A biometric approach towards recognizing face in various dark illuminations

Face Recognition is a computerized biometric modality which automatically identifies an individual's face for the purpose of recognition. The ability to recognize human faces can be categorized under two senses, the former is the biometric identification and the later is the visual perception. The biometric identification can be done by obtaining a person's image and matching the same against the set of known images whereas the later is how the system percepts the familiar faces and recognize them. This paper presents such a biometric identification of the frontal static face image subjected in various dark illuminations. Face Recognition Biometric Systems automatically recognize the individuals based on their physiological characteristics. The research on such areas has been conducted for more than thirty years, but still more processes and better techniques for biometric facial extraction and recognition are required. This paper presents a framework on such issue by integrating the preprocessing method, local feature extractor and a recognizer for face recognition. An automatic FRBS has been developed that uses 1) Local Binary Pattern and 2) k — Nearest Neighbor classifier. Experimental results based on the Yale — B database show that the use of LBP and k-NN is able to improve the face recognition performance in various dark illuminations.