Robust natural image matting approach based on strokes
Yue Wu, Fazhi He, Dengyi Zhang, Lingyun Wei, Zhiyong Huang · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
Image matting is a process of extracting a foreground object from a complex background. This paper proposes a robust interactive image matting approach. The method requires only a few user interactions in the form of drawing a rectangle and a few strokes to indicate background and foreground. We consider the constraints of accuracy and continuity for the estimated alpha values together to find the optimal matte by iteratively energy optimization. Different from existing sampling-based natural image matting methods which use only intensity information from statistic sampling of known foreground and background pixels to estimate the unknown pixels. We consider the distribution of the known pixels in color, texture and spatial spaces, and build a more robust statistical model. At each iteration, the statistical model is updated according to previous results of matting. Furthermore an accuracy function of sampling is proposed. These manipulations make the sampling of foreground and background pixels more accurate and thus improve the performance of the matting processing. Experiments show that compared with previous approaches, our method is more efficient to extract high quality matte for texture-rich images and difficult images in which foreground and background have very similar colors, while requiring a surprising small amount of user interaction.