CN113408521A - Answer picture identification method, reading and amending device and storage medium - Google Patents
Answer picture identification method, reading and amending device and storage medium Download PDFInfo
- Publication number
- CN113408521A CN113408521A CN202110804000.7A CN202110804000A CN113408521A CN 113408521 A CN113408521 A CN 113408521A CN 202110804000 A CN202110804000 A CN 202110804000A CN 113408521 A CN113408521 A CN 113408521A
- Authority
- CN
- China
- Prior art keywords
- answer
- matching
- template
- picture
- gray
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application relates to an answer picture identification method, an approval device and a storage medium. The identification method comprises the following steps: selecting an answer identification template with the same number of pages according to the number of pages of the homework or test paper; carrying out gray level matching according to the identification area of each original image and a preset matching area on the answer identification template to determine a first gray level matching value of each original image; scanning each page of the homework or test paper to generate an original answer picture; determining whether each original image of the answer needs to be identified after being rotated according to the gray matching value of each original image of the answer; when the answer identification template is judged not to be rotated, identifying each original answer picture according to the answer identification template; and when the answer is judged to be rotated, identifying each answer rotation picture according to the answer identification template. The method and the device effectively solve the problem of rescanning identification caused by inconsistent directions of collected test papers or jobs.
Description
Technical Field
The present disclosure relates to the field of image recognition, and in particular, to an answer image recognition method, an approval device, and a storage medium.
Background
With the development of science and technology, the reading and amending device with a test paper or operation recognition system is widely applied to school education, collected test paper or operation can be scanned into an original answer picture, and the original answer picture is read through the recognition system. In the prior art, the collected test paper or operation directions are inconsistent, so that the test paper or operation needs to be unified in direction and scanned again for identification when the test paper or operation is read by an identification system, and unnecessary troubles and workload are caused.
Disclosure of Invention
In order to solve the technical problem or at least partially solve the technical problem, the present application provides an answer sheet recognition method, an approval apparatus, and a storage medium.
In a first aspect, the present application provides an answer image recognition method, where the answer image recognition method includes:
selecting an answer identification template with the same number of pages according to the number of pages of the homework or test paper;
carrying out gray level matching according to the identification area of each original image and a preset matching area on the answer identification template to determine a first gray level matching value of each original image; scanning each page of the homework or test paper to generate an original answer picture;
determining whether each original image of the answer needs to be identified after being rotated according to the gray matching value of each original image of the answer;
when the answer identification template is judged not to be rotated, identifying each original answer picture according to the answer identification template;
and when the answer is judged to be rotated, identifying each answer rotation picture according to the answer identification template.
Optionally, the answer rotation picture is obtained by rotating the answer original picture by 180 degrees;
the step of determining whether to identify each original image of the answer after rotating according to the gray matching value of each original image of the answer includes:
for the condition that the operation or the test paper is one page, when the first gray matching value of one original answer picture corresponding to the operation or the test paper is not less than a preset turning matching threshold value, judging that the original answer picture does not need to be rotated; otherwise, judging that the original image of the answer needs to be rotated;
for the case that the job or the test paper is two pages, when the second gray matching value of the first original image is not less than the turning matching threshold, or the third gray matching value of the second original image is not less than the turning matching threshold, judging that the original images do not need to be rotated; otherwise, judging that the original pictures of the answers need to be rotated.
Optionally, when it is determined that rotation is not required, identifying each original answer picture according to the answer identification template includes:
for the condition that the operation or the test paper is one page, identifying the original answer picture corresponding to the operation or the test paper according to the answer identification template;
for the condition that the operation or the test paper is two pages, when the second gray matching value is not less than the third gray matching value, respectively identifying a first answer original picture and a second answer original picture according to a first page matching template and a second page matching template of the answer identification template; and when the second gray matching value is smaller than the third gray matching value, respectively identifying the first answer original picture and the second answer original picture according to the second page matching template and the first page matching template of the answer identification template.
