Si-Bin He

Wuyi University, Chiang-men-shih, Guangdong, China

Are you Si-Bin He?

Claim your profile

Publications (5)0 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel discriminant analysis named two-dimensional Heteroscedastic Discriminant Analysis (2DHDA) is presented for face recognition. In 2DHDA, small sample size problem (S3 problem) of Heteroscedastic Discriminant Analysis is overcome. Firstly, the criterion of 2DHDA is defined according to that of 2DLDA. Secondly, criterion of 2DHDA, log and rearranging terms are taken, and then the optimal projection matrix is solved by gradient descent algorithm. Thirdly, face images are projected onto the optimal projection matrix, thus the 2DHDA features are extracted. Finally, Nearest Neighbor classifier is selected to perform face recognition. Experimental results show that higher recognition rate is obtained by way of 2DHDA compared with 2DLDA.
    Advanced Intelligent Computing Theories and Applications - 6th International Conference on Intelligent Computing, ICIC 2010, Changsha, China, August 18-21, 2010. Proceedings; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Kernel method is a nonlinear feature extraction approach. Firstly, the samples in the original feature space are transformed into a higher dimensional feature space by nonlinear mapping. Then, linear approaches are used in the higher dimensional feature space, and thus nonlinear features of original samples are extracted. The Heteroscedastic Discriminant Analysis (HDA), in which the equal within-class scatters matrix constraint of Linear Discriminant Analysis (LDA) is removed and more discriminant information is achieved. In this paper, take the advantages of kernel method and HDA, kernel Heteroscedastic discriminant analysis (KHDA) is presented and used for face recognition. Experimental results based on Olivetti Research Laboratory (ORL), ORL and Yale mixture face database show the validity KHDA for face recognition.
    Fifth International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2010, University of Hunan, Liverpool Hope University, Liverpool, United Kingdom / Changsha, China, September 8-10 and September 23-26, 2010; 01/2010
  • Jun-Ying Gan, Si-Bin He, Peng Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: In Two-Dimensional Linear Discriminant Analysis (2DLDA), it is satisfied that within-class covariance matrixes are equal; while in Two-Dimensional Heteroscedastic Discriminant Analysis (2DHDA), within-class covariance matrixes are heteroscedastic. Based on the characters of 2DLDA and 2DHDA, Weighted Two-Dimensional Heteroscedastic Discriminant Analysis (W2DHDA) is introduced and used in face recognition, in which within-class covariance matrix is defined as weighted summation of both within-class covariance matrixes of 2DLDA and 2DHDA. In this way, the defined within-class covariance matrixes in W2DHDA are more robust. Experimental results based on ORL (Olivetti Research Laboratory) and Yale mixture face database show the validity of W2DHDA in face recognition.
    01/2010;
  • Jun-Ying Gan, Si-Bin He
    [Show abstract] [Hide abstract]
    ABSTRACT: Singularity problem of LDA algorithm is overcome by two-dimensional LDA (2DLDA), and support vector machine (SVM) has the character of structural risk minimization. In this paper, two methods are combined and used for face recognition. Firstly, the original images are decomposed into high-frequency and low-frequency components with the help of wavelet transform (WT). The high-frequency components are ignored, while the low-frequency components can be obtained. Then, the linear discriminant features are extracted by 2DLDA, and SVM is selected to perform face recognition. Experimental results based on ORL(Olivetti Research Laboratory) and Yale face database show the validity of 2DLDA+SVM for face recognition.
    Wavelet Analysis and Pattern Recognition, 2009. ICWAPR 2009. International Conference on; 08/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel discriminant analysis named two-dimensional Heteroscedastic Discriminant Analysis (2DHDA) is presented, and used for gender classification. In 2DHDA, equal within-class covariance constraint is removed. Firstly, the criterion of 2DHDA is defined according to that of 2DLDA. Secondly, the criterion of 2DHDA, log and rearranging terms are taken, and then the optimal projection matrix is solved by gradient descent algorithm. Thirdly, face images are projected onto the optimal projection matrix, thus the 2DHDA features are extracted. Finally, Nearest Neighbor classifier is selected to perform gender classification. Experimental results show that higher recognition rate is obtained by way of 2DHDA compared with 2DLDA and HDA.
    Emerging Intelligent Computing Technology and Applications, 5th International Conference on Intelligent Computing, ICIC 2009, Ulsan, South Korea, September 16-19, 2009. Proceedings; 01/2009