CN110659584B - Intelligent mark-remaining paper marking system based on image recognition - Google Patents
Intelligent mark-remaining paper marking system based on image recognition Download PDFInfo
- Publication number
- CN110659584B CN110659584B CN201910815582.1A CN201910815582A CN110659584B CN 110659584 B CN110659584 B CN 110659584B CN 201910815582 A CN201910815582 A CN 201910815582A CN 110659584 B CN110659584 B CN 110659584B
- Authority
- CN
- China
- Prior art keywords
- image
- test paper
- test
- question
- area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides an intelligent mark-remaining paper marking system based on image recognition, which comprises: the customized answer sheet module is used for generating answer sheet information; the image processing module is used for scanning the two-dimensional code to obtain the test paper number, obtaining a corresponding coordinate information description table and test paper test question information according to the test paper number, and comparing the actual coordinate position of the marking point of the scanned image with the coordinate position of the marking point recorded in the positioning information table; the data processing module is used for acquiring the recognition result tables of all the reference students, further acquiring answer information of test questions, respectively calculating scores of objective questions and subjective questions, obtaining scores and ranks of single test paper of each student, and storing the scores and ranks in the calculation result tables. According to the invention, the knowledge mastering situation of students is quickly known through the report, the targeted explanation is convenient, the operation flow of paper reading is simplified, and the learning cost of teachers is greatly reduced.
Description
Technical Field
The invention relates to the technical field of computers and image recognition, in particular to an intelligent mark-remaining paper marking system based on image recognition.
Background
With the development of computer technology, the traditional manual examination paper marking mode of objective questions has been replaced by intelligent examination paper marking mode, thereby greatly improving the examination paper marking accuracy and examination paper marking efficiency.
However, in the existing automatic examination paper system, the reading of the study number and the identification of the objective questions are mostly completed by a computer, and then the teacher is required to intensively read the subjective questions, so that the teacher needs to be trained in advance, the consumption of manpower resources is relatively high, the manpower is wasted when dealing with the small examination of the examination type, and the collection of the wrong examination questions for each student and the strengthening exercise of similar questions cannot be provided. In the scene of rapid test, the traditional paper marking system needs to train teachers and intensively mark paper marking, which is inconvenient to use.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks.
Therefore, the invention aims to provide an intelligent mark-keeping scoring system based on image recognition.
In order to achieve the above object, an embodiment of the present invention provides an intelligent marking and scoring system based on image recognition, including: the system comprises a customized answer sheet module, an image processing module and a data processing module, wherein,
the customized answer sheet module is used for generating answer sheet information and comprises the following components: the test paper number, a two-dimensional code corresponding to the test paper number, a positioning mark, a scoring frame, an input label of examinee basic information and a total column, an objective question number and a filling area, and a positioning information table for describing the information of the whole answer sheet;
the image processing module is used for scanning the two-dimensional code to obtain the test paper number, obtaining a corresponding coordinate information description table and test paper test question information according to the test paper number, comparing the actual coordinate position of a mark point of a scanned image with the coordinate position of the mark point recorded in the positioning information table, calculating the scale between the test paper scanned image and the test paper layout generated by typesetting according to the actual coordinate position of the mark point of the scanned image, and carrying out conversion to correct the test paper scanned image to the size of the previous design; then cutting the image area corresponding to each test question according to the coordinate information table generated by the answer sheet customizing module, and dividing the image area into a privacy area, an objective question area, a subjective question area and a handwriting scoring frame area; for the objective question area, identifying the result filled by the student according to the number of options and the coordinate information, drawing the identification result on an identification result image, and storing the identification result in an identification result table; for the subjective question area, calling a recognition model trained previously to recognize the handwriting image of the teacher in the scoring frame, drawing the recognition result on the recognition result image, and storing the recognition result image in a recognition result table; the identification result image and the identification result table are sent to a data processing module for processing analysis;
the data processing module is used for acquiring the recognition result tables of all the reference students, further acquiring answer information of test questions, respectively calculating scores of objective questions and subjective questions, obtaining scores and ranks of single test paper of each student, and storing the scores and ranks in the calculation result tables.
