计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (34): 155-157.DOI: 10.3778/j.issn.1002-8331.2008.34.048

• 图形、图像、模式识别 • 上一篇    下一篇

分块PCA与最大散度差鉴别分析结合的人脸识别

崔美琳,陈才扣   

  1. 扬州大学 信息科学与工程学院,江苏 扬州 225009
  • 收稿日期:2008-05-26 修回日期:2008-09-05 出版日期:2008-12-01 发布日期:2008-12-01
  • 通讯作者: 崔美琳

Combination of modular PCA and maximum scatter difference discriminate analysis for face recognition

CUI Mei-lin,CHEN Cai-kou   

  1. Department of Computer Science and Engineering,Yangzhou University,Yangzhou,Jiangsu 225009,China
  • Received:2008-05-26 Revised:2008-09-05 Online:2008-12-01 Published:2008-12-01
  • Contact: CUI Mei-lin

摘要: 提出了一种将分块PCA与最大散度差鉴别分析相结合的人脸识别方法。该方法是先对原始的人脸图像进行分块,然后对分块得到的子图像矩阵采用PCA方法进行特征抽取,从而把原始模式从高维空间映射到较低维空间。接下来再对新模式采用最大散度差线性鉴别分析,这样就避免了对新模式的类内散布矩阵非奇异的要求。在ORL人脸库和Yale人脸库上分别检验了分块PCA与最大散度差鉴别分析相结合的人脸识别方法的识别性能,实验结果表明该方法抽取的鉴别特征有较强的鉴别能力。

关键词: 分块PCA, 最大散度差鉴别分析, 人脸识别

Abstract: In this paper,a new method of combination of modular PCA and Maximum Scatter Difference Discriminate Analysis(MSDDA) is developed.In the proposed method,the original face images are divided into smaller sub-images.Then the PCA approach is applied to each of these sub-images,and the new lower dimensionality patterns take the place of the original patterns.Because the MSDDA eliminates the redundant information within the features,in the end,the MSDDA is performed for the pattern classification.Finally,extensive experiments performed on both ORL face database and Yale face database verify the effectiveness of the proposed method.

Key words: modular PCA, Maximum Scatter Difference Discriminate Analysis(MSDDA), face recognition