Optionally, when it is determined that rotation is required, identifying each answer rotation picture according to the answer identification template includes:
for the case where the job or test paper is one page:
carrying out gray matching on the identification area of the answer rotating picture corresponding to the operation or the test paper and a preset matching area on the answer identification template to determine a fourth gray matching value of the answer rotating picture;
judging whether the first gray matching value is smaller than a preset minimum matching threshold value or not;
under the condition that the first gray matching value is smaller than the minimum matching threshold, judging whether the fourth gray matching value is smaller than a preset turning matching threshold, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the preset turning matching threshold; when the fourth gray matching value is not greater than a preset minimum matching threshold value, judging that the answer original picture and the answer rotating picture are not matched with the selected answer identification template; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, identifying the answer rotating picture according to the answer identification template;
judging whether the fourth gray matching value is smaller than the turning matching threshold value or not under the condition that the first gray matching value is not smaller than the minimum matching value, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the turning matching threshold value; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, according to the size relationship between the first gray matching value and the fourth gray matching value, identifying an original answer picture or a rotated answer picture according to the answer identification template; and when the fourth gray matching value is not greater than the minimum matching threshold value, identifying the answer original picture according to the answer identification template.
Optionally, when it is determined that rotation is required, identifying each answer rotation picture according to the answer identification template includes:
for the case where the job or test paper is two pages:
carrying out gray level matching on the identification areas of the first and second answer rotation pictures and a preset matching area on the answer identification template respectively, and determining a fifth gray level matching value of the first answer rotation picture and a sixth gray level matching value of the second answer rotation picture;
judging whether the fifth gray matching value is not smaller than the turning matching threshold or not, or whether the sixth gray matching value is not smaller than the turning matching threshold or not;
if so, when the fifth grayscale matching value is not less than the sixth grayscale matching value, respectively identifying a first answer rotation picture and a second answer rotation picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is smaller than the sixth gray matching value, respectively identifying a first answer rotating picture and a second answer rotating picture according to a second matching template and a first matching template of the answer identifying template;
if not, judging that the first answer and second original pictures and the first and second answer rotating pictures are not matched with the answer identification template when the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value are all smaller than the minimum matching threshold value; otherwise, the maximum value of the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value is judged; when the second gray matching value is the maximum value, identifying a first answer original picture and a second answer original picture according to a first matching template and a second matching template of the answer identification template; when the third gray matching value is the maximum value, identifying a second answer original picture and a first answer original picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the first matching template and the second matching template of the answer identifying template; and when the sixth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the second matching template and the first matching template of the answer identifying template.
Optionally, the flip matching threshold is 85% and the minimum matching threshold is 55%.
Optionally, before performing gray matching according to the identification region of each original answer picture and the matching region preset on the answer identification template and determining the first gray matching value of each original answer picture, the method includes:
and determining the identification area of the original answer picture according to the preset matching area on the answer identification template.
Optionally, before determining the recognition area of the original answer picture according to the preset matching area on the answer recognition template, the method includes:
and setting a matching area on the answer recognition template according to a preset matching accuracy, wherein the matching accuracy is in direct proportion to the size of the matching area on the answer recognition template.
In a second aspect, the present application provides an approving device comprising a memory and a processor; the memory stores a computer program; the computer program, when executed by the processor, implements the steps of the answer sheet recognition method described in any one of the above.
In a third aspect, the present application provides a computer-readable storage medium, where an answer sheet identification program is stored, and when the answer sheet identification program is executed by a processor, the steps of the answer sheet identification method described in any one of the above are implemented.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the method and the device, the problem of rescanning identification caused by inconsistent directions of collected test papers or jobs is effectively solved, and the reading efficiency of the jobs and examinations is improved. .
