EV-SIFT - An Extended Scale Invariant Face Recognition for Plastic Surgery Face Recognition

Abstract

Automatic recognition of people faces many challenging problems which has experienced much attention due to many applications in different fields during recent years. Face recognition is one of those challenging problem which does not have much technique to solve all situations like pose, expression, and illumination changes, and/or ageing. Facial expression due to plastic surgery is one of the additional challenges which arise recently. This paper presents a new technique for accurate face recognition after the plastic surgery. This technique uses Entropy based SIFT (EV-SIFT) features for the recognition purpose. The corresponding feature extracts the key points and volume of the scale-space structure for which the information rate is determined. This provides least effect on uncertain variations in the face since the entropy is the higher order statistical feature. The corresponding EV-SIFT features are applied to the Support vector machine for classification. The normal SIFT feature extracts the key points based on the contrast of the image and the V- SIFT feature extracts the key points based on the volume of the structure. But the EV- SIFT method provides the contrast and volume information. This technique provides better performance when compare with PCA, normal SIFT and V-SIFT based feature extraction.