates of the small graph;

[0368] The electronic device can determine the question number for each answer box on the current grading page based on the coordinates of the corresponding area in the base map and the overlapping area between the coordinates of the answer boxes for each question on the base map page.

[0369] S1506, call the answer recognition algorithm for the small image containing question numbers;

[0370] For an answer box with a specific question number, the electronic device can call an answer recognition algorithm to determine the answer within the answer box.

[0371] S1507 calls the correction recognition algorithm for large images marked by teachers;

[0372] Electronic devices can use recognition algorithms to identify teachers' marking marks. For marking marks that overlap with multiple question areas, the electronic device can use the marking result corresponding to that marking mark as the marking result for those multiple questions.

[0373] S1508, merge the answer recognition results and the correction recognition results;

[0374] For questions with marking traces, the electronic device can determine the corresponding answer based on the marking results indicated by the marking traces. For questions without marking traces but with answers, the electronic device can determine the corresponding answer based on the matching result between the corresponding answer and the standard answer. For questions without marking traces or answers, the electronic device can determine the corresponding answer as incorrect.

[0375] S1509, returns the recognition result and the client projection result.

[0376] The electronic device identifies the current grading page, determines the answers to each question, returns the identification results, and determines the projection parameters for the auxiliary grading markers based on these results. The projection results can be the projection parameters themselves.

[0377] In one embodiment, the flowchart of a correction assistance method provided in this application can be as follows: Figure 16 As shown. Specifically, it may include the following steps:

[0378] S1601, Teacher Login;

[0379] Teachers can log in to the system before grading papers.

[0380] S1602, Teachers manually select the name of teaching aids;

[0381] Teachers can manually select the names of the teaching materials to be graded in the system.

[0382] S1603, Teacher enters the range of the grading page;

[0383] Teachers can manually select the range of pages to be graded in the system.

[0384] S1604, the teacher clicks the "Start Grading" button;

[0385] Teachers can press the start button on the motor to allow the system to assist them in grading.

[0386] S1605, Loading the base map and model;

[0387] The system can load the base map of the page range corresponding to the teaching aid name entered by the teacher based on the base map library 1611; and load the model for grading assistance based on the model file 1612.

[0388] S1606, Invoke the AR correction auxiliary module;

[0389] The system can call the AR (Augmented Reality) grading assistance module to project the answers to the questions on the current grading page as grading assistance icons onto the current grading page, so that teachers can grade according to the grading assistance icons.

[0390] S1607, Teacher's marking completed;

[0391] Once the teacher has finished grading, they can click the "End Grading" button.

[0392] S1608, Student Learning Statistics.

[0393] The system can record each student's answers to various questions. Based on these answers, the system can perform statistics on the overall class accuracy rate, the accuracy rate for each question, and the accuracy rate for each student. Furthermore, teachers can use the statistical results to create lesson plans tailored to the class's performance, or to develop personalized teaching methods for different students.

[0394] In one implementation, Figure 16 The detailed flowchart of step S1606 in the flowchart shown can be as follows: Figure 17 As shown. Specifically, it may include the following steps:

[0395] S1701, capturing page images;

[0396] Electronic devices can capture images of the currently edited page.

[0397] S1702, Image Correction;

[0398] Electronic devices can convert images viewed from a tilted angle into images viewed from a vertical angle using a pre-determined correction matrix, thus obtaining a corrected image. Typically, the images acquired by the image acquisition device are high-resolution images, while the corrected images are medium-resolution images.

[0399] S1703, Motion Analysis;

[0400] To determine whether a teacher is turning pages, electronic devices can perform motion analysis on the identification area and the marking area of ​​the paper.

[0401] S1704, Determine if there is movement in the identity area; if yes, proceed to step S1705; if no, proceed to step S1709.

[0402] If the identity area moves, it indicates a change in the student to whom the graded item belongs. To determine if the student to whom the graded item belongs has changed, the electronic device can detect movement in the identity area. The identity area can be a region for identifying individuals.

[0403] S1705, Identity Recognition;

[0404] If the identity area moves, it means the student to whom the graded item belongs has changed. To determine the student to whom the current graded item belongs, the electronic device can perform identity recognition on the identity recognition area of ​​the current grading page.