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of an answer image recognition method provided in each embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
Example one
The embodiment of the invention provides an answer picture identification method, and as shown in fig. 1, the answer picture identification method includes:
s101, selecting an answer identification template with the same number of pages according to the number of pages of the job or the test paper;
s102, carrying out gray level matching according to the identification area of each original image and a preset matching area on the answer identification template, and determining a first gray level matching value of each original image; scanning each page of the homework or test paper to generate an original answer picture;
s103, determining whether each original image of the answer needs to be identified after rotation according to the gray matching value of each original image of the answer;
s104, when the answer identification template is judged not to be rotated, identifying each original answer picture according to the answer identification template;
and S105, when the rotation is judged to be needed, identifying each answer rotation picture according to the answer identification template.
The embodiment of the invention effectively solves the problem of rescanning identification caused by inconsistent directions of collected test papers or jobs, and improves the reading efficiency of the jobs and examinations.
The answer rotating picture is obtained by rotating the answer original picture by 180 degrees; the flip match threshold is 85% and the minimum match threshold is 55%.
Before S102, the method may further include: and determining the identification area of the original answer picture according to the preset matching area on the answer identification template. Of course, before determining the recognition area of the original answer picture according to the preset matching area on the answer recognition template, the method includes:
and setting a matching area on the answer recognition template according to a preset matching accuracy, wherein the matching accuracy is in direct proportion to the size of the matching area on the answer recognition template.
That is to say, the larger the matching area selected in the embodiment of the present invention is, the higher the accuracy is, and in the embodiment of the present invention, more than 85% is obtained as a matching value for determining a certain matching through repeated experiments; less than 55% as a certain unmatched match; and identifying the test paper with the matching value between 85% and 55% and the highest matching value according to different states of the test paper.
In some embodiments, the determining whether to perform recognition after rotation on each original answer picture according to the gray-scale matching value of each original answer picture includes:
for the condition that the operation or the test paper is one page, when the first gray matching value of one original answer picture corresponding to the operation or the test paper is not less than a preset turning matching threshold value, judging that the original answer picture does not need to be rotated; otherwise, judging that the original image of the answer needs to be rotated;
for the case that the job or the test paper is two pages, when the second gray matching value of the first original image is not less than the turning matching threshold, or the third gray matching value of the second original image is not less than the turning matching threshold, judging that the original images do not need to be rotated; otherwise, judging that the original pictures of the answers need to be rotated.
In the embodiment, different judgment logics are adopted for the single-page and double-page jobs or test papers, so that the identification accuracy can be effectively ensured.
In some embodiments, when it is determined that rotation is not required, identifying each original answer picture according to the answer identification template includes:
for the condition that the operation or the test paper is one page, identifying the original answer picture corresponding to the operation or the test paper according to the answer identification template;
for the condition that the operation or the test paper is two pages, when the second gray matching value is not less than the third gray matching value, respectively identifying a first answer original picture and a second answer original picture according to a first page matching template and a second page matching template of the answer identification template; and when the second gray matching value is smaller than the third gray matching value, respectively identifying the first answer original picture and the second answer original picture according to the second page matching template and the first page matching template of the answer identification template.
In some embodiments, when it is determined that rotation is required, identifying each answer rotation picture according to the answer identification template includes:
for the case where the job or test paper is one page:
carrying out gray matching on the identification area of the answer rotating picture corresponding to the operation or the test paper and a preset matching area on the answer identification template to determine a fourth gray matching value of the answer rotating picture;
judging whether the first gray matching value is smaller than a preset minimum matching threshold value or not;
under the condition that the first gray matching value is smaller than the minimum matching threshold, judging whether the fourth gray matching value is smaller than a preset turning matching threshold, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the preset turning matching threshold; when the fourth gray matching value is not greater than a preset minimum matching threshold value, judging that the answer original picture and the answer rotating picture are not matched with the selected answer identification template; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, identifying the answer rotating picture according to the answer identification template;
judging whether the fourth gray matching value is smaller than the turning matching threshold value or not under the condition that the first gray matching value is not smaller than the minimum matching value, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the turning matching threshold value; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, according to the size relationship between the first gray matching value and the fourth gray matching value, identifying an original answer picture or a rotated answer picture according to the answer identification template; and when the fourth gray matching value is not greater than the minimum matching threshold value, identifying the answer original picture according to the answer identification template.
