2004, Volume 6, Issue 2
Strategic Study of CAE >> 2004, Volume 6, Issue 2
A Study on the Essence of Optimal Statistical Uncorrelated Discriminant Vectors
1. East China Shipbuilding Institute , Zhenjiang , Jiangsu 212003 , China
2. School of Information , Nanjing University of Science & Technology , Nanjing 210094 , China
3. Shenyang Institute of Automation , Chinese Academy of Science , Shenyang 110015 , China
4. CVSSP , University of Surrey , Surrey GU2 7XH , UK
Next Previous
Abstract
A study has been made on the essence of optimal set of uncorrelated discriminant vectors in this paper. A whitening transform has been constructed on the basis of the eigen decomposition of population scatter matrix, which makes the population scatter matrix an identity matrix in the transformed sample space. Thus, the optimal discriminant vectors solved by conventional LDA methods are statistical uncorrelated. The research indicates that the essence of the statistical uncorrelated discriminant transform is the whitening transform plus conventional linear discriminant transform. The distinguished characteristic of the proposed method is that the obtained optimal discriminant vectors are orthogonal and statistical uncorrelated. The proposed method suits for all the problems of algebraic feature extraction. The numerical experiments on facial database of ORL show the effectiveness of the proposed method.
Keywords
pattern recognition ; feature extraction ; disciminant analysis ; generalized optimal set of discriminant vectors ; face recognition
Figures
图1
图2
图3
图4
图5
图6
图7
图8
图9
References
[ 1 ] TurkM , PentlandA .Eigenfacesforfacerecognition[J].CognitiveNeuroscience, 1991, 3 (1) :71～86
[ 2 ] FoleyDH , SammonJW .Anoptimalsetofdiscriminantvectors[J].IEEETransComputers, 1975, 24 (3) :281～289
[ 3 ] DucheneJ, LeclercqS .Anoptimaltransformationfordiscriminantand principalcomponentanalysis[J].IEEETransPAMI , 1988, 10 (6) :978～983
[ 4 ] HongZQ .Algebraicfeatureextractionofimageforrecognition[J].PatternRecognition, 1991, 24 (3) :211～219
[ 5 ] 洪子泉, 杨静宇.用于图像识别的图像代数特征抽取[J].自动化学报, 1992, 18 (2) :232～238 link1
[ 6 ] 洪子泉, 杨静宇.基于奇异值特征和统计模型的人像识别算法[J].计算机研究与发展, 1994, 31 (3) :60～65 link1
[ 7 ] ChengYQ , YangJY , LiuK , etal.Anovelfeatureextractionmethodforimagerecognitionbasedonsimilardiscrminantfunction[J].PatternRecognition, 1993, 26 (1) :115～125
[ 8 ] LiuK , ChengYQ , YangJY , etal.AnefficientalgorithmforFoley-Sammonoptimalsetofdiscriminantvectorsbyalgebraicmethod[J ]. InternationalJournalofPatternRecognitionandArtificialIntelligence, 1992, 6 (5) :817～829
[ 9 ] LiuK , ChengYQ , YangJY , etal.Ageneralizedoptimalsetofdiscriminantvectors[J].PatternRecognition, 1992, 25 (7) :731～739
[10] 郭跃飞, 杨静宇.求解广义最佳鉴别矢量的一种迭代算法及人脸识别[J].计算机学报.2000, 23 (11) :1189～1195 link1
[11] 郭跃飞.人脸图像代数特征提取与最佳鉴别矢量的研究[D].南京:南京理工大学, 2000
[12] GuoYuefei, LiShijin, YangJingyu, etal.AgeneralizedFoley-Sammontransformbasedongeneralizedfisherdiscriminantcriterionanditsapplicationtofacerecognition[J].PatternRecognitionLetters, 2003, 24 (1-3) :147～158
[13] WuXiaojun, YangJingyu, WangShitong, etal.Anewalgorithmforsolvingtheoptimaldiscriminantvectors[J ].JournalofComputerScienceandTechnology, 2002, 17 (3) :324～330 link1
[14] 金 忠.人脸图像特征抽取与维数研究[D].南京:南京理工大学, 1999
[15] 金 忠, 杨静宇.一种具有统计不相关性的最佳鉴别矢量集[J].计算机学报, 1999, 22 (10) :1105～1108 link1
京公网安备 11010502051620号