[0405] S1706, Determine whether the identity recognition result is correct; if yes, proceed to step S1707; if no, proceed to step S1708.

[0406] Electronic devices can broadcast the identified identity information through audio playback, display it on a monitor, or project it using a projector, thereby enabling teachers to determine whether the identity information extracted by the electronic device is correct.

[0407] S1707, indicating a new identity;

[0408] If correct, the electronic device can display the new identity. This new identity can be the identity information corresponding to the current edited page, which has changed compared to the identity information on the previous edited page.

[0409] S1708, Modify identity information;

[0410] If an error is found, the teacher can manually correct the incorrect identity information. Once corrected, the electronic device can broadcast, display, or project the corrected identity information.

[0411] S1709, Answer Recognition;

[0412] If there is no movement in the identity area, it means that the current grading page belongs to the same student as the previous grading page. Therefore, the electronic device can identify the answers on the current grading page and obtain the answers to each question on the current grading page.

[0413] S1710, the answer is relevant to the student;

[0414] Once the electronic device has determined the answers to each question on the current grading page, it can associate the answers with the identified identity information.

[0415] S1711, reverse correction of the projection frame;

[0416] Because the projection device projects onto the projection frame at an angle, it is necessary to perform reverse correction on the projection frame, projecting it from a vertical angle to an angled angle. The projection frame can be projected onto the area corresponding to the question, indicating whether the answer to the question is correct or incorrect.

[0417] S1712, AR projection.

[0418] After the projection frame is reverse-corrected, the electronic device can project the reverse-corrected projection frame onto the current correction page using AR.

[0419] It should be noted that the acquisition, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of this application are all carried out with the user's authorization.

[0420] Corresponding to the above-described correction assistance method, this application embodiment also provides a correction assistance device, which will be described below.

[0421] like Figure 18 As shown, a correction assistance device includes:

[0422] Image acquisition module 1801 is used to acquire the image of the current editing page captured by the image acquisition device;

[0423] Image recognition module 1802 is used to recognize the image and obtain a recognition result;

[0424] The parameter determination module 1803 is used to determine the projection parameters of the auxiliary grading identifier based on the identification results, including the answer status of the questions on the current grading page and the teacher's grading status corresponding to the questions. The auxiliary grading identifier is used to represent the answer status of the questions to assist the teacher in grading the current grading page.

[0425] The label projection module 1804 is used to control the projection device to project the auxiliary correction label onto the area corresponding to the question according to the projection parameters.

[0426] As can be seen, in this embodiment, the electronic device can acquire an image of the current grading page captured by the image acquisition device; perform recognition on the image to obtain a recognition result; based on the recognition result including the answers to the questions on the current grading page and the teacher's grading of the corresponding questions, determine the projection parameters of the auxiliary grading identifier, wherein the auxiliary grading identifier is used to represent the answers to the questions to assist the teacher in grading the current grading page; and control the projection device to project the auxiliary grading identifier onto the area corresponding to the questions according to the projection parameters. Since the auxiliary grading identifier can be used to represent the answers to the target questions, after projecting the auxiliary grading identifier onto the area corresponding to the questions, the teacher can determine the answers to the target questions based on the auxiliary grading identifier, without needing the teacher to constantly remember the standard answers. Therefore, it can reduce the workload of the teacher in the grading process and increase the convenience for the teacher in grading.

[0427] As one embodiment of this application, the parameter determination module 1803 may include:

[0428] The result judgment submodule is used to determine whether the recognition result includes the grading result and the answer to the question;

[0429] The first parameter determination submodule is used to match the answer to the question on the current grading page included in the recognition result with the standard answer corresponding to the question if the answer exists and the grading result does not exist, to obtain a matching result; and to determine the projection parameters of the auxiliary grading identifier based on the matching result.

[0430] The second parameter determination submodule is used to determine the answer to the question as an error result if neither the grading result nor the answer exists, and to determine the projection parameter of the auxiliary grading identifier based on the error result;

[0431] The third parameter determination submodule is used to determine the projection parameters of the auxiliary correction identifier based on the correction result if the correction result exists.