For the case where the job or test paper is two pages:
carrying out gray level matching on the identification areas of the first and second answer rotation pictures and a preset matching area on the answer identification template respectively, and determining a fifth gray level matching value of the first answer rotation picture and a sixth gray level matching value of the second answer rotation picture;
judging whether the fifth gray matching value is not smaller than the turning matching threshold or not, or whether the sixth gray matching value is not smaller than the turning matching threshold or not;
if so, when the fifth grayscale matching value is not less than the sixth grayscale matching value, respectively identifying a first answer rotation picture and a second answer rotation picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is smaller than the sixth gray matching value, respectively identifying a first answer rotating picture and a second answer rotating picture according to a second matching template and a first matching template of the answer identifying template;
if not, judging that the first answer and second original pictures and the first and second answer rotating pictures are not matched with the answer identification template when the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value are all smaller than the minimum matching threshold value; otherwise, the maximum value of the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value is judged; when the second gray matching value is the maximum value, identifying a first answer original picture and a second answer original picture according to a first matching template and a second matching template of the answer identification template; when the third gray matching value is the maximum value, identifying a second answer original picture and a first answer original picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the first matching template and the second matching template of the answer identifying template; and when the sixth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the second matching template and the first matching template of the answer identifying template.
In the embodiment, in the process of identifying double pages, a strategy different from that of a single page is adopted, so that the efficiency of identifying double pages can be effectively improved, and the answer pictures are processed before the examination paper is identified according to the logic, so that the finally identified answer pictures are all in correct picture sequence. When there is an error in the direction of placing an individual test paper or a job in the scanning, it is not necessary to take time and effort to deal with the abnormality caused by the error.
The following describes the embodiments of the present invention in detail by taking test paper as an example.
The answer image recognition method in the embodiment comprises the following steps:
step 1, scanning the test paper to obtain an original answer picture of the scanned test paper.
And 2, judging whether the test paper is a single page or a double page. Step 3 is performed for single pages and step 10 is performed for double pages.
And 3, carrying out gray level matching on the identification area of the answer original picture of the single sheet of the test paper and the matching area of the selected answer identification template in the single sheet.
And 4, judging whether the first gray matching value of the original image of the answer is not less than a preset turning matching threshold value. If yes, step 5 is executed, and if no, step 6 is executed.
And 5, identifying the original answer picture corresponding to the operation or the test paper according to the answer identification template.
And 6, rotating the original answer picture by 180 degrees, carrying out gray matching on the identification area of the answer rotation picture corresponding to the operation or the test paper and the preset matching area on the answer identification template, and determining a fourth gray matching value of the answer rotation picture.
And 7, judging whether the first gray matching value is smaller than a preset minimum matching threshold value. If the first grayscale matching value is smaller than the minimum matching threshold, step 8 is performed, and if the first grayscale matching value is not smaller than the minimum matching threshold, step 9 is performed.
Step 8, under the condition that the first gray matching value is smaller than the minimum matching threshold, judging whether the fourth gray matching value is smaller than a preset turning matching threshold, and when the fourth gray matching value is not smaller than the preset turning matching threshold, identifying the answer rotating picture according to the answer identification template; when the fourth gray matching value is not greater than a preset minimum matching threshold value, judging that the answer original picture and the answer rotating picture are not matched with the selected answer identification template; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, identifying the answer rotating picture according to the answer identification template;
step 9, under the condition that the first gray matching value is not less than the minimum matching value, judging whether the fourth gray matching value is less than the turning matching threshold value, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not less than the turning matching threshold value; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, according to the size relationship between the first gray matching value and the fourth gray matching value, identifying an original answer picture or a rotated answer picture according to the answer identification template; when the fourth grayscale matching value is not greater than the minimum matching threshold
And identifying the original image of the answer according to the answer identification template.
