Title :
Two Dimension Locally Principal Component Analysis for Face Recognition
Author :
Lin, Yu-sheng ; Wang, Jian-guo ; Yang, Jing-Yu
Author_Institution :
Dept. of Comput. Sci., Nanjing Univ. of Sci. & Technol., Nanjing
Abstract :
In this paper, we propose a feature extraction method called two dimension locally principal component analysis (2DLPCA) for face recognition, which is based directly image matrix rather than 1D image vectors. 2DLPCA seeks to discover the intrinsic image local structure. This local structure may contain useful information for discrimination. Experimental results on ORL face database show the effectiveness of the proposed algorithm.
Keywords :
face recognition; feature extraction; matrix algebra; principal component analysis; 2D locally principal component analysis; ORL face database; face recognition; feature extraction; image local structure; image matrix; Computer science; Computer science education; Educational institutions; Electronic mail; Face detection; Face recognition; Feature extraction; Image databases; Principal component analysis; Spatial databases;
Conference_Titel :
Pattern Recognition, 2008. CCPR '08. Chinese Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2316-3
DOI :
10.1109/CCPR.2008.52