[0432] As one embodiment of this application, the above-mentioned first parameter determination submodule may include:

[0433] The first parameter determining unit is used to determine the projection parameter of the auxiliary correction identifier as a first preset parameter if the matching result indicates that the answer is the same as the standard answer;

[0434] The second parameter determination unit is used to determine the projection parameter of the auxiliary correction identifier as a second preset parameter if the matching result indicates that the answer is different from the standard answer;

[0435] The aforementioned second parameter determination submodule may include:

[0436] The third parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the second preset parameter;

[0437] The third parameter determination submodule includes:

[0438] The fourth parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the first preset parameter if the correction result indicates that the answer is correct.

[0439] The fifth parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the second preset parameter if the correction result indicates that the answer is wrong.

[0440] As one embodiment of this application, the image recognition module 1802 includes:

[0441] The answer box position determination submodule is used to determine the position of the answer box of the question in the current grading page based on the position offset of the answer box corresponding to the current grading page and the pre-determined calibration parameters corresponding to the current grading page. The position offset is the position offset of the answer area corresponding to the question in the current grading page relative to the answer area corresponding to the question in the base image. The calibration parameters are the positions of the answer areas corresponding to each question in the base image. The base image is an image pre-captured from the current grading page before grading.

[0442] The answer determination submodule is used to perform text recognition based on the position of the answer box corresponding to the question to obtain the recognized content. If the recognized content includes a text result, the text result is determined as the answer to the question.

[0443] The correction trace recognition submodule is used to identify the correction traces in the current correction page and obtain the correction content;

[0444] The grading result determination submodule is used to determine the position of the grading mark on the base map based on the position offset and the area where the grading mark is located, if the grading content includes preset grading marks, and based on the determined position and the position of the pre-determined question area, determine the grading result corresponding to the question.

[0445] As one embodiment of this application, the above-described apparatus may further include:

[0446] The answer box position determination module is used to determine the position of the answer box in the base map for each question, based on the position of the answer box and the position offset.

[0447] The overlapping area calculation module is used to calculate the overlapping area between the area corresponding to the answer box in the base map and the answer area corresponding to each question in the base map, based on the position of the answer box in the base map and the position of the answer area corresponding to each question in the base map that is predetermined.

[0448] The target question number determination module is used to determine the target question number of a question if there is an overlapping area larger than the first preset area, based on the pre-recorded correspondence between the answer area and the question number in the base map.

[0449] The standard answer determination module is used to determine the standard answer corresponding to the target question number based on the pre-recorded correspondence between question numbers and standard answers, and use it as the standard answer for that question.

[0450] As one embodiment of this application, the above-described apparatus may further include:

[0451] The identifier and matrix acquisition module is used to acquire the target base image identifier and target translation and rotation matrix corresponding to the image of the current censoring page, wherein the target translation and rotation matrix is ​​used to identify the mapping relationship between the image and the base image corresponding to the target base image identifier;

[0452] The calibration parameter determination module is used to determine the target calibration parameter corresponding to the target base map identifier based on the pre-established correspondence between the base map identifier and the calibration parameter, and use it as the calibration parameter corresponding to the current modification page;

[0453] The position offset determination module is used to determine the position offset of the answer box corresponding to the current grading page based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page.

[0454] As one embodiment of this application, the above-mentioned identifier and matrix acquisition module includes:

[0455] The motion marker acquisition submodule is used to acquire the motion marker corresponding to the current revision page, wherein the motion marker is used to characterize the content change of the current revision page relative to the previous revision page;

[0456] The first identifier and matrix determination submodule is used to, if the motion marker corresponding to the current revision page is the first motion marker, take the base map marker and translation / rotation matrix corresponding to the previous revision page as the target base map marker and the target translation / rotation matrix, respectively. The first motion marker indicates that the content change of the current revision page relative to the previous revision page is less than a first preset degree.

