Research on a skin color detection algorithm based on hybrid color model

Skin-color detection is an important subject in computer vision research. The skin-color detection algorithm based on hybrid color model is proposed in this paper. Firstly, the hybrid skin color eigenvectors are built according to the analysis of various color models, and then the analysis method of principal component is applied to the linear transformation of hybrid color eigenvectors. Several kinds of new skin color spaces are acquired by designing various selection schemes of principal components. The elliptical boundary model classifier is designed according to distribution of new skin color spaces. The experimental results have indicated that this algorithm can effectively fulfill the skin-color detection for images captured under different environmental condition and the performance of the skin color segmentation is significantly improved.