Face Recognition Using SIFT- PCA Feature Extraction and SVM Classifier

Abstract

Face recognition is a biometric software application that can identify a specific individual in a digital image by analyzing and comparing pattern. In the proposed approach, Here main focus on the face recognition system. It will one of the new face recognition system based on an efficient design. This paper present proposed methodology of global thresholding technique, SIFT (Scale Invariant Feature Transform),PCA(Principal Component Analysis) and SVM (Support Vector Machine) classifier. SIFT is used for extract the feature from faces. This SIFT feature will possess strong robustness to the accessory, expression, pose, illumination variations. PCA is a standard technique use for dimensionality reduction in which face data can analyze and observation can be described by several inter-correlated dependent variables. The SVM classifiers are then applied to these extracted features to classify the input images. Global thresholding technique will used for detecting the face. So this proposed system will increases the face identification rate.