A single page scanning blank page processing system and method based on a review system

Abstract

The application discloses a kind of based on the single page scanning blank page processing system and method of reading system, system includes: examination information module: for storing the student information that should participate in examination and the student information of various schools pre-uploaded absent from examination;Image acquisition module: for collecting volume image;Blank page detection module: for detecting whether the volume image collected exists blank page;Recording module: for when blank page detection module detects blank page, record the blank page related data;Verification module: for checking whether there is the possibility of reverse page in the blank page detected according to the following process, the reverse page is the volume image obtained due to error reverse test paper or answer sheet.The blank page in volume image is automatically identified, and whether there is reverse page is judged, when finding there is reverse page risk, staff goes to find verification again, and the position of blank page can be efficiently positioned, so the workload of staff can be greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent marking technology, specifically to a single-page scanning blank page processing system and method based on a marking system. Background Technology

[0002] During the intelligent marking process, due to the large number of examinees and the tight time constraints of scanning, operational errors are prone to occur. One common error is that when scanning answer sheets with only one page containing answers, the answer sheet is placed upside down, with the blank back page placed on the front, resulting in a blank image. The current common approach is to simply ignore the blank paper and treat it as if the student was absent. This method is extremely unfair, but manually searching for images or checking answer sheets page by page is extremely inefficient. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention aims to provide a single-page scanning blank page processing system and method based on a marking system.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] A single-page scanning blank page processing system based on a marking system includes:

[0006] Examination information module: This module stores information on students who should take the exam, as well as information on absent students uploaded in advance by various schools. The student information includes their name and exam number.

[0007] Image acquisition module: Used to acquire images of students' completed test papers or answer sheets awaiting grading;

[0008] Blank page detection module: used to detect whether there are blank pages in the acquired roll image;

[0009] Recording module: When the blank page detection module detects a blank page, it records the relevant data of the blank page. The relevant data includes the ID of the blank page, as well as the candidate information of the previous and next page images of the exam paper in the scanning order. The ID of each exam paper image is generated according to its scanning order. If there is no corresponding candidate information before or after the blank page, the missing candidate information of the previous or next page is recorded.

[0010] Verification module: Used to verify whether there is a possibility of an inverted page among the detected blank pages, wherein the inverted page is the image of the test paper or answer sheet obtained due to an error:

[0011] 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module;

[0012] 2) Count the total number of collected test paper images and the total number of detected blank pages;

[0013] 3) Calculate the difference between the total number of images on the exam paper and the total number of blank pages, and record it as the actual number of test takers; record the sum of the actual number of test takers and the number of absent test takers as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, then it is determined that there are no reversed pages among the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, then it is determined that there may be reversed pages among the detected blank pages.

[0014] Furthermore, the image acquisition module is also used to preprocess the acquired roll image, and the preprocessing includes one or more of rectangular correction, inversion correction, and curved surface correction.

[0015] Furthermore, the blank page detection module is used to detect blank pages in any of the following ways:

[0016] (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page.

[0017] (2) Detect whether the paper image has a preset positioning point. If no preset positioning point is detected, the paper image is determined to be a blank page.

[0018] (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram;

[0019] (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range on the paper image with a preset pixel value threshold, and if it is less than the preset pixel value threshold, then determine that the paper image is a blank page.

[0020] The present invention also provides a method for operating the above-mentioned system, the specific process of which is as follows:

[0021] The exam administration information module stores information on students who should take the exam and information on students who are absent, which has been uploaded in advance by each school.

[0022] After the exam, the image acquisition module is used to capture images of the students' completed exam papers or answer sheets that are awaiting grading;

[0023] After the data acquisition is completed, the blank page detection module checks whether there are blank pages in the acquired paper image;

[0024] When the blank page detection module detects a blank page, the recording module records the relevant data of the blank page;

[0025] Then, the verification module checks whether there is an inverted page among the detected blank pages according to the following process. The inverted page is the image of the test paper or answer sheet obtained due to an error:

[0026] 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module;

[0027] 2) Count the total number of collected test paper images and the total number of detected blank pages;

[0028] 3) Calculate the difference between the total number of images on the exam paper and the total number of blank pages, and record it as the actual number of test takers; record the sum of the actual number of test takers and the number of absent test takers as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, then it is determined that there are no reversed pages among the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, then it is determined that there may be reversed pages among the detected blank pages.

[0029] When the verification module detects the possibility of a reversed page among the blank pages, it prompts the staff. The staff then searches the test paper or answer sheet based on the blank page data recorded by the recording module to verify whether each blank page is indeed a reversed page.

[0030] Furthermore, after acquiring the paper image, the image acquisition module further preprocesses the acquired paper image, and the preprocessing includes one or more of the following: rectangular correction, inversion correction, and curved surface correction.

