Performance Evaluation of Face Recognition based on Multiple Feature Descriptors using Euclidean Distance Classifier

Personal Identification based on face recognition is receiving extensive attention over the last few years in both research and real time applications due to increasing emphasis on security. In this paper, Face Recognition based on Stationary Wavelet Transform (SWT), Discrete Cosine Transform (DCT) and Local Ternary Pattern (LTP) is presented. Face images are resized. SWT and DCT are applied on face images to produce features. LTP is applied on SWT features. SWT, DCT and LTP features are concatenated to get final features. Features of test and database images are compared using Euclidean distance. It is found that Total Success Rate of the proposed system is better than existing systems.