CN110942054B - Page content identification method - Google Patents
Page content identification method Download PDFInfo
- Publication number
- CN110942054B CN110942054B CN201911396610.7A CN201911396610A CN110942054B CN 110942054 B CN110942054 B CN 110942054B CN 201911396610 A CN201911396610 A CN 201911396610A CN 110942054 B CN110942054 B CN 110942054B
- Authority
- CN
- China
- Prior art keywords
- page
- area
- content
- question
- answer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/416—Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A page content identification method comprises the following steps; the method comprises the steps of dividing a question area and a question answering area on test paper, setting page number information on the test paper, and setting area marks on the question answering area; and acquiring image information of a plurality of stacked test paper sheets, identifying the image information, and identifying the placement relation of the test paper sheets through the image information. The scheme can solve the problem that whether the placement relation of the identification test question paper meets the requirements. If the placement relationship is correct, the answer content of a plurality of test paper sheets can be acquired and transmitted through one-time image. The effects of saving time and data transmission bandwidth are achieved.
Description
Technical Field
The invention relates to the field of online teaching, in particular to an image-based answer content identification optimization technology.
Background
The existing answer sheet is a carrier for inputting information by a cursor reader and is a generic name of various information input forms matched with the cursor reader. The information card converts the information required by the user into selectable options for the user to write. The OMR device restores the information according to the painted and uncoated and formatted file settings of the information points.
The style of the information card is designed based on the information entered into the computer and in a format required by the design specifications of the cursor reader.
In practical application, the special answer sheet is identified, so that the user needs to switch filling on the test paper and the answer sheet when making questions, filling errors are easy to occur, and identification correction is not facilitated.
Disclosure of Invention
Therefore, a new page content identification method is needed to solve the problem that the page content identification in the prior art is inconvenient.
To achieve the above object, the present inventors provide a page content recognition method including the steps of; acquiring image information of a plurality of staggered stacked pages, wherein the image information comprises all or part of the uppermost page and non-covered areas of the lower page which are not covered by the upper page;
and identifying the content of the non-shielded pages which are overlapped in a staggered way and the non-coverage residual content of the shielded pages according to the image information.
Further, the staggered pages include,
the upper page covers the left side area of the lower page;
or the upper page covers the right side area of the lower page;
or the upper page covers the upper side area of the lower page;
or the upper page covers the lower side area of the lower page;
or the upper page covers the left upper side area of the lower page;
or the upper page covers the right upper side area of the lower page;
or the upper page covers the left lower side area of the lower page;
or the upper page covers the lower right region of the lower page.
Specifically, the non-occluded page content or the residual content includes an area marker therein.
Specifically, the method further comprises the step of identifying at least two area marks of the non-occluded page content or the residual content and correcting the distortion of the photographed image.
Specifically, the region is marked as a mark pair, and when at least one mark is identified and at least one mark is not identified, the page is judged not to be placed according to the specified requirement.
Specifically, a certain expected area mark cannot be recognized in the video, and the absence of the expected page is determined.
Specifically, the non-coverage area further comprises page number information, and the method further comprises the step of judging whether a plurality of stacked test paper sheets are disordered or not through identifying the page number information.
Further, the method further comprises the step of sending out a prompt signal when the page is judged to be not placed according to the specified requirement or the expected page or out of order.
Specifically, the page comprises an answer area arranged on the right side.
Specifically, the region is marked as an AR code.
Unlike the prior art, the above scheme can identify the uppermost portion and the remaining portion of the staggered page content. And identifying the covered and uncovered contents as different pages. The better technical effect of image partition is achieved by distinguishing the content of the non-occluded page and the residual content.
Drawings
Fig. 1 is a block diagram of an answer content recognition system according to an embodiment;
FIG. 2 is a schematic diagram of the placement of test paper according to an embodiment;
FIG. 3 is a flowchart of a page content identification method according to an embodiment;
FIG. 4 is a flowchart of a page content identification method according to an embodiment;
fig. 5 is a flowchart of an answer sheet generating method according to an embodiment;
fig. 6 is a block diagram of an answer sheet generating system according to an embodiment.
Detailed Description
In order to describe the technical content, constructional features, achieved objects and effects of the technical solution in detail, the following description is made in connection with the specific embodiments in conjunction with the accompanying drawings.