Further, the customized answer sheet module is used for generating positioning marks positioned at least three corner blanks of the paper surface, and the positioning marks are used for confirming the scaling between the actual printed paper size and the original electronic paper size and correcting the deformation of the electronic paper image;
the positioning information table includes: positioning area, number area, coordinate information corresponding to each test question.
Further, the coordinate information description table includes: the method comprises the following steps of testing paper locating point coordinates, coordinates of each objective question, coordinates of each subjective question, subject area coordinates, privacy area coordinates which are required to be covered during paper reading and teacher scoring frame coordinates corresponding to each subjective question.
Further, the test paper test question information comprises the total score of each objective question, correct answers, the number of options, the total score of each subjective question and the total score of the whole test paper.
Further, the image processing module performs correction, including the steps of: firstly, acquiring coordinate information L1 of a positioning point from a coordinate information table, amplifying the area of the coordinate area by m times to obtain L2, then cutting the L2 area from an original image obtained by a scanner to obtain an image I1, searching positioning information of the positioning point in an actual image in the image I1 to obtain L3, obtaining actual coordinate information corresponding to one positioning point, repeating the process, finding the coordinate information corresponding to all positioning points in an answer sheet, and correcting the original image to the coordinates designated by an answer sheet design module through affine transformation.
Further, the image processing module performs handwriting image recognition, including the following steps: preprocessing a handwritten image, namely converting the image into a gray level image, binarizing the gray level image according to an Ojin method, denoising and enhancing the image, and finally converting the image into data acceptable by a recognition model.
Further, the recognition model can accept data including converting pixel data in the image into a set of numbers of length to the image area, each number representing a gray level of a designated area of the image.
Further, the data processing module is further used for obtaining questions that each student does not obtain full score from the calculation result, grading answer images of the students and teachers, collecting the read-by-click images, storing the results into a student wrong question table, and then calculating the difficulty, the distinguishing degree and the answering rate of each test paper according to the single test paper scoring condition of all the students.
Further, the data processing module is further used for calculating a test paper difficulty coefficient:
for objective questions, difficulty p=k/N, where k is the number of people answering the question and N is the total number of people taking part in the test;
for subjective questions, difficulty p=x/M, where X is the average score of the questions; m is the full score of the test question.
Further, the data processing module is further used for generating a reinforced exercise test paper for each student according to the wrong test question condition of each student, wherein the difficulty and knowledge point coverage of all the test questions of the test paper are consistent with the wrong test questions of the student.
According to the intelligent mark-remaining paper marking system based on image recognition, through the pre-arrangement of the scoring frame on the answer sheet, a teacher can write scores on the answer sheet, and finally, the information such as scores, ranks and the like of all students participating in the examination can be directly obtained through system scanning, so that the operation flow of the teacher is simplified, the students can know about own wrong questions, and then, strengthening exercise is carried out through exercise of similar questions, so that the aim of really grasping knowledge is achieved. Aiming at the scene of rapid test, the traditional examination system needs to train teachers, intensively examine the examination papers and is inconvenient to use, and the teacher can directly score and mark subjective questions on the answer sheet by presetting a scoring frame on the answer sheet, and then automatically identify objective questions, subjective question scores and finally rapidly obtain the information of scores, ranks and the like of students. The teacher can quickly know the knowledge mastered situation of the students through the report, the teaching can be conveniently and specifically conducted, the operation flow of paper reading is simplified, and the learning cost of the teacher is greatly reduced.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a block diagram of an intelligent mark-keeping scoring system based on image recognition according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an intelligent mark-keeping scoring system based on image recognition according to an embodiment of the invention;
fig. 3 is a schematic diagram of a table of recognition results of subjective questions according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
As shown in fig. 1 and fig. 2, an intelligent mark-remaining paper marking system based on image recognition according to an embodiment of the present invention includes: the system comprises a customized answer sheet module 100, an image processing module 200 and a data processing module 300.
