An Adaptive Answer Sheet Sequence Correction Method

An answer sheet, self-adaptive technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as low efficiency of manual matching and inability to guarantee accuracy

Active Publication Date: 2021-09-07
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of one or more embodiments of this specification is to propose an adaptive answer sheet sequence correction method, which can realize automatic matching of answer sheets, so as to solve the problem of low efficiency and inability to guarantee accuracy of manual matching

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
  • An Adaptive Answer Sheet Sequence Correction Method
  • An Adaptive Answer Sheet Sequence Correction Method
  • An Adaptive Answer Sheet Sequence Correction Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0172] The sequence of student answer sheets (A1, A2, A3, A4,...A32), (B1, B2, B3, B4,,,,,,,B32) obtained by scanning, the sequence of each processing in this embodiment The number is 32, where A represents the data on the A side of the answer sheet, B represents the data on the B side of the answer sheet, and there is a mismatch between the A and B sides in the original sequence.

[0173] Input the first pair of AB images A1 and B1 of the original answer sheet sequence into the yolov3-based model respectively, and obtain several image blocks (x1, y1, z1,.... ) and (x2,y2,z2,...). The corresponding image blocks form a data pair (x1, x2)(y1, y2)....... For each pair of data pairs (x1, x2), input it into the Siamese-based handwriting matching model In the feature extraction network Gw(), the corresponding low-dimensional feature vectors Gw(x1) and Gw(x2) are extracted, and then the Euclidean distance E between the two low-dimensional feature vectors is calculated according to t...

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

One or more embodiments of this specification provide a method for correcting an adaptive answer sheet sequence, including: acquiring the A-side scan image, the B-side scan image, and the original image sequence of the student's answer sheet; Segment the scanned image respectively to obtain the A-side image block and the B-side image block containing the student's handwriting; input the A-side image block and the B-side image block into the pre-trained handwriting matching model to obtain the original image sequence The matching result of the adjacent A-side scan image and B-side scan image; the A-side scan image and B-side scan image that are not successfully matched in the matching results are input into the pre-trained handwriting search model, for each A-side The scanned image searches for the matching B-side scanned image, so as to realize the automatic correction of the answer sheet sequence.

Description

technical field [0001] The invention relates to the technical field of intelligent marking, in particular to an adaptive answer sheet sequence correction method. Background technique [0002] After the current intelligent marking system collects the student's answer sheets, it scans the front and back of the answer sheets through a scanner and stores them, and then sends them to the follow-up system for automatic correction. However, in the process of scanning by the scanner, there will be a phenomenon that the front and back do not match. Specifically, in the answer sheet sequence obtained after the scanner scans, there are cases where side A and side B are not from the same student. The other side of the corresponding match can only be found in the scan results of . [0003] This scanning sequence error is due to the interleaving of the timing between the image storage process and the scanning process when the scanner encounters a large number of scanning tasks, which eve...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/00G06K9/20G06K9/34G06N3/04G06N3/08
CPCG06N3/084G06V40/30G06V10/22G06V10/26G06N3/045G06F18/22G06F18/213G06F18/214
Inventor 傅慧源马华东田杨峰
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap