Peeping cheating behavior identification method based on attention area

A recognition method and attention technology, applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as insufficient recognition

Active Publication Date: 2020-03-10
西安云海信息技术有限责任公司
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But for cheating with smaller body movements, that is, keeping the corresponding face still within the shooting area of ​​the camera, but actually corresponding to the candidate’s head who is viewing the materials brought in or the screen of the adjacent candidate, it is better than normal answering. The identification of voyeuristic cheating behaviors that only change at a certain angle is still insufficient

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
  • Peeping cheating behavior identification method based on attention area
  • Peeping cheating behavior identification method based on attention area
  • Peeping cheating behavior identification method based on attention area

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0097] A peeping class cheating behavior recognition method based on attention area, the steps are as follows:

[0098] (1) Before the test, measure the standard angle range of the candidate's head angle relative to the camera when watching the screen;

[0099] (2) During the test, the candidate’s face image is captured by the camera every 100 ms, and the attention area is formed by its head rotation angle α, horizontal inclination angle β, and vertical inclination angle γ relative to the camera, and it is determined whether the attention area is within the standard within the angle range;

[0100] (3) Taking 1s as the statistical period, if at least one of the corresponding 10 judgments has its attention area within the standard angle interval, it is considered that the attention is concentrated, otherwise the attention is not concentrated; with 3 minutes as the statistical period, if the If the time of inattention exceeds 60s, it is considered that it is suspected of cheati...

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 relates to a peeping cheating behavior identification method based on an attention area and discloses a peeping cheating behavior identification method based on an attention area. The method comprises the following steps: measuring a standard angle interval of a head angle of an examinee relative to a camera when the examinee watches a screen; during an examination, acquiring a faceimage of an examinee every 100ms through a camera, and judging whether the attention area is in a standard angle interval or not; (3) taking 1s as a statistical period, if the attention area of at least one of the corresponding ten times of judgment is within a standard angle interval, considering that the attention is concentrated, otherwise, considering that the attention is not concentrated; taking 3 min as a statistical period, if the time of inattention exceeds 60 s, considering that cheating suspicion exists, and displaying a warning message on a screen of the mobile terminal; if the warning message shows that no 1s in 10s is attention concentration, judging that cheating occurs. According to the invention, the position of the facial organ in the video image is identified, and then the position of the examinee attention concentration area is calculated.

Description

technical field [0001] The invention relates to the field of identification of cheating behaviors in a paperless examination system, in particular to a method for identifying cheating behaviors of peeping based on attention regions. Background technique [0002] At present, scholars at home and abroad have provided various solutions to cheating in exams. It can be roughly divided into two categories: traditional information verification and electronic auxiliary verification. The traditional information verification category is dedicated to improving and improving the traditional methods of identifying cheating in exams, such as planning more effective patrols for invigilators or enabling candidates to provide more difficult-to-fake information for identity verification. The electronic assisted verification category is dedicated to using electronic automation technology to supervise and identify cheating behaviors of candidates in addition to the traditional examination info...

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): G06K9/00G06T7/73
CPCG06T7/73G06T2207/30201G06T2207/30232G06V40/16Y02D10/00
Inventor 伍懿
Owner 西安云海信息技术有限责任公司
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