A Three-Stage Matting Method

Abstract

Natural image matting is an important image processing task. How to leverage the advantages of both sampling matting and propagation matting is a challenge issue. In this paper, we propose a novel sampling-propagation matting method. First, in an overall framework, we propose a three-stage method for sampling-propagation matting, in which the sampling matting stage and propagation matting stage are bridged by a new stage (stage 2). Second, in the sampling matting stage (stage 1), a new gradient sampling matting is presented to cover more diversified samples, and a new equation is proposed to calculate the impact of sample-pair overlap. Third, in bridge stage (stage 2), we propose a judgment criterion to distinguish each pixel of matte after stage 1. For pixels that fail to meet the criterion, we propose an automatic labeling method. Fourth, in the propagation stage (stage 3), we discriminatingly process non-labeled pixels and labeled pixels with separate weight coefficients. The non-labeled pixels are smoothed by propagation, and the labeled pixels are solved by propagation matting. Finally, the proposed method is compared with other methods on public available benchmark. The results show that our method outperforms many other methods and achieves a good ranking.