Abstract

We address the problem of having insufficient labels in an interac- tive image segmentation framework, for which most current methods would fail without further user interaction. To minimize user interaction, we use the appear- ance and boundary information synergistically. Speci fically, we perform distribu- tion propagation on the image graph constructed with color features to derive an initial estimate of the segment labels. Following that, we include automatically estimated segment distributions at “critical pixels ” with uncertain labels to im- prove the segmentation performance. Such estimation is realized by incorporat- ing boundary information using a non-parametric Dirichlet process for modeling diffusion signatures derived from the salient boundaries. Our main contribution is fusion of image appearance with probabilistic modeling of boundary informa- tion to segment the whole-object with a limited number of labeled pixels. Our proposed framework is extensively tested on a standard dataset, and is shown to achieve promising results both quantitatively and qualitatively.