Face Authentication Using Color and Depth Images

This paper presents a novel face authentication method integrating both 2D (color or intensity) and 3D range data, based on a low-cost system, capable of real-time acquisition of 3D and color images. Novel algorithms are proposed that exploit depth information to achieve robust face detection, localization and recognition under conditions of background clutter, occlusion, face pose alteration and harsh illumination. The well known embedded hidden markov model technique for face authentication is extended to handle depth maps. A method for the enrichment of face databases with synthetically generated views depicting various head poses and illumination conditions is developed. The performance of the proposed authentication scheme is tested thoroughly in terms of the receiver operating characteristic on two distinct face databases, recorded with the 3D acquisition system. Experimental results demonstrate significant gains resulting from the combined use of depth and color or intensity information.