一种新颖的基于LDA的人脸识别方法(英文)  

A NOVEL FACE RECOGNITION METHOD BASED ON LINEAR DISCRIMINANT ANALYSIS

作　　者：张燕昆[1] 刘重庆[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200030

出　　处：《红外与毫米波学报》2003年第5期327-330,共4页Journal of Infrared and Millimeter Waves

摘　　要：提出一种基于离散余弦变换 (DCT)与LDA相结合的人脸识别方法 ,首先利用DCT将图像进行降维 ,然后在低维空间中利用LDA进行特征提取 .利用ORL人脸数据库和我们上海交通大学图像处理与模式识别研究所的人脸数据库进行测试 ,实验结果分别得到了 97.5 %和 92 .6 %的正确识别率 。A novel face recognition approach based on the DCT and the LDA is proposed. First the DCT is used for dimension reduction,then LDA transform is performed on the lower space to extract feature. The ORL face database and the SJ-TU-IPPR face database are used to test our approach and the correct recognition rates of 97.5% and 92.6% are obtained respectively, which shows that our approach is comparable with other approaches.

关 键 词：人脸识别 离散余弦变换 线性判别分析 主元分析 图像处理 模式识别 LDA 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]