Improved Algorithm on Digital Image Matting

Digital image matting is to extract the foreground objects with arbitrary shapes from an image. This paper proposes optimal and developed algorithms for image matting in the efficiency and user interaction, without solving an optimization problem, but transforms the optimization problem into the minimum weighted distance issues based on dynamic programming. This method begins from segmenting regions by a user with two different colors to identify the foreground and background, and then the algorithm will be automatically propagated according to sampling points. Thus we can calculate the alpha channel of the overall image. This method is much faster than the existing approaches of comparable quality.