Referring to fig. 1, a page content recognition system includes an image capturing unit 100, a processing unit 102, where the image capturing unit 100 is configured to obtain image information of a plurality of staggered pages, the image information includes all or part of an uppermost page, and a non-covered area where a lower page is not covered by an upper page. The processing unit 102 is configured to identify, according to the image information, content of non-occluded pages and non-covered residual content of occluded pages that are stacked in a staggered manner. In our example the staggered pages include an upper page overlaying the left region of a lower page; or the upper page covers the right side area of the lower page; or the upper page covers the upper side area of the lower page; or the upper page covers the lower side area of the lower page; or the upper page covers the left upper side area of the lower page; or the upper page covers the right upper side area of the lower page; or the upper page covers the left lower side area of the lower page; or the upper page covers the lower right region of the lower page. The above page coverage results in a division of the residual content of the non-occluded and occluded portions. By photographing and distinguishing the images, the technical effect of partitioning the images into different pages can be achieved. Specifically, the edge orientation of the page where the top page is located can be judged by identifying the content position of the top page, for example, the content on the page can be generally identified as a rectangular range, and the parallel expansion of the edges of the rectangle to the periphery is generally the edge orientation of the page. Searching for the first contacted content range in the process of extending the rectangle edge outwards in parallel can be judged as the residual content of the lower page covered by the first contacted content range. The specific content association range determination process can be determined according to a connected domain algorithm in the image recognition field. By the content identification system, the effect of identifying the content of different pages among a plurality of staggered pages is achieved.
The following description is made by taking a page as a test paper 104 or called answer paper and an answer sheet as examples, wherein the test paper is divided into a question area and an answer area, the test paper is provided with page number information, and the answer area is provided with an area mark. Thus, the area indicia may be included in either the non-occluded page content or the residual content. Firstly, compared with the scheme of setting a special answer sheet, the separate arrangement of the question area and the answer area on the test question paper can play a role in facilitating answering by an answer sheet, and meanwhile, wrong answer numbers are avoided. The answer area guides the user to concentrate the answers to a small area, and the shooting of the answer information by the shooting unit can be facilitated. If the user is guided to stack the test question papers after answering the questions, the stacking sequence of the stacked test question papers is obtained by erecting a camera on the upper part of a table top, for example, the user can stack the test question papers according to the prompt to expose the relevant area, for example, the part of the test question papers carrying page number information or area marks is exposed, and in this case, the processing unit can identify whether the placing relation of the test question papers meets the requirements. If the placement relationship is correct, the system can display the answer part of the user through one-time image acquisition and image transmission, and the rear end can be cloud storage or third-end correction display. The effects of saving time and data transmission bandwidth are achieved.
As an example of the scheme, the page number information may be a number of the test question paper, for example, 1, 2, 3, etc. are digitally printed on the test question paper, and is preferably designed near the answer area or near the edge of the paper. In this way, the corresponding positions of the test paper are staggered when the test paper is stacked, and whether the test paper is disordered can be judged by identifying page numbers at specific positions. Fig. 2 shows an embodiment of sequential stacking, where the basis for determination is provided by the exposed page number information. In order to avoid the problem that simple numbers are easy to be identified by mistake, the AR codes are used as area marks, and naturally, two-dimensional codes, bar codes and other setting modes can be selected. The area marks may be provided in the answer area or near the paper edge, and the cross star and the six-mango star positions in the embodiment of fig. 2 indicate design examples of the area mark positions. The AR code records at least a corresponding test paper ID, which plays a role of page number information, and the area mark is stored in the storage unit 104, and the storage unit may be set in the cloud or local. The processing unit 102 is configured to identify the test paper ID to determine whether the plurality of stacked test papers are out of order, if the region labels are set in the answer region at the right edge of the test papers, the correct stacking order should be that the region labels exposed from the front to the back test papers are in a left-to-right relationship in the spatial position, and then the processing unit is configured to identify whether page number information corresponding to the region labels appearing in the drawing satisfies the preset order from left to right. Through the scheme, the problem that the stacking position relationship among a plurality of test paper sheets is judged by setting page number information is solved, and the answer content is collected conveniently.
In other embodiments, the area markers may be set to more than two, at least two area markers identifying non-occluded page content or residual content, correcting distortion of the photographed image. The specific correction method can adjust the distortion of the image into orthographic projection by the position relation of more than two area marks, and can also correct the distortion of the whole image by identifying the shape distortion of a single mark.