Specifically, the customized answer sheet module 100 is configured to generate answer sheet information, including: the test paper number, a two-dimensional code corresponding to the test paper number, a positioning mark, a scoring frame, an input label of examinee basic information and a total column, an objective question number and a filling area, and a positioning information table for describing the information of the whole answer sheet. Wherein the positioning information table includes: positioning area, number area, coordinate information corresponding to each test question.
In the embodiment of the present invention, the customized answer sheet module 100 is used for generating a test paper number and a two-dimensional code corresponding to the test paper number, and placing the two-dimensional code on a fixed corner position of the answer sheet, where the test paper number has uniqueness. The customized answer sheet module 100 generates positioning marks located at least three corner blanks of the paper surface, where the positioning marks are used for confirming the scaling between the actual printed paper size and the original electronic paper size and correcting the deformation of the electronic paper image.
In addition, the customized answer sheet module 100 generates the basic information of the examinee and the input label of the total column, and places the basic information and the input label at the test paper title column; the examinee basic information comprises names, classes, grades, numbers and the like. For subjective questions, a handwriting score scoring box is added at the appropriate location of the question (e.g., at the end of the question).
The image processing module 200 is used for scanning the two-dimensional code to obtain the test paper number. Specifically, the two-dimensional code and the test paper locating point of the identified test paper are found at four corners of the test paper scanning image, and the two-dimensional code is converted into the test paper number. And then the image processing module 200 acquires the corresponding coordinate information description table and the test paper test question information according to the test paper number. Wherein the coordinate information description table includes: the method comprises the following steps of testing paper locating point coordinates, coordinates of each objective question, coordinates of each subjective question, subject area coordinates, privacy area coordinates which are required to be covered during paper reading and teacher scoring frame coordinates corresponding to each subjective question.
The test paper test question information comprises the total score of each objective question, correct answers, the number of options, the total score of each subjective question and the total score of the whole test paper.
The image processing module 200 compares the actual coordinate position of the marking point of the scanned image with the coordinate position of the marking point recorded in the positioning information table, calculates the scale between the scanned image of the test paper and the layout of the test paper generated by typesetting according to the calculated scale, and transforms the test paper to the size of the previous design.
Specifically, the image processing module 200 performs correction, including the following steps: firstly, acquiring coordinate information L1 of a positioning point from a coordinate information table, amplifying the area of the coordinate area by m times to obtain L2, and then cutting the L2 area from an original image obtained by a scanner to obtain an image I1. For example, m=4, where the magnification m may be set according to user needs, which is for exemplary purposes only.
The image processing module 200 searches the positioning information of the positioning point in the actual image in the image I1 to obtain L3, obtains actual coordinate information corresponding to one positioning point, repeats the process, finds the coordinate information corresponding to all positioning points in the answer sheet, and corrects the original image to the coordinate designated by the answer sheet design module through affine transformation.
And then cutting the image area corresponding to each test question according to the coordinate information table generated by the answer sheet customizing module, and dividing the image area into a privacy area, an objective question area, a subjective question area and a handwriting scoring frame area.
And for the objective question area, identifying the result filled by the student according to the number of options and the coordinate information, drawing the identification result on an identification result image, and storing the identification result in an identification result table. The training model is to prepare a handwritten material image, and train the handwritten material by using caffe to obtain an identification model.
For subjective questions, invoking a recognition model trained previously to recognize the handwriting numbers of the teacher in the scoring frame, drawing the recognition result on a recognition result image, and storing the recognition result in a recognition result table, as shown in fig. 3.
The image processing module 200 performs handwriting image recognition, including the steps of: preprocessing a handwritten image, namely converting the image into a gray level image, binarizing the gray level image according to an Ojin method, denoising and enhancing the image, and finally converting the image into a group of data acceptable by a recognition model.