[0457] The second identifier and matrix determination submodule is used to, if the motion marker corresponding to the current revision page is the second motion marker, take the base map marker corresponding to the previous revision page as the target base map marker; and determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base map image corresponding to the target base map marker, wherein the second motion marker indicates that the content change degree of the current revision page relative to the previous revision page is greater than the first preset degree, and the content change degree is less than the second preset degree;

[0458] The third identifier and matrix determination submodule is used to determine the target translation and rotation matrix based on the image features of the current modified page and the features of the base image corresponding to the target base image identifier if the motion marker corresponding to the current modified page is the third motion marker; and to use the base image identifier corresponding to the next page of the previous modified page as the target base image identifier, wherein the third motion marker indicates that the content change of the current modified page relative to the previous modified page is greater than the second preset degree.

[0459] As one implementation of this application, the above-mentioned correction result determination submodule may include:

[0460] The correction mark location determination unit is used to determine the location of each correction mark in the base map based on the area where the correction mark is located and the location offset.

[0461] The overlapping area calculation unit is used to calculate the overlapping area between the area corresponding to the correction mark on the base map and the area of ​​each question on the base map, based on the position of the correction mark on the base map and the position of each question area in the pre-determined map.

[0462] The grading result determination unit is used to determine the grading result corresponding to the grading mark based on the correspondence between the grading mark and the grading result recorded in advance if there is an overlapping area larger than the second preset area. This grading result is then used as the grading result corresponding to the question corresponding to the overlapping area.

[0463] As one embodiment of this application, the above-described apparatus may further include:

[0464] The image correction module is used to correct the acquired image according to a predetermined correction matrix to obtain a corrected image, which is used as the image of the current censored page. The correction matrix is ​​used to correct the image from a tilted view to a vertical view.

[0465] The aforementioned sign projection module 1804 may include:

[0466] The labeling projection submodule is used to control the projection device to perform anti-distortion on the auxiliary correction label according to the projection parameters and the correction matrix, and to project the anti-distortion auxiliary correction label onto the area corresponding to the question.

[0467] As one embodiment of this application, the above-described apparatus may further include:

[0468] The identity information determination module is used to identify a preset identity recognition area in the image to obtain identity information;

[0469] The above-mentioned device may further include:

[0470] The answer recording module is used to record the answer status of the questions on the current grading page, corresponding to the identity information.

[0471] As one embodiment of this application, the above-described apparatus may further include:

[0472] The identity information projection module is used to control the projection device to project the identity information corresponding to the current revision page to a preset area when the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page.

[0473] Corresponding to the above-described correction assistance method, this application embodiment also provides a correction assistance system, which will be described below.

[0474] like Figure 19 As shown, a correction assistance system includes a processing device 1901, an image acquisition device 1902, and a projection device 1903, wherein:

[0475] The processing device 1901 is used to execute the batch correction auxiliary method steps described in any of the above embodiments;

[0476] The image acquisition device 1902 is used to acquire an image of the current page being edited;

[0477] The projection device 1903 is used to project auxiliary correction marks onto the area corresponding to the question according to the projection parameters.

[0478] As can be seen, in this embodiment, the electronic device can acquire an image of the current grading page captured by the image acquisition device; perform recognition on the image to obtain a recognition result; based on the recognition result including the answers to the questions on the current grading page and the teacher's grading of the corresponding questions, determine the projection parameters of the auxiliary grading identifier, wherein the auxiliary grading identifier is used to represent the answers to the questions to assist the teacher in grading the current grading page; and control the projection device to project the auxiliary grading identifier onto the area corresponding to the questions according to the projection parameters. Since the auxiliary grading identifier can be used to represent the answers to the target questions, after projecting the auxiliary grading identifier onto the area corresponding to the questions, the teacher can determine the answers to the target questions based on the auxiliary grading identifier, without needing the teacher to constantly remember the standard answers. Therefore, it can reduce the workload of the teacher in the grading process and increase the convenience for the teacher in grading.

[0479] This application also provides a processing device, such as... Figure 20 As shown, it includes:

[0480] Memory 2001 is used to store computer programs;

[0481] When the processor 2002 executes the program stored in the memory 2001, it implements the steps of the correction assistance method described in any of the above embodiments.

[0482] Furthermore, the aforementioned processing device may also include a communication bus and / or a communication interface, and the processor 2002, the communication interface, and the memory 2001 communicate with each other through the communication bus.