[0031] Furthermore, the blank page detection module performs blank page detection in any of the following ways:

[0032] (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page.

[0033] (2) Detect whether the paper image has a preset positioning point. If no preset positioning point is detected, the paper image is determined to be a blank page.

[0034] (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram;

[0035] (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range on the paper image with a preset pixel value threshold, and if it is less than the preset pixel value threshold, then determine that the paper image is a blank page.

[0036] The beneficial effects of this invention are as follows: This invention automatically identifies blank pages in the paper image and determines whether there are reversed pages. When a risk of reversed pages is found, staff can then search and verify the information. Furthermore, it can efficiently locate the position of blank pages, thus greatly reducing the workload of staff. Detailed Implementation

[0037] The present invention will be further described below. It should be noted that this embodiment is based on the present technical solution and provides detailed implementation methods and specific operation processes, but the protection scope of the present invention is not limited to this embodiment.

[0038] Example 1

[0039] This embodiment provides a single-page scanning blank page processing system based on a marking system, including:

[0040] Examination information module: This module stores information on students who should take the exam and information on students who are absent and uploaded in advance by various schools. The student information includes name and exam number, and may also include more detailed information such as school and grade.

[0041] Image acquisition module: Used to acquire images of students' completed test papers or answer sheets awaiting grading;

[0042] Blank page detection module: used to detect whether there are blank pages in the acquired roll image;

[0043] Recording module: When the blank page detection module detects a blank page, it records the relevant data of the blank page. The relevant data includes the ID of the blank page, and the candidate information of the preceding and following pages of the exam paper in the scanning order. The ID of each exam paper image is generated according to its scanning order (e.g., the ID of the exam paper image can be generated using a preset prefix and scanning order, such as image_00001, image_00002). If there is no corresponding candidate information before or after the blank page, the missing candidate information from the preceding or following page is recorded.

[0044] Verification module: Used to verify whether there is a possibility of an inverted page among the detected blank pages, wherein the inverted page is the image of the test paper or answer sheet obtained due to an error:

[0045] 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module;

[0046] 2) Count the total number of collected test paper images and the total number of detected blank pages;

[0047] 3) Calculate the difference between the total number of images on the exam paper and the total number of blank pages, and record it as the actual number of test takers; record the sum of the actual number of test takers and the number of absent test takers as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, then it is determined that there are no reversed pages among the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, then it is determined that there may be reversed pages among the detected blank pages.

[0048] In this embodiment, the image acquisition module is also used to preprocess the acquired roll image, and the preprocessing includes one or more of rectangular correction, inversion correction, and curved surface correction.

[0049] In this embodiment, the blank page detection module performs blank page detection in any of the following ways:

[0050] (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page.

[0051] (2) Detect whether the paper image has preset positioning points (such as multiple small black squares that are preset on the test paper or answer sheet). If no preset positioning points are detected, the paper image is determined to be a blank page.

[0052] (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram;

[0053] (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range (e.g., the preset answer area, which is represented by coordinate data) on the paper image with a preset pixel value threshold. If the average pixel value is less than the preset pixel value threshold, the paper image is determined to be a blank page.

[0054] Example 2

[0055] This embodiment provides a working method for the system described in Embodiment 1, the specific process of which is as follows:

[0056] The exam administration information module stores information on students who should take the exam and information on students who are absent, which has been uploaded in advance by each school.

[0057] After the exam, the image acquisition module is used to capture images of the students' completed exam papers or answer sheets that are awaiting grading;

[0058] After the data acquisition is completed, the blank page detection module checks whether there are blank pages in the acquired paper image;

[0059] When the blank page detection module detects a blank page, the recording module records the relevant data of the blank page;

[0060] Then, the verification module checks whether there is an inverted page among the detected blank pages according to the following process. The inverted page is the image of the test paper or answer sheet obtained due to an error:

[0061] 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module;

[0062] 2) Count the total number of collected test paper images and the total number of detected blank pages;

[0063] 3) Calculate the difference between the total number of images on the exam paper and the total number of blank pages, and record it as the actual number of test takers; record the sum of the actual number of test takers and the number of absent test takers as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, then it is determined that there are no reversed pages among the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, then it is determined that there may be reversed pages among the detected blank pages.

[0064] When the verification module detects the possibility of a reversed page among the blank pages, it prompts the staff. The staff then searches the test paper or answer sheet based on the blank page data recorded by the recording module to verify whether each blank page is indeed a reversed page.

[0065] Specifically, by combining the blank page ID with the candidate information corresponding to the two pages before and after the blank page, staff can accurately and efficiently locate the corresponding exam paper or answer sheet for the blank page.

[0066] Furthermore, after acquiring the paper image, the image acquisition module further preprocesses the acquired paper image, and the preprocessing includes one or more of rectangular correction, inversion correction, and curved surface correction.

