Abstract

Face recognition subjected to various conditions is a challenging task. This paper presents a combined feature improved Fisher classifier method for face recognition. Both of the facial holistic information and local information are used for face representation. In addition, the improved linear discriminant analysis (I-LDA) is employed for good generalization capability. Experiments show that the method is not only robust to moderate changes of illumination, pose and facial expression but also superior to the traditional methods, such as eigenfaces and Fisherfaces.

© 2005 Chinese Optics Letters

Enhanced facial texture illumination normalization for face recognition

Yong Luo and Ye-Peng Guan
Appl. Opt. 54(22) 6887-6894 (2015)

Face verification through tracking facial features

Baoxin Li and Rama Chellappa
J. Opt. Soc. Am. A 18(12) 2969-2981 (2001)

Face recognition by using feature-specific imaging

Himadri S. Pal, Dinesh Ganotra, and Mark A. Neifeld
Appl. Opt. 44(18) 3784-3794 (2005)

Discriminant analysis for recognition of human face images

Kamran Etemad and Rama Chellappa
J. Opt. Soc. Am. A 14(8) 1724-1733 (1997)

Improving cross-modal face recognition using polarimetric imaging

Nathaniel Short, Shuowen Hu, Prudhvi Gurram, Kristan Gurton, and Alex Chan
Opt. Lett. 40(6) 882-885 (2015)