In an embodiment of the invention, identifying data acceptable to the model includes converting pixel data in the image to a set of numbers of length to the image area, each number representing a gray level of a designated area of the image, facilitating matching in the identification model, finding the nearest number.
For the subjective question area, calling a recognition model trained previously to recognize the handwriting image of the teacher in the scoring frame, drawing the recognition result on the recognition result image, and storing the recognition result image in a recognition result table; the recognition result image and the recognition result table are transmitted to the data processing module 300 for processing analysis.
The data processing module 300 is configured to obtain the recognition result tables of all the reference students, further obtain the test paper numbers from the recognition result tables, obtain answer information of the test questions according to the test paper numbers, calculate scores of objective questions and subjective questions respectively, obtain scores and ranks of individual test papers of each student, and store the scores and ranks in the calculation result tables.
Specifically, for objective questions, answer information of the questions is compared with actual filling answers in a student identification result table, and the students are scored according to a set scoring strategy. And for subjective questions, taking out the hand-reading score of the student for the test question from the student identification result table as the score of the test question for the student.
And summarizing the scores of all the test questions of each student, and calculating the score condition of a single test paper of each student. And calculating the total score of the students according to the score condition of each test paper of the students, and ranking information in the class, the grade and the ranking condition of the student single department in the class grade, and storing the calculation result into a calculation result table.
In addition, the data processing module 300 is further configured to obtain the questions that each student does not obtain full score from the calculation result, collect answer images of the students and scores of teachers, read the answer images, store the results in the student wrong question table, and calculate the difficulty, the degree of distinction and the answering rate of each test question of each test paper according to the single test paper score of all students.
The data processing module 300 is further configured to calculate a test paper difficulty coefficient:
for objective questions, difficulty p=k/N, where k is the number of people answering the question and N is the total number of people taking part in the test;
for subjective questions, difficulty p=x/M, where X is the average score of the questions; m is the full score of the test question.
According to the test paper distinguishing coefficient calculating method, reference students are ranked according to test paper scores, students with the first 27% of ranks are used as high grouping calculation difficulty coefficients to be PH, students with the last 27% of ranks are used as low grouping calculation difficulty coefficients to be PL, and then the distinguishing degree D=PH-PL of the test paper.
The question answering rate calculating method is that answering rate P=answer to test question number/total number.
The data processing module 300 then further derives a data analysis report from the above data.
In addition, the invention can provide an account for students, check test questions which are answered by previous exams after logging in, and print the test questions for retesting.
The data processing module 300 is further configured to generate an intensive exercise test paper for each student according to the wrong test question condition of each student, where the difficulty and knowledge point coverage of all the test questions of the test paper are consistent with the wrong test questions of the student, so as to achieve the purpose of intensive exercise.
According to the intelligent mark-remaining paper marking system based on image recognition, through the pre-arrangement of the scoring frame on the answer sheet, a teacher can write scores on the answer sheet, and finally, the information such as scores, ranks and the like of all students participating in the examination can be directly obtained through system scanning, so that the operation flow of the teacher is simplified, the students can know about own wrong questions, and then, strengthening exercise is carried out through exercise of similar questions, so that the aim of really grasping knowledge is achieved. Aiming at the scene of rapid test, the traditional examination system needs to train teachers, intensively examine the examination papers and is inconvenient to use, and the teacher can directly score and mark subjective questions on the answer sheet by presetting a scoring frame on the answer sheet, and then automatically identify objective questions, subjective question scores and finally rapidly obtain the information of scores, ranks and the like of students. The teacher can quickly know the knowledge mastered situation of the students through the report, the teaching can be conveniently and specifically conducted, the operation flow of paper reading is simplified, and the learning cost of the teacher is greatly reduced.