Fast adaptive matting based on iterative solution

摘要

In this paper, we introduce a fast adaptive matting method, where the adaptive matting is carried with a parallelized iterative method, instead of a closed-form solution. As one of its applications, we also incorporate a saliency detection into the adaptive matting, which provides an automated way of extracting salient objects from a bundle of images. This is useful for various problems including object based retrieval, classification and so on. Numerical experiments and visual comparison with the publicly available sample images show the effectiveness of the proposed method.