In other embodiments, the area mark is a mark pair set on a single sheet of test paper, or the area mark is an AR code, that is, the answer area of each test paper includes two area marks, each mark corresponds to an ID. The processing unit is configured to identify the mark pair through the image information, and identify that the test question paper is not placed according to the requirement when one mark of the mark pair is not used, if the answer area is not completely exposed. In some preferred embodiments, two area marks may be disposed on one side near the question area, and the connection line between the two area marks is used as the boundary between the answer area and the question area or parallel to the boundary, so that once one area mark is not detected by the processing unit, it is indicated that the answer paper covered on the area mark is not placed uniformly, which is likely to cause incomplete exposure of the answer area. Through the scheme, the problem that whether the stacking of a plurality of test question papers is completely exposed or not is solved by setting the area mark, and the answer content is collected conveniently.
In still other embodiments, taking the area tag as an AR code as an example, the area tag corresponds to an ID, and the processing unit is configured to identify the content of the area tag through image information, and identify that a page is missing when the area tag corresponding to a page of test paper is missing. The region mark can be set as a mark pair on a single-page test paper, and when one group of mark pairs are missing, the test paper is judged to be a missing page. Through the scheme, the problem that whether a plurality of test sheets are unfilled by setting the area marks is solved, and the answer content is collected conveniently.
In the preferred embodiment, the answer area is arranged at the right edge of the test paper, and the left and right parts of the test paper are respectively provided with the answer area and the answer area, so that the answer area and the answer area are more in line with the reading habit of a common person. Through the setting, the practicality of this technical scheme can be promoted.
Further, in fig. 1 we see that the system further comprises a prompt unit 106, and the prompt unit 106 is configured to emit an acoustic or optical signal, for example, may be configured as a horn, a display screen, a flash lamp, or other various prompt elements. The prompting unit 106 is connected with the processing unit 102, and the processing unit may send an enabling signal to the prompting unit, or may directly control the prompting unit. In order to achieve the effect of enhancing the practicability and prompting the user, the processing unit is arranged to enable the prompting unit when the examination paper is judged to be not completely exposed out of the answer area or the examination paper is identified to be unfilled or the examination paper is disordered. Taking a prompt unit as an example of an intelligent voice assistant (capable of transplanting the prior art) in the system, when judging that the problem occurs in the placement relation of the test question paper, the intelligent voice assistant can broadcast through the voice assistant: the pages are not available, please put in order, please put the test papers in order in parallel, etc. The preset animation pictures can be played on the display screen at the same time, so that a user can understand how to correctly place the animation pictures. Through the scheme, the system can help a user to correctly use, guide the user to correctly stack test paper, collect answer contents better, and improve the practicability of the technical scheme.
In other embodiments, the processing unit 102 is further configured to divide the content of the answer area in the image information and send the content to the modifying unit 108. Under the condition that the test paper is correctly placed, the extraction of the contents of the answer regions becomes very convenient, and the scheme has great advantages in the comprehensive content extraction of a plurality of test papers, and by taking the answer regions at the right edge of the test paper as an example, by combining the setting characteristics, only the regional mark pair of the answer region at the uppermost layer needs to be identified, and the contents of the right part of the mark pair connecting line can be extracted as the contents of the answer regions. And meanwhile, the normal answer of the clients is not influenced when the clients do the questions. The correcting unit can be embedded with intelligent character recognition AI in the back-end processor and the cloud server by the prior art, and can also be sent to the correcting personnel end to receive correcting and remarking information of the correcting personnel. Through being connected with the correction end, the technical effects of extracting answer information and correcting can be achieved.
As a preferred embodiment, the above-described page recognition system may also be dedicated to exercise book content recognition without requiring additional improvements. Here, even when recognizing the image content, only the recognition algorithm in which the upper page covers the left area of the lower page and the upper page covers the right area of the lower page may be considered. Or to turn up the priority of the recognition algorithm that the upper page covers the left area of the lower page and the upper page covers the right area of the lower page. Since both types of applications are most common in the field of content recognition of a finished exercise book.
Accordingly, in the embodiment shown in fig. 3, we also introduce a page content recognition method, which includes the following steps: s300, acquiring image information of a plurality of staggered and stacked pages. The image information here includes all or part of the uppermost page, and the non-covered area where the lower page is not covered by the upper page;
s302, identifying the content of the non-shielded pages which are overlapped in a staggered way according to the image information, and the non-covered residual content of the shielded pages. The effect of identifying the content of different pages among a plurality of staggered pages is achieved.