Step 10, for the case that the job or the test paper is two pages, when the second gray matching value is not less than the third gray matching value, respectively identifying a first answer original picture and a second answer original picture according to a first page matching template and a second page matching template of the answer identification template; and when the second gray matching value is smaller than the third gray matching value, respectively identifying the first answer original picture and the second answer original picture according to the second page matching template and the first page matching template of the answer identification template.
Step 11, carrying out gray level matching on the identification areas of the first and second answer rotation pictures and a matching area preset on the answer identification template respectively, and determining a fifth gray level matching value of the first answer rotation picture and a sixth gray level matching value of the second answer rotation picture;
step 12, judging whether the fifth gray matching value is not less than the flip matching threshold or whether the sixth gray matching value is not less than the flip matching threshold;
step 13, in the case of yes, when the fifth grayscale matching value is not less than the sixth grayscale matching value, respectively identifying the first answer rotation picture and the second answer rotation picture according to the first matching template and the second matching template of the answer identification template; when the fifth gray matching value is smaller than the sixth gray matching value, respectively identifying a first answer rotating picture and a second answer rotating picture according to a second matching template and a first matching template of the answer identifying template;
step 14, in the case of no, when the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value are all smaller than the minimum matching threshold, determining that the first answer and the second answer original pictures and the first answer and the second answer rotated pictures are not matched with the answer identification template; otherwise, the maximum value of the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value is judged; when the second gray matching value is the maximum value, identifying a first answer original picture and a second answer original picture according to a first matching template and a second matching template of the answer identification template; when the third gray matching value is the maximum value, identifying a second answer original picture and a first answer original picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the first matching template and the second matching template of the answer identifying template; and when the sixth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the second matching template and the first matching template of the answer identifying template.
In the embodiment, in the process of identifying double pages, a strategy different from that of a single page is adopted, so that the efficiency of identifying double pages can be effectively improved, and the answer pictures are processed before the examination paper is identified according to the logic, so that the finally identified answer pictures are all in correct picture sequence. When there is an error in the direction of placing an individual test paper or a job in the scanning, it is not necessary to take time and effort to deal with the abnormality caused by the error.
Example two
The embodiment of the invention provides a reading device, which comprises a memory and a processor; the memory stores a computer program; the computer program, when executed by the processor, implements the steps of the answer sheet recognition method according to any one of the embodiments.
EXAMPLE III
The embodiment of the present invention provides a computer-readable storage medium, where an answer image recognition program is stored on the computer-readable storage medium, and when the answer image recognition program is executed by a processor, the steps of the answer image recognition method according to any one of the embodiments are implemented.
In the specific implementation process of the second embodiment and the third embodiment, reference may be made to the first embodiment, and corresponding technical effects are achieved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. An answer picture recognition method, characterized in that, the answer picture recognition method comprises:
selecting an answer identification template with the same number of pages according to the number of pages of the homework or test paper;
carrying out gray level matching according to the identification area of each original image and a preset matching area on the answer identification template to determine a first gray level matching value of each original image; scanning each page of the homework or test paper to generate an original answer picture;
determining whether each original image of the answer needs to be identified after being rotated according to the gray matching value of each original image of the answer;
when the answer identification template is judged not to be rotated, identifying each original answer picture according to the answer identification template;
and when the answer is judged to be rotated, identifying each answer rotation picture according to the answer identification template.