[0067] Furthermore, the blank page detection module performs blank page detection in any of the following ways:

[0068] (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page.

[0069] (2) Detect whether the paper image has a preset positioning point. If no preset positioning point is detected, the paper image is determined to be a blank page.

[0070] (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram;

[0071] (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range on the paper image with a preset pixel value threshold, and if it is less than the preset pixel value threshold, then the paper image is determined to be a blank page.

[0072] For those skilled in the art, various corresponding changes and modifications can be made based on the above technical solutions and concepts, and all such changes and modifications should be included within the protection scope of the claims of this invention.

Claims

1. A single-page scanning blank page processing system based on a marking system, characterized in that, include: Examination information module: This module stores information on students who should take the exam, as well as information on absent students uploaded in advance by various schools. The student information includes their name and exam number. Image acquisition module: Used to acquire images of students' completed test papers or answer sheets awaiting grading; Blank page detection module: used to detect whether there are blank pages in the acquired roll image; Recording module: When the blank page detection module detects a blank page, it records the relevant data of the blank page. The relevant data includes the ID of the blank page, as well as the candidate information of the previous and next page images of the exam paper in the scanning order. The ID of each exam paper image is generated according to its scanning order. If there is no corresponding candidate information before or after the blank page, the missing candidate information of the previous or next page is recorded. Verification module: Used to verify whether there is a possibility of an inverted page among the detected blank pages, wherein the inverted page is the image of the test paper or answer sheet obtained due to an error: 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module; 2) Count the total number of collected test paper images and the total number of detected blank pages; 3) Calculate the difference between the total number of images on the paper and the total number of blank pages, and record it as the actual number of participants; The sum of the actual number of test takers and the number of absent test takers is recorded as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, it is determined that there are no reversed pages in the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, it is determined that there may be reversed pages in the detected blank pages.

2. The system according to claim 1, characterized in that, The image acquisition module is also used to preprocess the acquired roll image, and the preprocessing includes one or more of the following: rectangular correction, inversion correction, and curved surface correction.

3. The system according to claim 1, characterized in that, The blank page detection module is used to detect blank pages in any of the following ways: (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page. (2) Detect whether the paper image has a preset positioning point. If no preset positioning point is detected, the paper image is determined to be a blank page. (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram; (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range on the paper image with a preset pixel value threshold, and if it is less than the preset pixel value threshold, then determine that the paper image is a blank page.

4. A method of operating the system according to claims 1-3, characterized in that, The specific process is as follows: The exam administration information module stores information on students who should take the exam and information on students who are absent, which has been uploaded in advance by each school. After the exam, the image acquisition module is used to capture images of the students' completed exam papers or answer sheets that are awaiting grading; After the data acquisition is completed, the blank page detection module checks whether there are blank pages in the acquired paper image; When the blank page detection module detects a blank page, the recording module records the relevant data of the blank page; Then, the verification module checks whether there is an inverted page among the detected blank pages according to the following process. The inverted page is the image of the test paper or answer sheet obtained due to an error: 1) Obtain the number of candidates who should take the exam and the number of candidates who are absent from the exam from the exam administration information module; 2) Count the total number of collected test paper images and the total number of detected blank pages; 3) Calculate the difference between the total number of images on the paper and the total number of blank pages, and record it as the actual number of participants; The sum of the actual number of test takers and the number of absent test takers is recorded as the number of test takers; if the number of test takers is equal to the number of test takers who should have taken the exam, it is determined that there are no reversed pages in the detected blank pages; if the number of test takers is less than the number of test takers who should have taken the exam, it is determined that there may be reversed pages in the detected blank pages. When the verification module detects the possibility of a reversed page among the blank pages, it prompts the staff. The staff then searches the test paper or answer sheet based on the blank page data recorded by the recording module to verify whether each blank page is indeed a reversed page.

5. The method according to claim 4, characterized in that, After acquiring the paper image, the image acquisition module further preprocesses the acquired paper image. The preprocessing includes one or more of the following: rectangular correction, inversion correction, and curved surface correction.

6. The method according to claim 4, characterized in that, The blank page detection module detects blank pages using any of the following methods: (1) Perform OCR recognition on the paper image. If no valid text is extracted, the paper image is determined to be a blank page. (2) Detect whether the paper image has a preset positioning point. If no preset positioning point is detected, the paper image is determined to be a blank page. (3) Calculate the grayscale histogram of the paper image, and determine whether the paper image is a blank page based on the grayscale distribution of the grayscale histogram; (4) Obtain the pixels on the paper image, compare the average pixel value within a preset range on the paper image with a preset pixel value threshold, and if it is less than the preset pixel value threshold, then determine that the paper image is a blank page.