A New Approach for Face Recognition Based on Singular Value Features and Neural Networks

GAN Jun-ying; ZHANG You-wei

您当前的位置：

首页 >

文章列表页 >

A New Approach for Face Recognition Based on Singular Value Features and Neural Networks

更新时间：2025-07-16

- A New Approach for Face Recognition Based on Singular Value Features and Neural Networks
- Acta Electronica Sinica Vol. 32, Issue 1, Pages: 170-173(2004)
- 作者机构：
  
  1. 五邑大学信息学院,广东,江门,529020
  2. 北京航空航天大学电子信息工程学院,北京,100083
  3. 五邑大学信息学院广东江门,529020
  4. 北京航空航天大学电子信息工程学院北京,100083
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2004
- 稿件说明：
移动端阅览
GAN Jun-ying, ZHANG You-wei. A New Approach for Face Recognition Based on Singular Value Features and Neural Networks[J]. Acta Electronica Sinica, 2004, 32(1): 170-173.
DOI：

GAN Jun-ying, ZHANG You-wei. A New Approach for Face Recognition Based on Singular Value Features and Neural Networks[J]. Acta Electronica Sinica, 2004, 32(1): 170-173. DOI：

摘要

本文在Z Hong等人使用的奇异值分解(SVD)基础上

将人脸图像矩阵的奇异值作为识别特征

解决了奇异值处理、神经网络训练策略和竞争选择问题;运用BP网络进行识别

提出了一种基于奇异值特征的神经网络人脸识别新方法.基于ORL人脸数据库的多次反复实验结果表明

在大样本情况下

识别方法具有实现简单、识别速度快、识别率高的特点

为人脸的实时识别提供了一种新途径.

Abstract

In this paper

singular value processing

training strategies of neural networks and competition selection are solved on the basis of singular value decomposition(SVD) applied by Z Hong et al.A new approach for face recognition on singular value features and neural networks is presented

in which singular values of face image matrix are used as features

and Back-Propagation(BP) network as recognition.Repeated experimental results on ORL(Olivetti Research Laboratory) database demonstrate that under the conditions of large samples recognition method has the characteristics of simple realization

rapid recognition speed and high recognition rate

and also profits real-time realization.

关键词

Keywords

references

Views

1900

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bionic Pattern Recognition—— A New Model of Pattern Recognition Theory and Its Applications (Lab of Artificial Neural Networks,Institute of Semiconductors,CAS,Beijing 100083,China)

A Neural Network That Can Recognize Some Common Abstract Features of Different Samples

Pattern Classification Neural Network Model Based on Homologue Connectedness

The Equal-Error Range Approximation and Shrink Learning Rule for Multilayer Perceptions and Its Applications

A Neural Net DTW Architecture in Speech Recognition

Related Author

WANG Shou-jue

LI Qian

DENG Hao-jiang

WANG Shou-jue

YANG Guo-wei

WANG Shou-jue

WEI Cheng-bing

CAO Wen-yi

Related Institution

Topological

Artificial Neural Networks Laboratory,Institute of Semiconductors,Chinese Academy of Sciences

Nanchang Hangkong University, Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition

Laboratory of Artificial Neural Network, Institute of Semiconductors, Chinese Academy of Sciences

⁰