In some other further embodiments, the area marker is included in the non-occluded page content or the residual content. We also proceed to step S304 to judge the stacking relationship between pages by region labeling. Through the step, the problem that whether the placement relation of the identification page meets the requirement can be solved. If the placement relationship is correct, a plurality of page contents can be acquired and transmitted through one image. The effects of saving time and data transmission bandwidth are achieved. In a specific application example, when the page is an answer sheet, steps S300-S304 may be executed, and the answer area content of multiple answer sheets may be transmitted and identified in the result obtained by the first image through the steps. The above method may also be changed to an exercise book content recognition method, and steps S300-S304 may be performed as well. Here, even when recognizing the image content, only the recognition algorithm in which the upper page covers the left area of the lower page and the upper page covers the right area of the lower page may be considered. Or to turn up the priority of the recognition algorithm that the upper page covers the left area of the lower page and the upper page covers the right area of the lower page.
In some specific embodiments, we take the area label as AR code as an example. The region marks are mark pairs arranged on a single sheet of test paper,
as shown in fig. 4, taking a page as an example of test paper, the method further includes step S3041 of identifying a pair of marks through image information, and identifying that the page is not placed as required when one of the marks of the pair of marks is not used, where the placement as required may be that the answer area is not completely exposed. Step S3042 may be further included, in which the content of the area mark is identified by the image information, and when the area mark corresponding to a certain page of test paper is missing, the page is identified as a missing page. The area mark may further include page information, and further includes step S3043 of identifying the page information by image information to determine whether the stacked test paper is out of order.
In some embodiments, the method further includes step S306 of sending a prompt signal when the placement relation of the test paper is abnormal. Through above-mentioned scheme can help the user correctly to use this system, guide the user to cooperate the test paper to carry out the correct stack, carry out the collection of answer content better, can promote the practicality of this technical scheme.
Further, the method further includes a step of S308 dividing the answer area content in the image information and sending it to the correction unit. Through being connected with the correction end, the technical effects of extracting answer information and correcting can be achieved.
In order to better identify the content, we also carry out a page generation method, which comprises the following steps that a non-identification area and an identification area are divided on the page, wherein the identification area is printed with an area mark, the non-identification area can be printed normally, the area mark is used for identifying the overlapping relation between the pages after being shot by a camera, and the area mark can be a page number or a characteristic code with each page ID information, such as a two-dimensional code, an AR code and the like. Specifically, the area marks are mark pairs, the mark pairs of different pages have different carried information, the corresponding relation between the area marks and the related pages is recorded in the storage medium when the area marks are generated, the mark pairs of different pages can be recorded with the sequential relation among the pages, and the mark pairs of different pages can also be recorded in the storage medium. By analyzing the area marks in the aligned storage medium, it is possible to identify whether the overlay relationship between pages is correct as described above.
In other embodiments, in order to facilitate answering the test questions and subsequent recognition and correction, taking the above page as an answer sheet as an example, we also correspondingly design an answer sheet generating method, please refer to fig. 5, which includes the steps of S500 receiving user test selection information, S502 setting a question area and an answer area on each test sheet when the selected test sheet needs to be printed, setting a test question selected by the user in the question area of the test sheet, and setting a corresponding answer reference in the answer area of the test sheet, where the answer reference includes a question number that can be represented digitally, a filling position of a transverse line, a filling position of a square or a ring, and so on. Each test question corresponds to the corresponding answer reference symbol in the horizontal direction; the answer area of each test paper is positioned on the same side of the test paper; the answer area comprises an area mark, wherein the area mark can be a two-dimensional code, a bar code or an AR code with ID information of each test paper. The test paper comprises page number information, wherein the page number information can be directly printed numbers or can be additionally represented by area marks. Through the steps, according to the test question selection of a user, the test questions are arranged at the question areas of the answer sheets of different pages, and the answer areas are uniformly arranged at the left side or the right side, so that when the answer is finished and submitted to the computer for recording, the answer information of a whole set of test questions can be correctly obtained only by identifying the area marks of the answer area parts. Thereby facilitating the correction and identification of the back end.
In some other further embodiments, the region is marked as a marker pair, and a connection line of the marker pair divides the question area and the answer area. Through the design, the computer can judge whether the answer area is shielded or not through the mark pair on the test paper when the computer is used for shooting, so that the requirement of detecting whether the test paper is completely exposed or not is met.
