Unsupervised Segmentation for Digital Matting

Digital matting consists in extracting a foreground element from a background image. Besides the image, usual matting methods need to be initialized with two disjoint regions : the set of foreground only pixels and the set of background only pixels. Pixels belonging to none of these two regions are considered as an undetermined blending between the foreground and the background. Here, one has to estimate the opacity (alpha channel) and the original foreground and background colors that have been blended. Initialization is a crucial step for these methods, and usually one has to specify accurate initial regions, leaving undetermined as few pixels as possible. This is especially true for recent methods that use local models. This paper proposes an unsupervised segmentation scheme that initializes any matting method by extracting the foreground and background regions from just a small subset of them. Standard statistical models are used for the foreground and background regions, while a specific one is design for the blended region. The three regions are determined simultaneously using a level set method implementation. Results show that our method works in various conditions, simplifying as much as possible the user’s job. Even when a sufficient but non perfect initialization is given to the matting algorithm, it turns out that using our method as a first step significantly improves the final matting result.