基于PCA的最小二乘支持向量机人脸识别研究  

Face Recognition Research Based on PCA and LSSVM

作　　者：史永伟[1] 王仲华[1] 

机构地区：[1]太原师范学院数学系,太原030012

出　　处：《电脑开发与应用》2014年第9期70-72,共3页Computer Development & Applications

摘　　要：人脸识别是模式识别的一个重要分支,主要由特征提取和分类识别两个阶段决定,由于其小样本,高维数的特点,传统的分类器容易导致过学习问题,首先使用主成分分析法对人脸图像进行降维表示,然后将最小二乘支持向量机用于识别阶段,仿真实验显示的方法取得了较好的识别效果和识别效率。Face recognition is an important branch in pattern recognition , its effect is mainly decided by the two stages of feature extraction and classification method. Because of the small sample, high dimension, the traditional classifier can easily lead to overfitting problem,this paper uses principal component analysis to reduce the dimensionality of face image, then the least squares support vector machine is used for the recognition stage. The experimental results show that this method has good recognition effect and the recognition efficiency.

关 键 词：主成分分析 最小二乘法 支持向量机 人脸识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]