Multi-neural network cascaded face recognition method based on human face key points

A face key point, face recognition technology, applied in the field of face recognition, can solve the problems of inability to train face data sets, long calculation time, limited application of traditional methods, etc., to reduce the probability of falling into a local optimal solution , reduce the training time and improve the detection effect

Inactive Publication Date: 2018-04-27
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF1 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the light is too bright or too dark, the picture is blurred, etc., the traditional recognition method cannot accurately detect the face
[0012] (2) Extremely sensitive to face occlusion
In many occasions, it is inevitable that the face is occluded, and the application of

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
  • Multi-neural network cascaded face recognition method based on human face key points
  • Multi-neural network cascaded face recognition method based on human face key points
  • Multi-neural network cascaded face recognition method based on human face key points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] For the convenience of description, first explain the relevant professional terms appearing in the specific implementation:

[0043] MTCNN (Multi-task Convolutional Neural Networks): Multi-task convolutional neural network;

[0044] P-Net (Proposal Network): Proposal network;

[0045] R-Net (Refine Network): perfect network;

[0046] O-Net (Output Network): output network;

[0047] CNN (Convolutional Neural Networks): Convolutional Neural Networks;

[0048] PCA (Principal Component Analysis): principal component analysis;

[0049] BP neural network (Error Back Propagation Neural Network): Back propagation neural network.

[0050] figure 1 It is a flow chart of the method of multi-neural network cascade recognition based on the key points of the face of the present invention.

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 multi-neural network cascaded face recognition method based on human face key points. The multi-neural network cascaded face recognition method comprises the steps of: detecting a face image by adopting an MTCNN algorithm, and then utilizing affine transformation to rotate, translate and zoom a human face for subsequent processing; and utilizing a convolutional neural network for detecting human face contour key points and human face internal key points respectively, and performing feature dimensionality reduction by adopting a PCA algorithm. When performing dimensionality reduction, methods based on a category pattern can be adopted according to different categories, the problems that the traditional PCA algorithm cannot effectively utilize category information between categories and the robustness is poor in the presence of illumination and facial expression changes can be overcame, and finally, the BP neural network is used for recognition. Since advanced or improved methods are used in many links, good effect can be obtained when face recognition is performed.

Description

Technical field [0001] The invention belongs to the technical field of face recognition, and more specifically, relates to a method for cascading multiple neural networks based on key points of the face to recognize faces. Background technique [0002] Face recognition is a kind of biometric recognition technology based on human facial feature information. A series of related technologies that use a camera or camera to collect images or video streams containing human faces, and automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called face recognition and facial recognition . [0003] Modern research on face recognition began in the late 1960s. In the past 20 years, with the improvement of computer performance and the continuous development of algorithms, face recognition has made a major breakthrough and has truly entered the stage of automatic recognition. Nowadays, face recognition has been widely ...

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): G06K9/00G06N3/08
CPCG06N3/084G06V40/165G06V40/171
Inventor 刘珊杨波郑文锋徐聪聪
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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