Perception based alpha estimation in natural image matting

An algorithm is presented for effectively, estimating alpha based on perceptual color space in natural image matting. After the foreground and background color components of given observed unknown pixel are estimated, our alpha estimating algorithm separates intensity and chroma information of RGB color, i.e, alpha is decomposed into intensity alpha and chroma alpha. Then we take the weighted mean over these two alpha values as the final alpha. Matte results and the comparison with the other alpha estimating algorithms in natural image matting are given in this paper.