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations may be made in the above embodiments by those skilled in the art without departing from the spirit and principles of the invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. An intelligent mark-keeping scoring system based on image recognition, which is characterized by comprising: the system comprises a customized answer sheet module, an image processing module and a data processing module, wherein,
the customized answer sheet module is used for generating answer sheet information and comprises the following components: the test paper number, a two-dimensional code corresponding to the test paper number, a positioning mark, a scoring frame, an input label of examinee basic information and a total column, an objective question number and a filling area, and a positioning information table for describing the information of the whole answer sheet; the customized answer sheet module is used for generating a test paper number and a two-dimensional code corresponding to the test paper number, and placing the two-dimensional code on a fixed corner position of the answer sheet, wherein the test paper number has uniqueness;
the image processing module is used for scanning the two-dimensional code to obtain the test paper number, obtaining a corresponding coordinate information description table and test paper test question information according to the test paper number, comparing the actual coordinate position of a mark point of a scanned image with the coordinate position of the mark point recorded in the positioning information table, calculating the scale between the test paper scanned image and the test paper layout generated by typesetting according to the actual coordinate position of the mark point of the scanned image, and carrying out conversion to correct the test paper scanned image to the size of the previous design; then cutting the image area corresponding to each test question according to the coordinate information table generated by the answer sheet customizing module, and dividing the image area into a privacy area, an objective question area, a subjective question area and a handwriting scoring frame area; for the objective question area, identifying the result filled by the student according to the number of options and the coordinate information, drawing the identification result on an identification result image, and storing the identification result in an identification result table; for the subjective question area, calling a recognition model trained previously to recognize the handwriting image of the teacher in the scoring frame, drawing the recognition result on the recognition result image, and storing the recognition result image in a recognition result table; the identification result image and the identification result table are sent to a data processing module for processing analysis; the image processing module corrects the image, and the method comprises the following steps: firstly, acquiring coordinate information L1 of a positioning point from a coordinate information table, amplifying the area of the coordinate area by m times to obtain L2, then cutting the L2 area from an original image obtained by a scanner to obtain an image I1, searching positioning information of the positioning point in an actual image in the image I1 to obtain L3, obtaining actual coordinate information corresponding to one positioning point, repeating the process, finding coordinate information corresponding to all positioning points in an answer sheet, and correcting the original image to coordinates designated by an answer sheet design module through affine transformation; the image processing module performs handwriting image recognition and comprises the following steps: preprocessing a handwritten image, namely converting the image into a gray level image, binarizing the gray level image according to an Ojin method, denoising and enhancing the image, and finally converting the image into data acceptable by an identification model;
