An efficient illumination invariant human face recognition using new preprocessing approach

Abstract

In any image, illumination is one of the challenges task and effect the performance of the system. In this paper, we have proposed new preprocessing approach to eliminate illumination effect from the human face images. In our approach we first apply Log transform on the input image to enhance illumination effect, output of this is given as input to the DoG filtering technique to smooth the image and then performing image normalization so we get the illumination eliminated image. To measure the performance of the proposed approach we are using PCA method to calculate the face recognition. We have performed analysis on the YaleB face database. We have proved that our approach give better recognition rate compare to some of the existing approaches.