Occluded Face Images Recognition Using Robust LDA

LDA´s between class scatter matrix is confronted with small sample size problem. In order to avoid this problem, PCA subspace is used which reduces the dimensions of images to such an extent that small sample size problem can be avoided. This approach is called as LDA using PCA subspace. Robust LDA by sub-sampling is a modification of LDA using PCA subspace and is designed to work in non-ideal conditions, in conditions where images are occluded. Robust LDA uses sub-sampling to avoid occluded pixels and use only true image pixels of the occluded image. The complexity efface recognition under non-ideal conditions is dependent upon number of classes used and percentage of occlusion applied to test image. In this paper comparison has been made and found that robust LDA by subsampling remains a better classifier than LDA using PCA subspace for occlusion of 50 percent using 17 classes