A Novel Skin Clustering Method for Face Detection

Nowadays, face detection plays an important role in many applications. Despite of the notable successes achieved in the past decades, making a tradeoff between computational complexity and detection efficiency is the main challenge. The ultimate goal is to develop fast detection algorithms with high practicalities. Among the proposed face detection algorithms, those based on skin color form an important category. However, varying illumination condition results in unstable clustering of the skin pixels. In this paper, we propose a novel skin color model, which can efficiently solve this problem. Experimental results demonstrate that utilizing the proposed model can accurately detect skin pixels under a wide range of illumination conditions and backgrounds