In other embodiments, a page generating system is designed, which comprises a page typesetting unit and a printing unit, wherein the page typesetting unit is used for dividing a non-recognition area and a recognition area on a page, a region mark is arranged on the recognition area, the printing unit is used for printing the page, and the region mark is used for recognizing a stacking relationship between the pages after being shot by a camera. The page generation system further comprises a storage medium, the corresponding relation between the region marks and the related pages is recorded in the storage medium when the page generation system generates the region marks, the sequence relation between the pages can be recorded in the mark pairs of different pages, and the corresponding relation between the region marks and the related pages can also be recorded in the storage medium. By analyzing the area marks in the aligned storage medium, it is possible to identify whether the overlay relationship between pages is correct as described above.
In the embodiment shown in fig. 6, taking a page as an answer sheet as an example, the non-recognition area and the recognition area respectively correspond to the question area and the answer area, a design is further performed that an answer sheet generating system comprises a question library unit 600, a question typesetting unit 602, a printing unit 604,
the test question library unit receives test question selection of a user, sends the selected test questions to the test question typesetting unit, and the test question typesetting unit is used for setting a question area and a question answering area on each test question paper when the test questions need to be printed into a plurality of test question papers, setting the test questions selected by the user in the question area of the test question paper, setting corresponding answer reference characters in the answer area of the test question paper, and enabling each test question to correspond to the corresponding answer reference characters in the horizontal direction; the answer area of each test paper is positioned on the same side of the test paper; the printing unit is used for printing the setting result of the test question typesetting unit onto test question paper. The question bank unit can be a database module of the system, and the typesetting unit can be embedded into the system by adopting the existing typesetting script to realize typesetting on A4 paper. The printing unit can be a printer, and the answer reference symbol comprises numbers, transverse lines, square checks or circular rings. Through the system, a user can autonomously select the test questions, the test questions are arranged at the positions of the question areas of the answer sheets of different pages, the answer areas are uniformly arranged on the left side or the right side, the efficiency of the user in answering is not affected, and the answer is not required to be copied to special answer sheets. Therefore, when the answer is finished and transmitted to the computer for recording, only the regional marks of the answer area are needed to be identified, and the answer data of a whole set of test questions can be correctly obtained. Thereby facilitating the correction and identification of the back end.
Specifically, the region is marked as a mark pair, and the connecting line of the mark pair divides the question area and the answer area. Through the design, the computer can judge whether the answer area is shielded or not through the mark pair on the test paper when the computer is used for shooting, so that the requirement of detecting whether the test paper is completely exposed or not is met.
It should be noted that, although the foregoing embodiments have been described herein, the scope of the present invention is not limited thereby. Therefore, based on the innovative concepts of the present invention, alterations and modifications to the embodiments described herein, or equivalent structures or equivalent flow transformations made by the present description and drawings, apply the above technical solution, directly or indirectly, to other relevant technical fields, all of which are included in the scope of the invention.
Claims (8)
1. A page content identification method is characterized by comprising the following steps of; acquiring image information of a plurality of staggered stacked pages, wherein the image information comprises all or part of the uppermost page and non-covered areas of the lower page which are not covered by the upper page; the page is generated by: receiving test question selection information of a user, when a plurality of test question papers need to be printed on the selected test questions, setting a question area and a question answering area on each test question paper, setting the test questions selected by the user on the question areas of the test question papers, setting corresponding answer reference characters on the question answering areas of the test question papers, wherein the question answering areas of each test question paper are positioned on the same side of the test question papers, and further comprising area marks, wherein the area marks are mark pairs, and connecting lines of the mark pairs divide the question areas and the question answering areas;
identifying the content of the non-shielded pages and the non-covered residual content of the shielded pages which are overlapped in a staggered manner according to the image information, specifically comprising the steps of identifying the content position of the uppermost page, judging the edge orientation of the page where the uppermost page is positioned, judging the content association range according to a connected domain algorithm in the image identification field, determining the rectangular range of the content on the page, enabling the rectangular range to extend to the periphery in parallel to obtain the edge orientation of the page, searching the content range which is contacted first in the process of extending the rectangular range to the periphery in parallel, judging the residual content of the lower page covered by the first content range, and judging that the page is not placed according to the specified requirement when at least one mark is identified and at least one mark is not identified.
