TY - GEN
T1 - Face recognition using modular locality preserving projections
AU - Liu, Pengzhang
AU - Shen, Tingzhi
AU - Hu, Yu
AU - Zhao, Sanyuan
PY - 2009
Y1 - 2009
N2 - Facial-image data are always distributed in the high-dimensional space, which makes it difficult to use for accurate face recognition. Recently, many manifold learning methods have been proposed to reduce the dimensionality of the image data. In this paper, a novel method, named Modular Locality Preserving Projection (Modular LPP), is proposed. This proposed method is derived from the LPP methods, and is designed to handle face images with various illuminations and facial expressions. In the proposed method, the face images are divided into smaller sub-images and the LPP approach is applied to each of these sub-images. As some of the local facial features of an individual do not vary even when the lighting directions and facial expressions vary, the proposed method is expected to cope with these variations. The Modular LPP and its variant are compared with LPP, based on the Yale and YaleB face database. Experimental results show the significant improvement of our proposed algorithm.
AB - Facial-image data are always distributed in the high-dimensional space, which makes it difficult to use for accurate face recognition. Recently, many manifold learning methods have been proposed to reduce the dimensionality of the image data. In this paper, a novel method, named Modular Locality Preserving Projection (Modular LPP), is proposed. This proposed method is derived from the LPP methods, and is designed to handle face images with various illuminations and facial expressions. In the proposed method, the face images are divided into smaller sub-images and the LPP approach is applied to each of these sub-images. As some of the local facial features of an individual do not vary even when the lighting directions and facial expressions vary, the proposed method is expected to cope with these variations. The Modular LPP and its variant are compared with LPP, based on the Yale and YaleB face database. Experimental results show the significant improvement of our proposed algorithm.
KW - Facial expressions
KW - Illuminations
KW - Locality preserving projections (LPP)
KW - Modular LPP
KW - Sub-image
UR - https://www.scopus.com/pages/publications/77949289798
U2 - 10.1109/CIS.2009.119
DO - 10.1109/CIS.2009.119
M3 - Conference contribution
AN - SCOPUS:77949289798
SN - 9780769539317
T3 - CIS 2009 - 2009 International Conference on Computational Intelligence and Security
SP - 320
EP - 324
BT - CIS 2009 - 2009 International Conference on Computational Intelligence and Security
T2 - 2009 International Conference on Computational Intelligence and Security, CIS 2009
Y2 - 11 December 2009 through 14 December 2009
ER -