A new alpha matting for nature image

Alpha matting, aiming at extraction of foreground elements from a natural image by means of color and opacity (alpha) estimation, is one of the key techniques for image editing and film production. However, matting is inherently an ill-posed problem. Many matting approaches perform poorly with the complex natural images. A new matting algorithm is proposed. The proposed method involves expansion of known regions, selection of foreground and background colors for unknown pixels, determination of the confidence for these samples and optimization of the initial alpha by minimizing the object function. Finally, the experiments on the benchmark images are carried out and the results show that compared with some popular matting, the proposed method performs better.