[0483] As can be seen, in this embodiment, the electronic device can acquire an image of the current grading page captured by the image acquisition device; perform recognition on the image to obtain a recognition result; based on the recognition result including the answers to the questions on the current grading page and the teacher's grading of the corresponding questions, determine the projection parameters of the auxiliary grading identifier, wherein the auxiliary grading identifier is used to represent the answers to the questions to assist the teacher in grading the current grading page; and control the projection device to project the auxiliary grading identifier onto the area corresponding to the questions according to the projection parameters. Since the auxiliary grading identifier can be used to represent the answers to the target questions, after projecting the auxiliary grading identifier onto the area corresponding to the questions, the teacher can determine the answers to the target questions based on the auxiliary grading identifier, without needing the teacher to constantly remember the standard answers. Therefore, it can reduce the workload of the teacher in the grading process and increase the convenience for the teacher in grading.

[0484] The communication bus mentioned in the above processing device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0485] The communication interface is used for communication between the aforementioned processing device and other devices.

[0486] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0487] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0488] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described modification assistance methods.

[0489] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the modification assistance methods described above.

[0490] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state disk (SSD).

[0491] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0492] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatuses, systems, processing devices, computer-readable storage media, and computer program products, since they are substantially similar to the method embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions of the method embodiments.

[0493] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. A method for assisting in correction, characterized in that, A processing device applied to a grading assistance system, the grading assistance system further including an image acquisition device and a projection device, the method comprising: Acquire the image of the current editing page captured by the image acquisition device; The image is then identified to obtain the identification result; Based on the identification results, including the answers to the questions on the current grading page and the teacher's grading of the questions, the projection parameters of the auxiliary grading identifier are determined. The auxiliary grading identifier is used to represent the answers to the questions to assist the teacher in grading the current grading page. The projection device is controlled to project the auxiliary correction mark onto the area corresponding to the question according to the projection parameters; The step of recognizing the image and obtaining the recognition result includes: Based on the position offset of the answer box corresponding to the current grading page and the predetermined calibration parameters corresponding to the current grading page, the position of the answer box of the question in the current grading page is determined. The position offset is the position offset of the answer area corresponding to the question in the current grading page relative to the answer area corresponding to the question in the base image. The calibration parameters are the positions of the answer areas corresponding to each question in the base image. The base image is an image pre-captured from the current grading page before grading. Based on the position of the answer box corresponding to the question, text recognition is performed to obtain the recognized content. If the recognized content includes text results, the text results are determined as the answer to the question. Identify the editing traces on the current editing page to obtain the editing content; If the correction content includes preset correction marks, the correction marks are located in the base map based on the position offset and the area where the correction marks are identified. Based on the determined position and the position of the pre-determined question area, the correction result corresponding to the question is determined.

2. The method according to claim 1, characterized in that, The step of determining the projection parameters of the auxiliary grading identifier based on the identification results, including the answers to the questions on the current grading page and the teacher's grading information corresponding to the questions, includes: Determine whether the recognition result includes the grading result and the answer to the question; If the answer exists but the grading result does not exist, the answer to the question on the current grading page included in the recognition result is matched with the standard answer corresponding to the question to obtain a matching result; the projection parameters of the auxiliary grading identifier are determined based on the matching result. If neither the grading result nor the answer exists, the answer corresponding to the question is determined to be an incorrect result, and the projection parameters of the auxiliary grading identifier are determined based on the incorrect result; If the correction result exists, determine the projection parameters of the auxiliary correction identifier based on the correction result.

3. The method according to claim 2, characterized in that, The step of determining the projection parameters of the auxiliary correction identifier based on the matching result includes: If the matching result indicates that the answer is the same as the standard answer, the projection parameter of the auxiliary correction indicator is determined to be the first preset parameter; If the matching result indicates that the answer is different from the standard answer, the projection parameter of the auxiliary correction indicator is determined to be the second preset parameter; The step of determining the projection parameters of the auxiliary correction identifier based on the error result includes: The projection parameters of the auxiliary correction mark are determined to be the second preset parameters; The step of determining the projection parameters of the auxiliary correction identifier based on the correction result includes: If the grading result indicates that the answer is correct, the projection parameter of the auxiliary grading indicator is determined to be the first preset parameter; If the grading result indicates that the answer is incorrect, the projection parameter of the auxiliary grading indicator is determined to be the second preset parameter.