the data processing module is used for acquiring the recognition result tables of all reference students, further acquiring answer information of test questions, respectively calculating scores of objective questions and subjective questions, obtaining scores and ranks of single test papers of each student, and storing the scores and ranks in the calculation result tables; the data processing module is also used for acquiring questions which are not fully scored by each student from the calculation result, scoring answer images of the students and teachers, collecting the click-through images, storing the results into a student wrong question table, and then calculating the difficulty, the distinguishing degree and the answering rate of each test paper according to the single test paper scoring condition of all students;
the customized answer sheet module is used for generating positioning marks positioned at the blank positions of at least three corners of the paper surface, and the positioning marks are used for confirming the scaling between the actual printed test paper size and the original electronic test paper size and correcting the deformation of the electronic test paper image;
the positioning information table includes: the positioning area, the number area and the coordinate information corresponding to each test question;
the coordinate information description table includes: the method comprises the following steps of (1) detecting point coordinates of a test paper, coordinates of each objective question, coordinates of each subjective question, subject area coordinates, privacy area coordinates which are required to be covered when the test paper is read, and teacher scoring frame coordinates corresponding to each subjective question;
the test paper test question information comprises the total score of each objective question, correct answers, the number of options, the total score of each subjective question and the total score of the whole test paper;
the data acceptable by the recognition model comprises that pixel data in an image is converted into a group of numbers with the length of the image area, and each number represents the gray level of a designated area of the image;
the data processing module is also used for calculating the test paper difficulty coefficient:
for objective questions, difficulty p=k/N, where k is the number of people answering the question and N is the total number of people taking part in the test; for subjective questions, difficulty p=x/M, where X is the average score of the questions; m is the full score of the test question;
the data processing module is also used for generating an intensive exercise test paper for each student according to the wrong test question condition of each student, wherein the difficulty and knowledge point coverage of all the test questions of the test paper are consistent with the wrong test questions of the student.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815582.1A CN110659584B (en) | 2019-08-30 | 2019-08-30 | Intelligent mark-remaining paper marking system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910815582.1A CN110659584B (en) | 2019-08-30 | 2019-08-30 | Intelligent mark-remaining paper marking system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110659584A CN110659584A (en) | 2020-01-07 |
| CN110659584B true CN110659584B (en) | 2023-12-26 |
Family
ID=69037957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910815582.1A Active CN110659584B (en) | 2019-08-30 | 2019-08-30 | Intelligent mark-remaining paper marking system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110659584B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666864B (en) * | 2020-06-01 | 2023-03-24 | 合肥工业大学 | Automatic paper marking method based on computer vision |
| CN112163529A (en) * | 2020-09-30 | 2021-01-01 | 珠海读书郎网络教育有限公司 | System and method for uniformly dividing test paper |
| CN112200058B (en) * | 2020-09-30 | 2021-07-06 | 珠海读书郎网络教育有限公司 | System and method for intelligently correcting auxiliary data |
| CN112287154A (en) * | 2020-10-30 | 2021-01-29 | 北京有竹居网络技术有限公司 | Information statistics method, device, computer equipment and storage medium |
| CN113065477B (en) * | 2021-04-08 | 2023-04-18 | 读书郎教育科技有限公司 | Intelligent classroom textbook content identification method |
| CN113033480B (en) * | 2021-04-20 | 2024-11-05 | 深圳市智像科技有限公司 | Objective question marking method, device, equipment and storage medium based on answer sheet |
| CN113408520B (en) * | 2021-07-16 | 2023-12-12 | 北京南昊科技股份有限公司 | Marking method, marking device and storage medium |
| CN114049805A (en) * | 2021-10-29 | 2022-02-15 | 珠海读书郎软件科技有限公司 | Intelligent classroom correction and data acquisition method based on ink screen |
| CN114639110A (en) * | 2022-02-17 | 2022-06-17 | 武汉全品教育科技有限公司 | Intelligent reading method and system |
| CN117037187A (en) * | 2023-10-10 | 2023-11-10 | 广东省科技基础条件平台中心 | Test paper image extraction method and device and terminal equipment |
| CN117372214A (en) * | 2023-10-13 | 2024-01-09 | 可之(宁波)人工智能科技有限公司 | Method for correcting trace on job based on coordinate information |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871274A (en) * | 2012-12-07 | 2014-06-18 | 大连联达科技有限公司 | On-site teaching system |