2. The answer picture recognition method according to claim 1, wherein the answer rotated picture is obtained by rotating the answer original picture by 180 degrees;
the step of determining whether to identify each original image of the answer after rotating according to the gray matching value of each original image of the answer includes:
for the condition that the operation or the test paper is one page, when the first gray matching value of one original answer picture corresponding to the operation or the test paper is not less than a preset turning matching threshold value, judging that the original answer picture does not need to be rotated; otherwise, judging that the original image of the answer needs to be rotated;
for the case that the job or the test paper is two pages, when the second gray matching value of the first original image is not less than the turning matching threshold, or the third gray matching value of the second original image is not less than the turning matching threshold, judging that the original images do not need to be rotated; otherwise, judging that the original pictures of the answers need to be rotated.
3. The answer picture recognition method according to claim 2, wherein recognizing each original answer picture according to the answer recognition template when it is determined that rotation is not required, comprises:
for the condition that the operation or the test paper is one page, identifying the original answer picture corresponding to the operation or the test paper according to the answer identification template;
for the condition that the operation or the test paper is two pages, when the second gray matching value is not less than the third gray matching value, respectively identifying a first answer original picture and a second answer original picture according to a first page matching template and a second page matching template of the answer identification template; and when the second gray matching value is smaller than the third gray matching value, respectively identifying the first answer original picture and the second answer original picture according to the second page matching template and the first page matching template of the answer identification template.
4. The answer picture recognition method according to claim 2, wherein when it is determined that rotation is required, recognizing each of the answer rotation pictures according to the answer recognition template comprises:
for the case where the job or test paper is one page:
carrying out gray matching on the identification area of the answer rotating picture corresponding to the operation or the test paper and a preset matching area on the answer identification template to determine a fourth gray matching value of the answer rotating picture;
judging whether the first gray matching value is smaller than a preset minimum matching threshold value or not;
under the condition that the first gray matching value is smaller than the minimum matching threshold, judging whether the fourth gray matching value is smaller than a preset turning matching threshold, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the preset turning matching threshold; when the fourth gray matching value is not greater than a preset minimum matching threshold value, judging that the answer original picture and the answer rotating picture are not matched with the selected answer identification template; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, identifying the answer rotating picture according to the answer identification template;
judging whether the fourth gray matching value is smaller than the turning matching threshold value or not under the condition that the first gray matching value is not smaller than the minimum matching value, and identifying the answer rotating picture according to the answer identification template when the fourth gray matching value is not smaller than the turning matching threshold value; when the fourth gray matching value is between the minimum matching threshold and the turning matching threshold, according to the size relationship between the first gray matching value and the fourth gray matching value, identifying an original answer picture or a rotated answer picture according to the answer identification template; and when the fourth gray matching value is not greater than the minimum matching threshold value, identifying the answer original picture according to the answer identification template.
5. The answer picture recognition method according to claim 2, wherein when it is determined that rotation is required, recognizing each of the answer rotation pictures according to the answer recognition template comprises:
for the case where the job or test paper is two pages:
carrying out gray level matching on the identification areas of the first and second answer rotation pictures and a preset matching area on the answer identification template respectively, and determining a fifth gray level matching value of the first answer rotation picture and a sixth gray level matching value of the second answer rotation picture;
judging whether the fifth gray matching value is not smaller than the turning matching threshold or not, or whether the sixth gray matching value is not smaller than the turning matching threshold or not;
if so, when the fifth grayscale matching value is not less than the sixth grayscale matching value, respectively identifying a first answer rotation picture and a second answer rotation picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is smaller than the sixth gray matching value, respectively identifying a first answer rotating picture and a second answer rotating picture according to a second matching template and a first matching template of the answer identifying template;
if not, judging that the first answer and second original pictures and the first and second answer rotating pictures are not matched with the answer identification template when the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value are all smaller than the minimum matching threshold value; otherwise, the maximum value of the second gray matching value, the third gray matching value, the fifth gray matching value and the sixth gray matching value is judged; when the second gray matching value is the maximum value, identifying a first answer original picture and a second answer original picture according to a first matching template and a second matching template of the answer identification template; when the third gray matching value is the maximum value, identifying a second answer original picture and a first answer original picture according to a first matching template and a second matching template of the answer identification template; when the fifth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the first matching template and the second matching template of the answer identifying template; and when the sixth gray matching value is the maximum value, identifying the first answer rotating picture and the second answer rotating picture according to the second matching template and the first matching template of the answer identifying template.
