Expected Distribution Discriminant Analysis Based on Similarity of Sample Distribution
GUO ZhiBo1,2, YANG JingYu1, ZHENG YuJie1, YAN YunYang1
1.College of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094 2.College of Information Engineering, Yangzhou University, Yangzhou 225009
Abstract:Principal component analysis (PCA) and linear discriminant analysis (LDA) are two kinds of popular feature extraction methods for pattern recognition. A new method, expected distribution discriminant analysis (EDDA), is proposed based on the similarity of sample distribution after some disadvantages of PCA and LDA are indicated. The distribution of extracted features is mostly close to the expected distribution such as idealized distribution by using EDDA. Based on EDDA, the small sample size problem (SSSP) does not occur any more. The dimension of discrimination feature is very low and the recognition performance is enhanced. Some experimental results on ORL and Yale face database demonstrate that the proposed method has higher recognition rate than PCA and LDA.
[1] Zhao W, Chelllappa R, Phillips P J, et al. Face Recognition: A Literature Survey. Technical Report, CARTR948, College Park, USA: University of Maryland. Center for Automation Research, 2000 [2] Kirby M, Sirovich L. Application of the KL Procedure for the Characterization of Human Faces. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(1): 103108 [3] Turk M, Pentland A. Eigenfaces for Recognition. Journal of Cognitive Neuroscience, 1991, 3(1): 7186 [4] Belhumeur P N, Hespanha J P, Kriengman D J. Eigenfaces vs. Fisherfaces: Recognition Using Class Special Linear Projection. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711720 [5] Swets D L, Weng J. Using Discriminant Eigenfeatures for Image Retrieval. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(8): 831836 [6] Chen L F, Liao H Y M, Han C C, et al. A New LDABased Face Recognition System Which Can Solve the Small Sample Size Problem. Pattern Recognition, 2000, 33(10): 17131726 [7] Huang Rui, Liu Qingshan, Lu Hanging, et al. Solving the Small Sample Size Problem of LDA // Proc of the International Conference on Pattern Recognition. Quebec, Canada, 2002: 2932 [8] Yang Jian, Yang Jingyu. Why Can LDA be Performed in PCA Transformed Space? Pattern Recognition, 2003, 36(2): 563566 [9] Jin Zhong. Research on Feature Extraction of Face Images and Feature Dimensionality. Ph.D Dissertation. Nanjing, China: Nanjing University of Sience and Technology. Department of Computer Science and Technology, 1999 (in Chinese) (金 忠.人脸图像特征抽取与维数研究.博士学位论文.南京:南京理工大学.计算机科学与技术学院, 1999) [10] Jin Zhong, Yang Jingyu, Hu Zhongshan, et al. Face Recognition Based on Uncorrelated Discriminant Transformation. Pattern Recognition, 2001, 34(7): 14051416