4. The method according to claim 2, characterized in that, Before the step of matching the answers to the questions on the current grading page, which include the recognition results, with the standard answers corresponding to the questions to obtain the matching results, the method further includes: For each question's answer box, determine the corresponding position of the answer box in the base image based on the answer box's position and the position offset. Based on the position of the answer box in the base map and the predetermined position of the answer area for each question in the base map, calculate the overlapping area between the area of ​​the answer box in the base map and the answer area for each question in the base map; If there is an overlapping area larger than the first preset area, according to the pre-recorded correspondence between the answer area and the question number in the base map, the question number corresponding to the answer area in the base map corresponding to the overlapping area is taken as the target question number of the question. Based on the pre-recorded correspondence between question numbers and standard answers, the standard answer corresponding to the target question number is determined and used as the standard answer for that question.

5. The method according to claim 1 or 4, characterized in that, Before the step of determining the position of the answer box of the question on the current grading page based on the position offset of the answer box corresponding to the current grading page and the predetermined calibration parameters corresponding to the current grading page, the method further includes: Obtain the target base image identifier and target translation and rotation matrix corresponding to the image of the current editing page, wherein the target translation and rotation matrix is ​​used to identify the mapping relationship between the image and the base image corresponding to the target base image identifier; Based on the pre-established correspondence between the base map identifier and the calibration parameters, the target calibration parameters corresponding to the target base map identifier are determined and used as the calibration parameters corresponding to the current revision page. Based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page, determine the position offset of the answer box corresponding to the current grading page.

6. The method according to claim 5, characterized in that, The step of obtaining the target base map identifier and target translation and rotation matrix corresponding to the image of the current editing page includes: Obtain the motion marker corresponding to the current revision page, wherein the motion marker is used to characterize the content change of the current revision page relative to the previous revision page; If the motion marker corresponding to the current revision page is the first motion marker, the base map identifier and translation / rotation matrix corresponding to the previous revision page are respectively used as the target base map identifier and the target translation / rotation matrix, wherein the first motion marker indicates that the content change of the current revision page relative to the previous revision page is less than a first preset degree; If the motion marker corresponding to the current revision page is the second motion marker, the base map identifier corresponding to the previous revision page is used as the target base map identifier; the target translation and rotation matrix is ​​determined based on the image features of the current revision page and the features of the base map image corresponding to the target base map identifier, wherein the second motion marker indicates that the content change degree of the current revision page relative to the previous revision page is greater than the first preset degree, and the content change degree is less than the second preset degree; If the motion marker corresponding to the current revision page is the third motion marker, the target translation and rotation matrix is ​​determined based on the image features of the current revision page and the features of the base image corresponding to the target base image identifier; the base image identifier corresponding to the next page of the previous revision page is used as the target base image identifier, wherein the third motion marker indicates that the content change of the current revision page relative to the previous revision page is greater than the second preset degree.

7. The method according to claim 1, characterized in that, The step of determining the position of the correction mark on the base map based on the position offset and the identified area of ​​the correction mark, and determining the correction result corresponding to the question based on the determined position and the pre-determined position of the question area, includes: For each correction mark, the position of the correction mark in the base map is determined based on the area where the correction mark is located and the position offset. Based on the location of the correction mark on the base map and the location of each question area in advance, calculate the overlapping area between the area of ​​the correction mark on the base map and each question area on the base map; If there is an overlapping area larger than the second preset area, the grading result corresponding to the grading mark is determined according to the pre-recorded correspondence between the grading marks and the grading results, and is used as the grading result corresponding to the question corresponding to the overlapping area.

8. The method according to any one of claims 1-4, characterized in that, Prior to the step of recognizing the image and obtaining the recognition result, the method further includes: The acquired image is corrected according to a predetermined correction matrix to obtain a corrected image, which is used as the image of the current revise page. The correction matrix is ​​used to correct the image from a tilted view to a vertical view. The step of controlling the projection device to project the auxiliary correction mark onto the area corresponding to the question according to the projection parameters includes: The projection device is controlled to perform anti-distortion on the auxiliary correction mark according to the projection parameters and the correction matrix, and the anti-distortion auxiliary correction mark is projected onto the area corresponding to the question.

