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

Face recognition method based on multi-dimensional Taylor network

A technology of face recognition and Taylor net, applied in the field of face recognition, can solve the problem that the convergence speed has not been significantly improved

Pending Publication Date: 2021-04-02
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The elastic BP neural network algorithm can avoid the situation that the training has stopped before reaching the optimal value, and can effectively eliminate the adverse effects of the gradient size on the neural network, but the convergence speed of the algorithm has not been significantly improved

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 multi-dimensional Taylor network
  • Face recognition method based on multi-dimensional Taylor network
  • Face recognition method based on multi-dimensional Taylor network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described below in conjunction with accompanying drawing.

[0059] Such as figure 1 As shown, the present invention proposes the face recognition method based on multidimensional Taylor network, comprises the following steps:

[0060] 1. Build a neural network structure. Specific steps are as follows:

[0061] Step (1) Build the neural network structure. Specific steps are as follows:

[0062] Step (1-1) uses the activation function to calculate the output of the hidden layer and the output of the output layer, and uses the principle of back propagation to update the weight and bias according to the error between the network output and the expected output.

[0063]

[0064]

[0065]

[0066] g(x) represents the activation function, n is the number of input layer nodes, l is the number of hidden layer nodes, a j Indicates the jth bias of the hidden layer, the weight matrix from the input layer to the hidden layer is 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 a multi-dimensional Taylor network. The construction process of the multi-dimensional Taylor network comprises the following steps: performing Taylor expansion on an activation function of a neural network structure, performing linear combination on the Taylor expansion of the activation function to obtain network output, and finally obtaining an optimal solution of a target function by minimizing a loss function. Through a simulation test of an ORL face data set, a feature face extracted by PCA and 2DPCA algorithms is used as networkinput, and the effectiveness of the method is verified.

Description

technical field [0001] The invention belongs to the field of face recognition, and in particular relates to a face recognition method based on multidimensional Taylor nets. Background technique [0002] In contemporary social services and industrial applications, face recognition has become a hot topic in the fields of pattern recognition, image processing, and computer vision due to its broad application prospects and unique academic value. Face recognition methods can be roughly divided into three categories: 1) face recognition methods based on geometric features; 2) face recognition methods based on models; 3) methods based on statistical features. Neural network is the mainstream method in the model-based face recognition method, and it was proposed by scientists Rumelhart and McClelland in 1986. Later, Yang Yiruo and Wang Xufa proposed the PCA-BP method, but this method is susceptible to illumination and face rotation. Aiming at the problem that the PCA-BP method is s...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/168G06V40/172G06N3/048G06N3/045G06F18/2135G06F18/214
Inventor 郭金金胡尘李明媚文成林徐晓滨
Owner HANGZHOU DIANZI UNIV
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