Unlock instant, AI-driven research and patent intelligence for your innovation.

Video stream based face recognition method and system

A face recognition system and face recognition technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problem that the face detection effect is not ideal, and the face recognition comparison efficiency cannot meet the face recognition requirements and other problems, to achieve the effect of fast and effective face detection and face recognition

Inactive Publication Date: 2018-11-27
GUANGZHOU HONGSEN TECH
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of the face recognition application environment and the variability of the face itself, the traditional face recognition technology cannot get rid of the problem of recognition deception based on static images, the actual face detection effect is not ideal, and the face The comparison efficiency of recognition cannot meet the face recognition requirements of the current complex crowd flow environment

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
  • Video stream based face recognition method and system
  • Video stream based face recognition method and system
  • Video stream based face recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0047] see figure 1 , figure 1 It is a schematic flowchart of a face recognition method based on video stream provided by the first embodiment of the present invention.

[0048] Described face recognition method based on video flow, comprises the steps:

[0049] S101. Collect the video stream to be identified;

[0050] S102. Use a template matching algorithm to perform face detection on each frame of the image in the video stream to be recognized, so as to filter out a face image to be recognized that contains at least one face, and extract a corresponding image from the face image to be recognized. key facial feature data;

[0051] S103. Perform similarity calculation according to the key face feature data and the reference feature data corresponding to each face model in the pre-built face image database to obtain a similarity result, and perform weighting processing on the similarity result to obtain Obtain the face recognition result corresponding to the maximum weight...

no. 2 example

[0071] see Figure 4 , Figure 4 It is a schematic structural diagram of a face recognition system based on video stream provided by the second embodiment of the present invention.

[0072] The face recognition system based on the video stream includes a video acquisition device, a face feature extraction server, a face feature comparison server, a platform server and a client;

[0073] The video collection device is used to collect video streams to be identified, and transmit the video streams to be identified to the facial feature extraction server;

[0074] The face feature extraction server is configured to use a template matching algorithm to perform face detection on each frame of image in the video stream to be recognized, so as to filter out a face image to be recognized that contains at least one face, and from the Extracting corresponding facial feature data from the face image to be recognized, so as to transmit the facial feature data to the facial feature compar...

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 video stream based face recognition method and system. The method comprises: acquiring a video stream to be recognized; performing face detection on each frame image of the video stream to be recognized by using a template matching algorithm to screen out a face image to be recognized that includes at least one face, and extracting corresponding key face feature data fromthe face image to be recognized; performing similarity calculation according to the key face feature data and reference feature data corresponding to each face model in a pre-established face image database, obtaining a similarity result, and weighting the similarity result to obtain a face recognition result corresponding to the maximum weighting value; writing the face recognition result into anewly built database, and sending the face recognition result to a client so as to allow the client to display the face recognition result. The video stream based face recognition method and system can perform fast and effective face detection and face recognition on dynamic image in a video stream.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a video stream-based face recognition method and system. Background technique [0002] In the field of computer vision, face recognition has always been a research hotspot, whether it is security defense, identity verification, passport recognition and driver's license, or automatic door guard system, bank and customs monitoring system, etc., it has important Applications. However, due to the complexity of the face recognition application environment and the variability of the face itself, the traditional face recognition technology cannot get rid of the problem of recognition deception based on static images, the actual face detection effect is not ideal, and the face The comparison efficiency of recognition cannot meet the face recognition requirements of the current complex crowd flow environment. Contents of the invention [0003] The technical problem to...

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): G06K9/00G06K9/62
CPCG06V40/161G06V40/171G06V40/172G06F18/22
Inventor 钱广遴邓毅邓先海
Owner GUANGZHOU HONGSEN TECH