Adaptive skin detection system on DTV

We propose a skin detection algorithmic system for a consequent video sequence which is fast, reliable and applicable. We adopted YCbCr color space, which is competitive in extracting the skin region from digital television (DTV) related images. Based on a Gaussian color probability density, and the assumption that the color is homogeneous in a continuous scene, we adopted a face detection method to extract the skin space locus from one scene to another scene so that adequate skin space is renewed by face detection. We target this algorithm for DTV applications. As speed of the algorithm is crucial in a real time system, we adopted motion estimation (ME) to find the exact frames which need the skin space to be updated due to scene change or skin color change. The core of this work is a practical adaptive skin space search algorithm, meanwhile reducing distortion from various image sources. Our adaptive skin locus update (ASLU) algorithm shows outstanding result comparing to static skin region detection algorithms.