2. The method of claim 1, wherein the staggered pages include,
the upper page covers the left side area of the lower page;
or the upper page covers the right side area of the lower page;
or the upper page covers the upper side area of the lower page;
or the upper page covers the lower side area of the lower page;
or the upper page covers the left upper side area of the lower page;
or the upper page covers the right upper side area of the lower page;
or the upper page covers the left lower side area of the lower page;
or the upper page covers the lower right region of the lower page.
3. The page content recognition method according to claim 1, further comprising the step of recognizing at least two area marks of the non-occluded page content or the residual content, correcting distortion of the photographed image.
4. The page content recognition method according to claim 1, wherein a certain area mark expected cannot be recognized in the video, and the absence of the expected page is determined.
5. The page content recognition method according to claim 1, wherein the non-covered region further includes page number information, further comprising the step of judging whether or not a plurality of stacked pages are out of order by recognizing the page number information.
6. The page content recognition method according to any one of claims 4 to 5, further comprising the step of issuing a hint signal when it is determined that the page is not laid out on specified demand or that the expected page is missing or out of order.
7. The page content recognition method according to claim 1, wherein the page includes an answer area disposed on the right side.
8. The page content identification method as claimed in claim 1, wherein the area is marked as an AR code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396610.7A CN110942054B (en) | 2019-12-30 | 2019-12-30 | Page content identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396610.7A CN110942054B (en) | 2019-12-30 | 2019-12-30 | Page content identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110942054A CN110942054A (en) | 2020-03-31 |
| CN110942054B true CN110942054B (en) | 2023-06-30 |
Family
ID=69913779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911396610.7A Active CN110942054B (en) | 2019-12-30 | 2019-12-30 | Page content identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110942054B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951133B (en) * | 2020-07-31 | 2024-03-22 | 北京伴我学教育科技有限公司 | Method, device and storage medium for assisting in solving questions |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440315A (en) * | 2013-08-27 | 2013-12-11 | 北京工业大学 | Web page cleaning method based on theme |
| CN110463177A (en) * | 2017-04-06 | 2019-11-15 | 华为技术有限公司 | The bearing calibration of file and picture and device |
Family Cites Families (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4457700B2 (en) * | 2004-03-08 | 2010-04-28 | 富士ゼロックス株式会社 | Page error inspection device |
| CN1317881C (en) * | 2004-12-30 | 2007-05-23 | 北京中星微电子有限公司 | Method for identifying multiple name cards by once photo taking by mobile terminal |
| JP4891102B2 (en) * | 2007-01-24 | 2012-03-07 | 京セラミタ株式会社 | Image forming apparatus, print preview program |
| US8915187B2 (en) * | 2007-08-07 | 2014-12-23 | Xerox Corporation | Edge marking for document identification |
| CN101896920A (en) * | 2008-03-19 | 2010-11-24 | 东莞市步步高教育电子产品有限公司 | Image processing method and device based on motion scan |
| JP4942688B2 (en) * | 2008-03-19 | 2012-05-30 | 京セラミタ株式会社 | Image forming apparatus, print preview image display program |
| CN101442484B (en) * | 2008-12-05 | 2012-09-05 | 杭州华三通信技术有限公司 | Method, system and equipment for detecting stacking multi-Active |
| JP2011123683A (en) * | 2009-12-10 | 2011-06-23 | Otari Kk | Device for measuring number of sheets |
| US20120147042A1 (en) * | 2010-06-24 | 2012-06-14 | Yuki Shinomoto | Electronic publication viewer, method for viewing electronic publication, program, and integrated circuit |
| CN102819739B (en) * | 2011-06-09 | 2016-08-10 | 汉王科技股份有限公司 | A kind of type page localization method and device |
| CN104094278A (en) * | 2012-01-23 | 2014-10-08 | 微软公司 | Pattern matching engine |
| CN202986405U (en) * | 2012-11-07 | 2013-06-12 | 张庆龙 | Multifunctional bookmark |
| CN104021419B (en) * | 2013-02-28 | 2017-09-19 | 华为终端有限公司 | A kind of method and apparatus for counting paper number |
