Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Face detection and recognition method based on binocular vision

A face detection and recognition method technology, applied in the field of face detection and recognition based on binocular vision, can solve problems such as difficult face detection

Active Publication Date: 2020-11-03
HOHAI UNIV CHANGZHOU
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is used to solve the problem that the traditional monocular camera is difficult to detect faces in some special scenes

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
  • Face detection and recognition method based on binocular vision
  • Face detection and recognition method based on binocular vision
  • Face detection and recognition method based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0037] Such as figure 1 Shown, a kind of face detection recognition method of the present invention comprises the following steps:

[0038] (1) Obtain two face images through the binocular camera. When acquiring the image, the face should be facing the binocular camera as possible, so as to obtain a more reliable face image. The resolution of the camera should be no less than 5 million pixels, so as to obtain more accurate facial feature point positions. The distance between the face and the camera should ensure that the face occupies as much photo area as possible.

[0039] (2) After obtaining the left and right images, use the improved version of the P_Net network to calculate the input, such as figure 2 As shown, the input size is set to 1202×1202×3, the second layer network is set to 600×600×10, the pooling layer is a 2×2 matrix, the thi...

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 face detection and recognition method based on binocular vision. The method comprises the following steps: (1) acquiring left and right face pictures through a binocular camera; (2) detecting two pictures through hog features, and finding out two corresponding face pictures from the two pictures; (3) extracting human face features from the two acquired pictures containingthe human faces; (4) obtaining face feature point depth information through a binocular vision distance measurement method so as to calculate a face three-dimensional model; (5) analyzing a calculated result by using a statistical method to realize identification. Specifically, a support vector machine is used to classify a three-dimensional face model so as to realize face recognition. Face detection and three-dimensional reconstruction and recognition are achieved through the shooting, detection, modeling and classification technologies, and the method has the advantages of being efficientand rapid in processing, safe, reliable and capable of providing more complete and richer detection information.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to a face detection and recognition method based on binocular vision. Background technique [0002] Since 2001, the public security department has begun to use face detection technology to prevent and crack down on major criminal crimes and obtain the support of the state. In 2008, when the Beijing Olympic Games was held, the face detection technology was applied, which marked that the face detection in our country entered the practical stage. Since then, at the Shanghai World Expo, this technology has been more widely used, and at the same time, major companies have also joined in, which has accelerated the large-scale application of face detection technology in China. With the domestic technological progress in this field, "three modernizations and two integrations" will be an inevitable trend in the development of face detection technology. Among th...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/653G06V40/166G06V40/168G06N3/045G06F18/2411
Inventor 李磊宦蕴哲蒋晨阳王永春金玮李建业
Owner HOHAI UNIV CHANGZHOU
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com