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

Age interference resistant face recognition method

A face recognition and normalization technology, which is applied in the field of face recognition against age interference, can solve the problems of poor face recognition ability across ages, and achieve the effects of small feature differences, improved recognition accuracy, and simple structure

Pending Publication Date: 2019-07-05
四川电科维云信息技术有限公司
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide a face recognition method with anti-age interference, which can not only better have the two advantages of time and performance (shorter time / stronger performance), but also improve the face angle, light intensity and occlusion. The degree of adaptability is good, and it also effectively overcomes the impact of age changes on face recognition, solves the problem of poor recognition ability of cross-age faces in the existing technology, and improves the accuracy of cross-age face recognition

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
  • Age interference resistant face recognition method
  • Age interference resistant face recognition method
  • Age interference resistant face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] The present invention designs a face recognition method that resists age interference, which can not only better have the two advantages of time and performance (shorter time / stronger performance), but also has a certain effect on the angle of the face, the intensity of light and the degree of occlusion. It has good adaptability, and effectively overcomes the impact of age changes on face recognition, solves the problem of poor recognition ability of cross-age faces in the existing technology, and improves the accuracy of cross-age face recognition, especially The following setting method is adopted: using an end-to-end non-cascaded deep convolutional neural network to perform feature extraction and face recognition on pictures of the same person at different ages.

Embodiment 2

[0058] This embodiment is further optimized on the basis of the above-mentioned embodiment, and further in order to better realize the present invention, the following setting mode is adopted in particular: the face recognition method includes the following steps:

[0059] 1) Data preparation: Obtain pictures from the cross-age face database to form training sets and test sets;

[0060] When in use, the universal cross-age face database acquires pictures, because the cross-age face database includes multiple picture groups classified according to identity features and age features of faces. In the cross-age face database, multiple picture groups have been classified according to the identity features and age features of faces. Among them, the identity feature of the picture is the image feature of the face represented by the picture. Different faces have different identity labels, and the identity features are grouped according to the identity statistics of the faces. Stages,...

Embodiment 3

[0066] This embodiment is further optimized on the basis of any of the above-mentioned embodiments. Further, in order to better realize the present invention, the following configuration method is adopted in particular: said step 1) includes the following specific steps:

[0067] 1.1) Obtain pictures from the CACD database to form a training set, and obtain pictures from the MORPH database to form a test set;

[0068] 1.2) Divide the training set into different age groups, and use each person in the CACD database as a category to generate a category label file and record it in a txt file;

[0069] 1.3) After step 1.2), preprocess the multiple pictures in the training set (face extraction, face correction, and image size fixation), cut out the pictures in a unified mode, and scale them to a uniform size of 128x128; if the picture It is not ideal, for example, the key points of the face are not aligned, or the size of the picture is not uniform, and preprocessing is required.

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 an age interference resistant face recognition method, which adopts an end-to-end non-cascade structure deep convolutional neural network to perform feature extraction and facerecognition on pictures of the same person at different age stages, and comprises the following steps of obtaining the pictures through an age-crossing face database, and forming a training set and atest set; expanding the data by adopting a data set increasing method to form a training image; establishing the end-to-end non-cascade structure deep convolutional neural network containing seven convolutional layers, three maximum pooling layers, one full connection layer and one softmax layer, and performing network training on the end-to-end non-cascade structure deep convolutional neural network; extracting the deep abstract features of the faces through a deep neural network to carry out face recognition, so that the method has the advantages of considering the time and performance, hasbetter adaptability to the face angle, the illumination intensity and the shielding degree, effectively overcomes the influence of age change on the face recognition, and improves the cross-age facerecognition precision.

Description

technical field [0001] The present invention relates to the field of computer vision (Computer Vision) and the field of deep learning (Deep Learning), specifically, it is a face recognition method against age interference. Background technique [0002] The face recognition system takes face recognition technology as the core. It is an emerging biometric technology and a high-tech technology in the international scientific and technological field. It widely adopts the regional feature analysis method, integrates computer image processing technology and biostatistics principles, uses computer image processing technology to extract portrait feature points from videos, and uses biostatistics principles to analyze and establish mathematical models. Prospects. In 2006, the United States has required countries with which it has a visa-free entry and exit agreement to use the electronic passport system combined with face recognition before October 26. By the end of 2006, more than ...

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
CPCG06V40/16G06V40/169G06V40/178G06N3/045G06F18/214
Inventor 殷光强向凯王志国王春雨
Owner 四川电科维云信息技术有限公司
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

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