6. The answer picture recognition method according to claim 4 or 5, wherein the flip matching threshold is 85% and the minimum matching threshold is 55%.
7. The answer picture identification method according to any one of claims 1 to 5, wherein before determining the first gray matching value of each original answer picture by performing gray matching according to the identification region of each original answer picture and the matching region preset on the answer identification template, the method comprises:
and determining the identification area of the original answer picture according to the preset matching area on the answer identification template.
8. The answer picture recognition method according to claim 7, wherein before determining the recognition area of the original answer picture according to the matching area preset on the answer recognition template, the method comprises:
and setting a matching area on the answer recognition template according to a preset matching accuracy, wherein the matching accuracy is in direct proportion to the size of the matching area on the answer recognition template.
9. An approval device, wherein the approval device comprises a memory and a processor; the memory stores a computer program; the computer program realizes the steps of the answer sheet recognition method according to any one of claims 1-8 when executed by the processor.
10. A computer-readable storage medium, on which an answer sheet identification program is stored, which, when executed by a processor, implements the steps of the answer sheet identification method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110804000.7A CN113408521B (en) | 2021-07-16 | 2021-07-16 | Answer picture identification method, reading device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110804000.7A CN113408521B (en) | 2021-07-16 | 2021-07-16 | Answer picture identification method, reading device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408521A true CN113408521A (en) | 2021-09-17 |
| CN113408521B CN113408521B (en) | 2023-09-05 |
Family
ID=77686858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110804000.7A Active CN113408521B (en) | 2021-07-16 | 2021-07-16 | Answer picture identification method, reading device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408521B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872475A (en) * | 2009-04-22 | 2010-10-27 | 中国科学院自动化研究所 | Method for automatically registering scanned document images |
| CN106033535A (en) * | 2015-03-18 | 2016-10-19 | 成都理想境界科技有限公司 | Electronic paper marking method |
| WO2017050083A1 (en) * | 2015-09-23 | 2017-03-30 | 广州视源电子科技股份有限公司 | Element identification method and device |
| CN106898085A (en) * | 2017-02-23 | 2017-06-27 | 深圳怡化电脑股份有限公司 | Identification bank note towards method and device |
| CN110555375A (en) * | 2019-07-24 | 2019-12-10 | 武汉天喻教育科技有限公司 | Method for identifying filling information of answer sheet |
| CN110689013A (en) * | 2019-10-10 | 2020-01-14 | 北京课程帮科技有限公司 | Automatic marking method and system based on feature recognition |
| CN112347946A (en) * | 2020-11-10 | 2021-02-09 | 成都兴唐信息技术有限公司 | Method and system for identifying multi-type answer sheet |
| CN112383670A (en) * | 2020-11-10 | 2021-02-19 | 武汉天有科技有限公司 | Test paper scanning automatic centering method and device |
| CN112613506A (en) * | 2020-12-23 | 2021-04-06 | 金蝶软件（中国）有限公司 | Method and device for recognizing text in image, computer equipment and storage medium |
| CN113076872A (en) * | 2021-04-01 | 2021-07-06 | 杭州云梯科技有限公司 | Intelligent test paper correcting method |
-
2021
- 2021-07-16 CN CN202110804000.7A patent/CN113408521B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872475A (en) * | 2009-04-22 | 2010-10-27 | 中国科学院自动化研究所 | Method for automatically registering scanned document images |
| CN106033535A (en) * | 2015-03-18 | 2016-10-19 | 成都理想境界科技有限公司 | Electronic paper marking method |
| WO2017050083A1 (en) * | 2015-09-23 | 2017-03-30 | 广州视源电子科技股份有限公司 | Element identification method and device |
| CN106898085A (en) * | 2017-02-23 | 2017-06-27 | 深圳怡化电脑股份有限公司 | Identification bank note towards method and device |
