A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation

AN Gao-yun; RUAN Qiu-qi

您当前的位置：

首页 >

文章列表页 >

A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation

更新时间：2025-07-16

- A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation
- Acta Electronica Sinica Vol. 34, Issue 10, Pages: 1900-1905(2006)
- 作者机构：
  
  北京交通大学信息科学研究所,北京,100044
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.4
- Published：2006
- 稿件说明：
移动端阅览
AN Gao-yun, RUAN Qiu-qi. A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation[J]. Acta Electronica Sinica, 2006, 34(10): 1900-1905.
DOI：

AN Gao-yun, RUAN Qiu-qi. A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation[J]. Acta Electronica Sinica, 2006, 34(10): 1900-1905. DOI：

摘要

鲁棒主分量分析(RPCA)模型在选取幅度参数时

忽略了各变量独有的统计特性.为克服RPCA模型的这一不足

本文提出了通用鲁棒主分量分析(GRPCA)模型

采用M估计器(M-Estimator)为每个变量估计符合其自身统计特性的幅度参数

以提高模型的鲁棒性和通用性

并在此基础上提出了一种集成小波分解、鲁棒估计及独立分量分析的WR-ICA人脸识别算法.WR-ICA对人脸识别中的多种外部干扰(残缺人脸图像、化妆及遮挡等)都表现出很好的鲁棒性.理论分析和实验结果证实了WR-ICA的有效性

采用Cos距离作相似性度量时

WR-ICA的平均识别率达到99.44%.

Abstract

In the robust principal component analysis(RPCA)model

the statistical properties of every variable are neglected when scale parameters are chosen for them.In order to overcome this drawback

a generalized robust principal component analysis(GRPCA)model was proposed in this paper

a M-estimator was adopted to estimate robust scale parameters for every variable according to their statistical properties.Then

a new independent component analysis algorithm for face recognition based on wavelet decomposition and robust estimation (WR-ICA) was proposed.WR-ICA is robust to many types of outliers (incomplete face image

making up

occlusion

etc).The validity of WR-ICA is confirmed by theory analysis and experimental data

with Cos distance as similarity measurement

the average recognition rate of WR-ICA is 99.44%.

关键词

Keywords

references

Views

1271

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Blind Source Separation

Lightweight New Fesidual Face Recognition Method Based on Feature Fusion

Multi-task Learning and Identity-constrained Generative Adversarial Network for Face Frontalization and Recognition

A Spectral Unmixing-Based Method for Road Detection in Hyperspectral Images

A Kernel Orthogonal Discriminant Locality Preserving Projections Method

Related Author

ZHANG Xian-da

BAO Zheng

HUI Kang-hua

YAN Jian-qing

GAO Si-hua

HE Huai-qing

HUANG Xin-yan

LIU Fang

Related Institution

Key Laboratory for Radar Signal Processing,Xidian University

College of Computer Science and Technology， Civil Aviation University of China

School of Artificial Intelligent， Xidian University

Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education， Xidian University

International Research Center for Intelligent Perception and Computation， Xidian University

⁰