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

Facial feature extraction system and method based on FECNN

A face feature and feature extraction technology, applied in the field of face recognition, can solve the problems of inability to fully characterize the face, many iterations, long convergence time, etc., to improve the extraction speed and accuracy, and robust face depth. The effect of features

Active Publication Date: 2017-04-05
GUILIN UNIV OF ELECTRONIC TECH
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a kind of human face feature extraction system based on FECNN, the technical problem to be solved is: the feature that shallow CNN network extracts can't represent human face fully, and the CNN network of deep layer is faced with too many iterations , the convergence time is too long

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
  • Facial feature extraction system and method based on FECNN
  • Facial feature extraction system and method based on FECNN
  • Facial feature extraction system and method based on FECNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Such as Figure 1 to Figure 3 As shown, a face feature extraction system based on FECNN, including face preprocessing module 1, FECNN (FECNN is Fast and Effective Convolutional Neural Networks, is an efficient convolutional neural network) module 2, feature extraction module 3 and feature ratio for module 4;

[0046] Described human face preprocessing module 1 is used for carrying out human face detection to human face pictures, and the detected human face image is cut out, and the human face key point is located on the human face image, and then the human face key point is combined with Align face images;

[0047] The FECNN module 2 is used to build the FECNN framework for feature extraction, and uses the training library sample face to train the FECNN framework until the FECNN framework converges to obtain the FECNN parameter model;

[0048] The feature extraction module 3 is used to extract the FECNN to extract the network parameter model, send the face key points ...

Embodiment 2

[0066] Such as Figure 4 Shown, a face feature extraction method based on FECNN, including the following steps:

[0067] Step S1. Face preprocessing module 1 performs face detection on the face picture, and cuts the detected face image, locates the key points of the face on the face image, and then compares the key points of the face with the face The images are aligned; the FECNN module 2 builds the FECNN framework for feature extraction, and uses the training library sample face to train the FECNN framework until the FECNN framework converges to obtain the FECNN parameter model;

[0068] Step S2. The feature extraction module 3 extracts the FECNN to extract the network parameter model, sends the key points of the face and the face image into the FECNN parameter model for feature extraction, and outputs the face features;

[0069] Step S3. The feature comparison module 4 uses the cosine distance to calculate the face features. When the calculated distance is greater than the...

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 relates to a facial feature extraction system and a method based on FECNN. The system comprises a face pretreatment module, an FECNN module, a feature extraction module and a feature comparison module, wherein the face pretreatment module is used for carrying out face detection on a face image and carrying out cutting, positioning and aligning on the detected face image; the FECNN module builds an FECNN frame for feature extraction and carries out training until the FECNN is converged, and an FECNN parameter model is obtained; the feature extraction module sends face key points and the face image to the FECNN parameter model to extract face features; and the feature comparison module uses a cosine distance to calculate the face features, when the distance is larger than a set threshold t, the same person is judged, and when the distance is smaller than the set threshold t, different persons are judged. Compared with the prior art, the system and the method of the invention use few parameters, the network model can be quickly converged, and robust face features can be extracted.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a system and method for extracting face features based on FECNN. Background technique [0002] Face recognition is currently one of the hottest research topics in the fields of machine learning, pattern recognition and computer vision, and it has more and more applications in practical engineering. After decades of research, fruitful results have been obtained. In recent years, CNN has been used for image processing many times, and it has been proved that it is more practical and has higher accuracy than traditional methods in feature extraction of targets. In particular, CNN has made breakthrough progress in face recognition, showing unlimited prospects; but in the existing technology, the features extracted by the shallow CNN network cannot fully represent the face, and the deep CNN network Faced with too many iterations and too long convergence time. Contents of 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): G06K9/00G06N3/04
CPCG06V40/165G06V40/172G06V40/171G06N3/045
Inventor 蔡晓东吕璐
Owner GUILIN UNIV OF ELECTRONIC 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