9. The method according to any one of claims 1-4, characterized in that, After the step of acquiring the image of the current revision page captured by the image acquisition device, the method further includes: The image is identified by a preset identity recognition region to obtain identity information; After the step of determining the projection parameters of the auxiliary grading identifier based on the identification results, including the answers to the questions on the current grading page and the teacher grading information corresponding to the questions, the method further includes: Corresponding to the identity information, the answers to the questions on the current grading page are recorded.

10. The method according to claim 9, characterized in that, The method further includes: If the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page, the projection device is controlled to project the identity information corresponding to the current revision page onto a preset area.

11. A correction auxiliary device, characterized in that, A processing device used in a grading assistance system, wherein the grading assistance system further includes an image acquisition device and a projection device, the device comprising: The image acquisition module is used to acquire the image of the current editing page captured by the image acquisition device; An image recognition module is used to recognize the image and obtain a recognition result; The parameter determination module is used to determine the projection parameters of the auxiliary grading identifier based on the identification results, including the answer status of the questions on the current grading page and the teacher's grading status corresponding to the questions. The auxiliary grading identifier is used to represent the answer status of the questions to assist the teacher in grading the current grading page. The labeling projection module is used to control the projection device to project the auxiliary correction label onto the area corresponding to the question according to the projection parameters. The image recognition module includes: The answer box position determination submodule is used to determine the position of the answer box of the question in the current grading page based on the position offset of the answer box corresponding to the current grading page and the pre-determined calibration parameters corresponding to the current grading page. The position offset is the position offset of the answer area corresponding to the question in the current grading page relative to the answer area corresponding to the question in the base image. The calibration parameters are the positions of the answer areas corresponding to each question in the base image. The base image is an image pre-captured from the current grading page before grading. The answer determination submodule is used to perform text recognition based on the position of the answer box corresponding to the question to obtain the recognized content. If the recognized content includes a text result, the text result is determined as the answer to the question. The correction trace recognition submodule is used to identify the correction traces in the current correction page and obtain the correction content; The grading result determination submodule is used to determine the position of the grading mark on the base map based on the position offset and the area where the grading mark is located, if the grading content includes preset grading marks, and based on the determined position and the position of the pre-determined question area, determine the grading result corresponding to the question.

