Method for identifying human faces in real time under multi-person dynamic environment

A face recognition and dynamic environment technology, applied in the field of electronic recognition, can solve the problem of obtaining part of the face, and achieve the effect of saving calculation amount, realizing high speed and high accuracy

Inactive Publication Date: 2011-11-23
周曦
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, there will often be many people entering the monitoring area at the same time, the flow of monitored people keeps moving and leaves the monitoring area in a short period of time, and the faces of the monitored people block each other and only part of the face can be obtained.

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
  • Method for identifying human faces in real time under multi-person dynamic environment
  • Method for identifying human faces in real time under multi-person dynamic environment
  • Method for identifying human faces in real time under multi-person dynamic environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with accompanying drawing.

[0026] Such as figure 1 , figure 2 and image 3 Shown, concrete steps of the present invention are: (1) image initialization; (2) face detection; (3) face feature extraction; (4) face information registration; (5) obtain video image sequence; (6) (7) face feature extraction; (8) face recognition; (9) obtain current face information sequence; (10) obtain video image sequence; (11) face detection; (12) people Face tracking; (13) obtain current face information sequence;

[0027] The specific steps of face detection are:

[0028] (1) Make a low-pass filter picture group: use 2x2, 3x3, 4x4 low-pass filter operators to low-pass filter the image to be detected, and obtain three filtered pictures, plus the original image, each picture to be detected Generate four pictures;

[0029] (2) Comparing feature point pairs: in the picture obtained through step (1), the gray value o...

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 method for identifying human faces in real time under multi-person dynamic environment, and belongs to the technical field of electronic identification. The method comprises the following steps of: (1) initializing an image; (2) detecting a human face; (3) extracting the facial feature of the human face; (4) registering human face information; (5) acquiring a video image sequence; (6) detecting the human face; (7) extracting the facial feature of the human face; (8) identifying the human face; (9) acquiring the current human face information sequence; (10) acquiring the video image sequence; (11) detecting the human face; (12) tracking the human face; and (13) acquiring the current human face information sequence. The method has the advantage that features required by the detection, tracking and identification of the human face are utilized repeatedly and are processed progressively, so that calculated amount is saved greatly and high speed and high accuracy are realized.

Description

technical field [0001] The invention relates to a face recognition method, in particular to a real-time face recognition method in a multi-person dynamic environment, and belongs to the technical field of electronic recognition. Background technique [0002] Facial recognition technology is often used in security and surveillance systems, for example to determine whether a person can be authorized or enter a particular system. At present, face recognition technology usually needs to provide a complete and clear face, and the recognition process takes a long time, so that a person needs to wait for a long time before the face recognition system obtains the recognition result. Such a facial recognition system can only be used when the user and the system fully cooperate. However, in the actual monitoring system, the user will not actively cooperate with the face recognition system. Therefore, it will often occur that many people enter the monitoring range at the same time, t...

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): G06K9/00G06K9/54
Inventor 周曦
Owner 周曦
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