| JP6233356B2 (en) * | 2015-07-01 | 2017-11-22 | コニカミノルタ株式会社 | Sheet size specifying system, sheet size specifying method, sheet size specifying program, and image forming apparatus |
| CN105118341B (en) * | 2015-08-21 | 2017-12-29 | 福建天晴数码有限公司 | A kind of network-based classroom instruction method and system |
| CN106023698A (en) * | 2016-07-29 | 2016-10-12 | 李铧 | Automatic reading and amending method for homework and exercise books |
| JP6575539B2 (en) * | 2017-01-30 | 2019-09-18 | 京セラドキュメントソリューションズ株式会社 | Image forming apparatus and image forming system |
| CN107016363B (en) * | 2017-03-30 | 2020-06-05 | 理光图像技术（上海）有限公司 | Bill image management device, bill image management system, and bill image management method |
| CN108334797B (en) * | 2017-06-21 | 2021-04-23 | 平安科技（深圳）有限公司 | File scanning method, device and computer readable storage medium |
| CN107622463A (en) * | 2017-09-27 | 2018-01-23 | 张鹏 | One kind makes the test and automatic marking papers system and method |
| JP6913606B2 (en) * | 2017-11-02 | 2021-08-04 | シャープ株式会社 | Image processing device |
| CN107907543A (en) * | 2017-11-10 | 2018-04-13 | 山形印刷(无锡)有限公司 | A kind of printed matter failure detection method |
| CN107908745A (en) * | 2017-11-16 | 2018-04-13 | 理光图像技术（上海）有限公司 | Masses of Document scanning collating unit, method, medium and equipment |
| CN108304836A (en) * | 2018-02-01 | 2018-07-20 | 上海海事大学 | A kind of books Ordering Detection Algorithm based on image |
| CN109255300B (en) * | 2018-08-14 | 2023-12-01 | 中国平安财产保险股份有限公司 | Bill information extraction method, bill information extraction device, computer equipment and storage medium |
| CN110298349A (en) * | 2019-06-15 | 2019-10-01 | 韶关市启之信息技术有限公司 | A kind of is quickly the method and apparatus of digital content by paper book content transformation |
-
2019
- 2019-12-30 CN CN201911396610.7A patent/CN110942054B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440315A (en) * | 2013-08-27 | 2013-12-11 | 北京工业大学 | Web page cleaning method based on theme |
| CN110463177A (en) * | 2017-04-06 | 2019-11-15 | 华为技术有限公司 | The bearing calibration of file and picture and device |
Non-Patent Citations (2)
| Title |
|---|
| Gang Chen et al .A Noisy-Or Discriminative Restricted Boltzmann Machine for Recognizing Handwriting Style Development.《2014 14th International Conference on Frontiers in Handwriting Recognition》.2014,714-719页. * |
| 魏宏喜等.一种基于连通域的蒙古文文档图像版面分析方法.《内蒙古大学学报》.2007,第38卷(第5期),586-590页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110942054A (en) | 2020-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101648756B1 (en) | Examination paper recognition and scoring system | |
| US7764923B2 (en) | Material processing apparatus and method for grading material | |
| US7227997B2 (en) | Image recognition apparatus, image recognition method, and image recognition program | |
| CN110942054B (en) | Page content identification method | |
| CN111126017A (en) | Answer sheet generation system | |
| CN110968277B (en) | Answer sheet generation method | |
| CN111144343B (en) | Answer sheet content identification system | |
| CN111178269B (en) | Answer sheet content identification method | |
| CN111144342B (en) | Page content identification system | |
| CN110969152B (en) | Exercise book content identification method | |
| CN111178268B (en) | Exercise book content identification system | |
| CN111221607B (en) | Page generation method | |
| CN111176775B (en) | Page generation system | |
| US7853194B2 (en) | Material processing apparatus, material processing method and material processing program | |
| US9531906B2 (en) | Method for automatic conversion of paper records to digital form | |
| US7865130B2 (en) | Material processing apparatus, material processing method, and material processing program product | |
| CN113378822A (en) | System for marking handwritten answer area by using special mark frame in test paper | |
| EP0471257A2 (en) | Dot constrained hand printed character recognition system and method | |
| JP2001154573A (en) | Automatic marking method and system therefor | |
| CN117037187A (en) | Test paper image extraction method and device and terminal equipment | |
| CN116824601A (en) | Correction assisting method, device, system, processing equipment and storage medium | |
| JP2007018215A (en) | System and program for processing tabulation | |
| CN118607470A (en) | Method and device for printing job correction mark, electronic equipment and storage medium | |
| JPH09214648A (en) | Image processor | |
| US20190055693A1 (en) | Processing print media |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |