DST Feature Based Locality Preserving Projections for Face Recognition

Locality preserving projection (LPP) is a promising manifold learning approach for dimensionality reduction. However, it often encounters small sample size (3S) problem in face recognition tasks. To overcome this limitation, this paper proposes a discrete sine transform (DST) feature extraction approach and develops a DST-feature based LPP algorithm for face recognition. The proposed method has been tested and evaluated with two public available databases, namely ORL and FERET databases. Comparing with Eigenface, Laplacianface methods, the proposed DST-LPP approach gives superior performance.

[1]  Lei Zhu,et al.  Face recognition based on orthogonal discriminant locality preserving projections , 2007, Neurocomputing.

[2]  Xiaoyang Tan,et al.  Pattern Recognition , 2016, Communications in Computer and Information Science.

[3]  Xuegang Wang,et al.  Uncorrelated Discriminant Locality Preserving Projections , 2008, IEEE Signal Processing Letters.

[4]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[6]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Haifeng Hu,et al.  Orthogonal neighborhood preserving discriminant analysis for face recognition , 2008, Pattern Recognit..

[8]  Xiaolong Teng,et al.  Face recognition using discriminant locality preserving projections , 2006, Image Vis. Comput..

[9]  A. Jain,et al.  A Fast Karhunen-Loeve Transform for a Class of Random Processes , 1976, IEEE Trans. Commun..

[10]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.