Publication

Abstract : In image processing domain biometrics is an emerging field, in which matching the face images of optical and infrared is a tough toil. Since the optical and infrared images are captured by two disparate devices there exists a great diversity between one and the other kinds of images. A classy method supported by Feature discriminant analysis[1], which uses fisher linear discriminant algorithm (FLDA) is proposed in this paper. This approach has two steps to minimize this chaos and to maximize the performance of optical-infrared face recognition. In first step, extract all the common discriminant features from heterogeneous (infrared and optical) face images using FLDA. In second step, k-Nearest Neighbors (k-NN) algorithm is used on the result to conclude whether they match or not. To show that the algorithm works better than the existing ones, experiments are conducted on optical and infrared datasets.