Performance comparison of KPCA and LDA using Gabor filters Based Face Recognition System

Abstract

Face recognition is one of the standout among the most essential areas in research over from the past to present. Feature extraction is very important and it plays a major role in improving the recognition rate of the face biometric system. In my project, I have mainly focused on Gabor filter feature extraction technique and performed comparison on the linear Gabor LDA with the Gabor KPCA which is a non-linear technique to analyze which technique is better suitable for face identification environment. These procedures, admirablyfunctions well under robust conditions like complex variations in picture quality, distinctive face positions and different lightening conditions. These calculations give diverse rates of exactness under various conditions as tentatively watched. These algorithms work well for ORL face dataset which have a particular appearance changing under certain range. We have taken a face picture database and successfully performed the calculations in MATLAB effectively