12. The apparatus according to claim 11, characterized in that, The parameter determination module includes: The result judgment submodule is used to determine whether the recognition result includes the grading result and the answer to the question; The first parameter determination submodule is used to match the answer to the question on the current grading page included in the recognition result with the standard answer corresponding to the question if the answer exists and the grading result does not exist, to obtain a matching result; and to determine the projection parameters of the auxiliary grading identifier based on the matching result. The second parameter determination submodule is used to determine the answer to the question as an error result if neither the grading result nor the answer exists, and to determine the projection parameter of the auxiliary grading identifier based on the error result; The third parameter determination submodule is used to determine the projection parameters of the auxiliary correction identifier based on the correction result if the correction result exists. The first parameter determination submodule includes: The first parameter determining unit is used to determine the projection parameter of the auxiliary correction identifier as a first preset parameter if the matching result identifier indicates that the answer is the same as the standard answer; The second parameter determination unit is used to determine the projection parameter of the auxiliary correction identifier as a second preset parameter if the matching result indicates that the answer is different from the standard answer; The second parameter determination submodule includes: The third parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the second preset parameter; The third parameter determination submodule includes: The fourth parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the first preset parameter if the correction result indicates that the answer is correct. The fifth parameter determination unit is used to determine the projection parameter of the auxiliary correction mark as the second preset parameter if the correction result indicates that the answer is wrong; The device further includes: The answer box position determination module is used to determine the position of the answer box in the base map for each question, based on the position of the answer box and the position offset. The overlapping area calculation module is used to calculate the overlapping area between the area corresponding to the answer box in the base map and the answer area corresponding to each question in the base map, based on the position of the answer box in the base map and the position of the answer area corresponding to each question in the base map that is predetermined. The target question number determination module is used to determine the target question number of a question if there is an overlapping area larger than the first preset area, based on the pre-recorded correspondence between the answer area and the question number in the base map. The standard answer determination module is used to determine the standard answer corresponding to the target question number based on the pre-recorded correspondence between question numbers and standard answers, and use it as the standard answer for that question. The device further includes: The identifier and matrix acquisition module is used to acquire the target base image identifier and target translation and rotation matrix corresponding to the image of the current censoring page, wherein the target translation and rotation matrix is ​​used to identify the mapping relationship between the image and the base image corresponding to the target base image identifier; The calibration parameter determination module is used to determine the target calibration parameter corresponding to the target base map identifier based on the pre-established correspondence between the base map identifier and the calibration parameter, and use it as the calibration parameter corresponding to the current modification page; The position offset determination module is used to determine the position offset of the answer box corresponding to the current grading page based on the target translation and rotation matrix and the calibration parameters corresponding to the current grading page. The identifier and matrix acquisition module includes: The motion marker acquisition submodule is used to acquire the motion marker corresponding to the current revision page, wherein the motion marker is used to characterize the content change of the current revision page relative to the previous revision page; The first identifier and matrix determination submodule is used to, if the motion marker corresponding to the current revision page is the first motion marker, take the base map marker and translation / rotation matrix corresponding to the previous revision page as the target base map marker and the target translation / rotation matrix, respectively. The first motion marker indicates that the content change of the current revision page relative to the previous revision page is less than a first preset degree. The second identifier and matrix determination submodule is used to, if the motion marker corresponding to the current revision page is the second motion marker, take the base map marker corresponding to the previous revision page as the target base map marker; and determine the target translation and rotation matrix based on the image features of the current revision page and the features of the base map image corresponding to the target base map marker, wherein the second motion marker indicates that the content change degree of the current revision page relative to the previous revision page is greater than the first preset degree, and the content change degree is less than the second preset degree; The third identifier and matrix determination submodule is used to determine the target translation and rotation matrix based on the image features of the current modified page and the features of the base image corresponding to the target base image identifier if the motion marker corresponding to the current modified page is the third motion marker; and to use the base image identifier corresponding to the next page of the previous modified page as the target base image identifier, wherein the third motion marker indicates that the content change of the current modified page relative to the previous modified page is greater than the second preset degree; The correction result determination submodule includes: The correction mark location determination unit is used to determine the location of each correction mark in the base map based on the area where the correction mark is located and the location offset. The overlapping area calculation unit is used to calculate the overlapping area between the area corresponding to the correction mark on the base map and the area of ​​each question on the base map, based on the position of the correction mark on the base map and the position of each question area in the pre-determined map. The grading result determination unit is used to determine the grading result corresponding to the grading mark based on the correspondence between the grading mark and the grading result recorded in advance if there is an overlapping area larger than the second preset area. This grading result is then used as the grading result corresponding to the question corresponding to the overlapping area. The device further includes: The image correction module is used to correct the acquired image according to a predetermined correction matrix to obtain a corrected image, which is used as the image of the current censored page. The correction matrix is ​​used to correct the image from a tilted view to a vertical view. The sign projection module includes: The labeling projection submodule is used to control the projection device to perform anti-distortion on the auxiliary correction label according to the projection parameters and the correction matrix, and project the anti-distortion auxiliary correction label onto the area corresponding to the question; The device further includes: The identity information determination module is used to identify a preset identity recognition area in the image to obtain identity information; The device further includes: The answer recording module is used to record the answer status of the questions on the current grading page, corresponding to the identity information. The device further includes: The identity information projection module is used to control the projection device to project the identity information corresponding to the current revision page to a preset area when the identity information corresponding to the current revision page is inconsistent with the identity information corresponding to the previous revision page.

13. A grading assistance system, characterized in that, The correction assistance system includes processing equipment, image acquisition equipment, and projection equipment, wherein: The image acquisition device is used to acquire an image of the current editing page; The processing device is used to perform the method according to any one of claims 1-10; The projection device is used to project auxiliary correction marks onto the area corresponding to the question according to the projection parameters.

14. A processing apparatus, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-10.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-10.

Images