Face Recognition Based on Two-Dimensional Heteroscedastic Discriminant Analysis
Junying Gan, Si-Bin He, Bing Luo · 2009
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 (HAD) 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.