| CN104809677A (en) * | 2015-05-13 | 2015-07-29 | 江苏黄金屋教育咨询有限公司 | Automatic examination paper scoring method based on statistics and analysis of knowledge point mastering condition |
| WO2016030900A2 (en) * | 2014-08-27 | 2016-03-03 | Eyessessment Technologies Ltd. | Evaluating test taking |
| CN107622463A (en) * | 2017-09-27 | 2018-01-23 | 张鹏 | One kind makes the test and automatic marking papers system and method |
| CN108229361A (en) * | 2017-12-27 | 2018-06-29 | 北京摩数教育科技有限公司 | A kind of electronic paper marking method |
| CN108805760A (en) * | 2017-05-06 | 2018-11-13 | 南京多邦软件有限公司 | A kind of intelligently reading system |
| CN110008933A (en) * | 2019-04-18 | 2019-07-12 | 江苏曲速教育科技有限公司 | A general intelligent scoring system and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120189999A1 (en) * | 2011-01-24 | 2012-07-26 | Xerox Corporation | System and method for using optical character recognition to evaluate student worksheets |
| US9805615B2 (en) * | 2014-12-18 | 2017-10-31 | Christopher P. Foley, JR. | Systems and methods for testing, evaluating and providing feedback to students |
| CN106780205A (en) * | 2016-11-22 | 2017-05-31 | 江苏黄金屋教育发展股份有限公司 | A kind of big data collection and analysis method read and made comments that be applied to take an examination |
| CN106781784A (en) * | 2017-01-04 | 2017-05-31 | 王骁乾 | A kind of intelligence correction system |
| CN108573461A (en) * | 2018-04-23 | 2018-09-25 | 温州市鹿城区中津先进科技研究院 | A kind of cloud is goed over examination papers data analysis system |
-
2019
- 2019-08-30 CN CN201910815582.1A patent/CN110659584B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871274A (en) * | 2012-12-07 | 2014-06-18 | 大连联达科技有限公司 | On-site teaching system |
| WO2016030900A2 (en) * | 2014-08-27 | 2016-03-03 | Eyessessment Technologies Ltd. | Evaluating test taking |
| CN104809677A (en) * | 2015-05-13 | 2015-07-29 | 江苏黄金屋教育咨询有限公司 | Automatic examination paper scoring method based on statistics and analysis of knowledge point mastering condition |
| CN108805760A (en) * | 2017-05-06 | 2018-11-13 | 南京多邦软件有限公司 | A kind of intelligently reading system |
| CN107622463A (en) * | 2017-09-27 | 2018-01-23 | 张鹏 | One kind makes the test and automatic marking papers system and method |
| CN108229361A (en) * | 2017-12-27 | 2018-06-29 | 北京摩数教育科技有限公司 | A kind of electronic paper marking method |
| CN110008933A (en) * | 2019-04-18 | 2019-07-12 | 江苏曲速教育科技有限公司 | A general intelligent scoring system and method |
Non-Patent Citations (1)
| Title |
|---|
| 在线测试分析与数据挖掘系统的设计;余胜泉, 李世亮, 谢晓林;开放教育研究(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110659584A (en) | 2020-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110659584B (en) | Intelligent mark-remaining paper marking system based on image recognition | |
| CN110008933B (en) | Universal intelligent marking system and method | |
| CN108388895B (en) | Machine learning-based automatic processing method for test paper answer sheet | |
| CN109033046A (en) | Structuring visible document snap information input system and method | |
| CN107622463A (en) | One kind makes the test and automatic marking papers system and method | |
| CN101901338A (en) | Method and system for calculating scores of test paper | |
| CN110597806A (en) | A system and method for wrong question set generation and answer statistics based on review recognition | |
| US8768241B2 (en) | System and method for representing digital assessments | |
| CN107784264A (en) | Test paper analysis method and system based on image procossing | |
| CN111144251A (en) | Automatic scanning identification system based on image acquisition | |
| CN109242856A (en) | A kind of papery operation electronization reads and makes comments method and device | |
| CN107067399A (en) | A kind of paper image segmentation processing method | |
| CN108428073A (en) | A kind of intelligent evaluation system for teachers ' teaching quality | |
| CN116824607A (en) | High-precision answer sheet identification method | |
| CN116486411A (en) | Method for collecting handwriting answer area in test paper | |
| JP2008020506A (en) | Image processor and image processing program | |
| CN111008594A (en) | Error correction evaluation method, related equipment and readable storage medium | |
| CN107066939A (en) | A kind of paper cutting process method of online paper-marking system | |
| CN113903039A (en) | Color-based answer area acquisition method for answer sheet | |
| CN108681713A (en) | A kind of system for teaching quality evaluation for teachers | |
| US9195875B1 (en) | Method and apparatus for defining fields in standardized test imaging | |
| CN115482535A (en) | A test paper automatic correction method, storage medium and equipment | |
| CN114708606A (en) | A kind of intelligent automatic scoring service method, system and device | |
| CN113065477B (en) | Intelligent classroom textbook content identification method | |
| CN115936937A (en) | Method, device and system for job processing based on smart answer sheet |
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 |