Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Handwritten test question answer extraction method

An extraction method and handwriting technology, applied in the field of image processing, can solve problems such as high requirements for angle and flatness, insufficient accuracy, inconvenient use, etc., to achieve reduced angle and low flatness, safe and convenient use, and scientific and reasonable structure Effect

Pending Publication Date: 2020-09-15
武汉唯理科技有限公司
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for extracting answers from handwritten test questions, which can effectively solve the problems raised in the above background technology. The more, the online test question review function can effectively reduce the work of teachers, and put more energy on teaching work and research on students' knowledge mastery. The current online test question review function, which obtains the test questions uploaded by students and extracts the answers, is often accurate. The degree of accuracy is not enough, or the angle and flatness of the pictures uploaded by students are high, and it is inconvenient to use

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Handwritten test question answer extraction method
  • Handwritten test question answer extraction method
  • Handwritten test question answer extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Embodiment: The present invention provides technical scheme, a kind of method for extracting the answer of handwritten examination question, comprises the following steps:

[0038] S1. Use the sift method provided by OpenCV to perform feature extraction on the two images respectively;

[0039] S2. Use the KNN method to perform feature matching on the feature points of the two pictures and match the output feature points to the findhomography method of input OpenCV to calculate the homography matrix H, and then press the matrix H on the picture B to get the picture C;

[0040] S3. Input graph A and graph C into the SuperGLUE graph neural network model to obtain matching pairs of feature points;

[0041] S4. Use feature point matching to calculate the position of the marked frame in graph A;

[0042] S5. Extract the handwritten answer in Figure C.

[0043] According to the above technical solution, in the above step S1, the two pictures are respectively a prepared blank...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a handwriting test question answer extraction method which comprises the following steps: taking one picture as a source test question picture A, taking the other picture as ato-be-extracted answer picture B, photographing and uploading; the method further comprises the following steps of S1, performing corresponding preprocessing on the graph A and the graph B, such as size scaling, and extracting feature points; S2, subjecting feature points of the graph A and the graph B to initial matching through a rough matching method, calculating a homography matrix from the graph B to the graph A, correspondingly mapping the graph B into a graph C, wherein at the moment, the graph C and the graph A are consistent in size and close in angle. The method is scientific and reasonable in structure and safe and convenient to use, the online test question marking function is improved, the problem that the angle and flatness degree of pictures uploaded by students are low is solved, answers are convenient to extract, inconvenience brought by the extremely high precision requirement in the past is reduced, and the method is suitable for application and popularization.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for extracting answers to handwritten test questions. Background technique [0002] Examination is a strict method of knowledge level identification. Through the examination, students' learning ability and other abilities can be checked. In order to ensure the fairness and fairness of the results, the examination room must have strong discipline constraints, and there are special supervisors such as examiners and invigilators. During the examination process, any cheating is absolutely prohibited, otherwise you will bear legal and criminal responsibility. The examination is to let a group of people with different educational resources complete the same answer sheet within a certain period of time. However, the significance of the examination is not limited to this. The examination It can also be an all-round assessment of a person for a goal, so this kind of exam...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62G06K9/46G06N3/04
CPCG06V40/33G06V10/462G06N3/045G06F18/22
Inventor 王家奎王旺
Owner 武汉唯理科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products