Face recognition method based on evolutionary convolutional neural network

A convolutional neural network and face recognition technology, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as dependence on artificial intelligence, and achieve the effect of ensuring elitism and improving diversity

Active Publication Date: 2020-07-14
SICHUAN UNIV
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the above-mentioned deficiencies in the prior art, a face recognition method based on evolutionary convolutional neural network provided by the present invention solves the problem that the prior art relies on artificial

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 recognition method based on evolutionary convolutional neural network
  • Face recognition method based on evolutionary convolutional neural network
  • Face recognition method based on evolutionary convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0061] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0062] Such as figure 1 As shown, a face recognition method based on evolutionary convolutional neural network includes the following steps:

[0063] S1. According to the variable-length coding strategy, generate N convolutional neural network structures through an indirect coding method, obtain an...

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 recognition method based on an evolutionary convolutional neural network, and the method employs a genetic algorithm to optimize the system structure design and connection weight initialization of the convolutional neural network, searches an optimal neural network through continuous evolution, and reduces the dependence on the artificial experience in the network architecture design. According to the method, the convolutional neural network is coded by adopting a variable-length gene coding strategy, the diversity of the structure of the convolutional neural network is improved, and in order to enable the variable-length chromosomes to be crossed, the crossing operation of the chromosomes with inconsistent lengths is realized by adopting a method of respectively crossing corresponding positions of structural units and then recovering. In the environment selection link, elite selection is firstly carried out, and two groups of fitness comparison and selection are carried out on the remaining individuals of the population, so that the elite property is ensured, and the diversity is realized.

Description

technical field [0001] The invention belongs to the field of face recognition, and in particular relates to a face recognition method based on an evolutionary convolutional neural network. Background technique [0002] Face recognition refers to a technology that can identify or verify the identity of a subject in an image or video. Compared with traditional recognition methods such as fingerprint or iris recognition, face recognition is considered to be a more robust biometric method. Face recognition is essentially non-invasive. Unlike fingerprint and iris recognition, which require a high degree of cooperation from users, face recognition is very user-friendly. Therefore, the potential applications of facial recognition are much wider, as it can also be deployed in environments where users are not expected to cooperate with the system, such as surveillance systems. In addition, face recognition technology is currently widely used in access control, fraud detection, ident...

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): G06K9/00G06N3/00G06N3/04G06N3/08G06N3/12
CPCG06N3/006G06N3/08G06N3/126G06V40/172G06N3/045G06V10/82G06N3/082G06N3/086G06V30/19173G06N3/04
Inventor 孙亚楠李思毅
Owner SICHUAN UNIV
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