The objective of this paper is to develop the image processing and recognize the faces using PCA-based face recognition technique. MATLAB based programs are implemented to identify the faces using Indian databases and the Face recognition data, University of Essex, UK. For matching unknown images with known images, different techniques like sum of absolute difference (SAD), sum of squared difference (SSD), normalized cross correlation (NCC) etc. can be used which has been shown in this paper. Finally, it has been shown that the performance of PCA-based face recognition system is quite satisfactory instead of having some shortcomings of the system.
principle component analysis (pca) independent component analysis (ica) sum of squared difference (ssd) normalized cross correlation (ncc) sum of absolute difference (sad) linear discriminant analysis (lda) peak signal to noise ratio (psnr)
Tahia Fahrin Karim Molla Shahadat Hossain Lipu Lushanur Rahman Faria Sultana
Electrical & Electronic Engineering Department Primeasia University Dhaka, Bangladesh Electrical & Electronic Engineering Department University of Asia Pacific Dhaka, Bangladesh IP Network, Implementation Department, Technology Division Axiata (Bangladesh) Limited Dhaka,Banglad Technical Department Automation Drives & Control Limited Dhaka, Bangladesh