An illumination invariant skin-color model for face detection

Face detection is an important step towards a fully automatic face recognition system. Among existing techniques in the literature, methods based on skin-color information have shown computational effectiveness as well as robustness in terms of rotation, scaling and partial occlusion. However, due to color variations resulted from illumination changes, many color-based techniques have yet to demonstrate a stable state of performance. In this paper, we present an illumination invariant color space model to address the color variation issue. The proposed method is evaluated both in terms of skin-color detection and face detection performances. Our empirical experiments evidenced both effectiveness and usefulness of the proposed method.

I. Introduction

IN future-generation mobile communication systems, the demand for multimedia streaming services is expected to increase dramatically. To meet the demand, Multimedia Broadcast/Multicast Service (MBMS) was proposed to enhance the bandwidth efficiency of multimedia services. MBMS is a unidirectional point-to-multipoint service that supports multimedia streams with possibly several resolutions from a single source to several destinations. By sharing the same data stream, multiple interested users can acquire the desired service simultaneously, thereby reducing the consumption of radio resources. In the 3rd Generation Partnership Project (3GPP) Release 6 [1], MBMS was standardized to increase system throughput by supporting multimedia services on a common channel for multiple recipients. Subsequently, in 3GPP Release 8 [2], MBMS single frequency network (MBSFN) was introduced, in which a cluster of multiple cells transmits the same data stream simultaneously with an identical modulation and coding scheme (MCS).