| CN110555375A (en) * | 2019-07-24 | 2019-12-10 | 武汉天喻教育科技有限公司 | Method for identifying filling information of answer sheet |
| CN110689013A (en) * | 2019-10-10 | 2020-01-14 | 北京课程帮科技有限公司 | Automatic marking method and system based on feature recognition |
| CN112347946A (en) * | 2020-11-10 | 2021-02-09 | 成都兴唐信息技术有限公司 | Method and system for identifying multi-type answer sheet |
| CN112383670A (en) * | 2020-11-10 | 2021-02-19 | 武汉天有科技有限公司 | Test paper scanning automatic centering method and device |
| CN112613506A (en) * | 2020-12-23 | 2021-04-06 | 金蝶软件（中国）有限公司 | Method and device for recognizing text in image, computer equipment and storage medium |
| CN113076872A (en) * | 2021-04-01 | 2021-07-06 | 杭州云梯科技有限公司 | Intelligent test paper correcting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408521B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220101030A1 (en) | Examination paper correction method and apparatus, electronic device, and storage medium | |
| US20220067416A1 (en) | Method and device for generating collection of incorrectly-answered questions | |
| US20050207635A1 (en) | Method and apparatus for printing documents that include MICR characters | |
| SE508972C2 (en) | Procedure for quality assurance when scanning / copying images / documents and device for carrying out the procedure | |
| CN112669515B (en) | Bill image recognition method and device, electronic equipment and storage medium | |
| CN105787425A (en) | Information processing apparatus, system, and information processing method | |
| CN111914597A (en) | Document comparison identification method and device, electronic equipment and readable storage medium | |
| CN110879965A (en) | Automatic reading and amending method of test paper objective questions, electronic device, equipment and storage medium | |
| CN114648776B (en) | Financial reimbursement data processing method and processing system | |
| CN112418206B (en) | Picture classification method based on position detection model and related equipment thereof | |
| CN113221897A (en) | Image correction method, image text recognition method, identity verification method and device | |
| CN113408521B (en) | Answer picture identification method, reading device and storage medium | |
| CN111178365A (en) | Picture character recognition method and device, electronic equipment and storage medium | |
| CN116050379A (en) | Document comparison method and storage medium | |
| CN110119743B (en) | Picture identification method, server and computer readable storage medium | |
| CN113408520A (en) | Marking paper reading method, marking paper reading device and storage medium | |
| CN106485586A (en) | The management method of insurance policy and device | |
| CN113705157A (en) | Method for correcting paper work by photographing | |
| CN111242112A (en) | Image processing method, identity information processing method and device | |
| CN117058700B (en) | Answer sheet identification method, device, equipment and storage medium | |
| JP4974794B2 (en) | Document recognition apparatus, document recognition method, and computer program | |
| CN113139071A (en) | Document processing system and method for classifying documents by machine learning | |
| CN113936277A (en) | Double-mode identification method, system and medium for handwritten name and school number | |
| Lu et al. | Online image classification under monotonic decision boundary constraint | |
| CN115866147A (en) | Image processing method, system, storage medium and electronic device |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220321 Address after: 100085 205, floor 2, building 8, Shangdi Fourth Street, Haidian District, Beijing Applicant after: Beijing Nanhao Science and Technology Co.,Ltd. Applicant after: Huayun (Hebei xiong'an) big data Technology Co.,Ltd. Address before: 100085 205, floor 2, building 8, Shangdi Fourth Street, Haidian District, Beijing Applicant before: Beijing Nanhao Science and Technology Co.,Ltd. Applicant before: Jinghao (Hebei xiong'an) data Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |