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

Non-cooperative examination personnel management method and system based on deep learning

A personnel management and deep learning technology, applied in the field of deep learning, can solve problems such as low efficiency, difficulty in detecting and preventing cheating on behalf of exams in time, time-consuming and labor-intensive, etc.

Pending Publication Date: 2019-12-06
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods are not only time-consuming, laborious and inefficient, but also often difficult to detect and prevent cheating in the exam

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
  • Non-cooperative examination personnel management method and system based on deep learning
  • Non-cooperative examination personnel management method and system based on deep learning
  • Non-cooperative examination personnel management method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

example

[0058] Referring to the article "S3FD:Single Shot Scale-invariant FaceDetector" included in the 2017 ICCV conference, its deep face detection neural network S3FD uses part of the VGG16 model: from conv1 to pool5, and removes other layers, through the VGG16 Upsample the parameters of fc6 and fc7, convert them to convolutional layers, and then add additional convolutional layers after them. These layers are gradually reduced in size to form multi-scale feature maps. Select conv3_3, conv4_3, conv5_3, conv_fc7, conv6_2and conv7_2 as the detection layer, and then use L2 normalization to scale the following three layers with different feature scales: the norms of conv3_3, conv4_3 and conv5_3 are scaled to 10, 8 and 5, respectively.

[0059] At the same time, in order to solve the serious imbalance of positive and negative samples for small faces, a max-out strategy is used: the layer that generates the most small targets—the output channel number of the conv3_3 layer is changed to (...

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 non-cooperative examination personnel management method and system based on deep learning. Based on a deep learning technology, by means of a modern computer and network technology, the non-cooperative examination personnel management method takes face detection and identification as means, abandons a backward mode of manual inspection and registration in traditional examination personnel management, realizes non-cooperative face detection and identification in an examination room, so as to realize identity authentication of examination personnel. And meanwhile, the non-cooperative examination personnel management method builds an information management platform to realize analysis and management of examinee information and data. The non-cooperative examination personnel management system comprises a video image acquisition module, a processing module and a data analysis and management module, wherein the processing module comprises a face detection link and aface recognition link based on a deep convolutional neural network, receives images transmitted by the video image acquisition module, and transmits results to the data analysis and management modulefor subsequent application operation after a series of processing. According to the non-cooperative examination personnel management method and system, improvement and optimization of an existing examination personnel management mode are facilitated, and the non-cooperative examination personnel management method and system are simpler and more efficient.

Description

technical field [0001] The invention relates to the technical field of deep learning and the technical field of face detection and recognition, in particular to a method and system for managing non-cooperative test personnel based on deep learning. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. . [0003] Face recognition technology has become an indispensable part of daily life, such as identity verification of security systems, public security criminal investigation, security verification, intelligent video surveillance, intelligent human-computer interaction and other aspects have a...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06Q50/20
CPCG06Q50/205G06V40/161G06V40/172G06V10/751G06F18/214
Inventor 王麒景康文雄
Owner SOUTH CHINA UNIV OF TECH
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