Authors: Walid Hizem
Keywords: Near-Infrared sensing, Landmark Detection, illumination suppression
Abstract: Illumination variation is one of the factors that has the greatest impact on the performance of a facial recognition system, especially in a mobility situation where the operator cannot control lighting. In this work, we present a new sensor that reduces ambient light ; the resulting image shows greater stability in relation to changes in ambient light. This sensor relies on a reduction of exposure time, so as to capture only a small quantity of ambient light, and during the exposure, a flash emitting a near-infrared light is activated. The resulting image is therefore dependent upon the luminance of the flash. A second characteristic of this sensor is the simultaneous production of a near-infrared image and a normal image acquired in ambient light. Besides this new sensor, we also aimed in among this and in view of a future implementation of our approach, we elaborated a method to detect landmarks in near-infrared images. This algorithm is based on the use of simple operators that has been implemented. The stability of the images in relation to the lighting changes allowed us to elaborate a simple method.
Using the landmarks detected and the edge image, we constructed a face-recognition algorithm, inspired by elastic graph matching, in order to build a model of the face. We compared the performance of our system to that of basic face-recognition algorithms, and achieved recognition levels equal to those of classic elastic graph matching.