Region-Based Nonparametric Model for Interactive Image Segmentation

In this paper, we present a novel framework for interactive segmentation problems. It integrates a nonparametric model into the Conditional Random Field (CRF) framework, which can effectively combine high-level features with low-level features to represent image information. In the nonparametric model, multiple region layers are used to estimate data likelihood terms to overcome the bad regions generated by unsupervised methods. The likelihood values of each layer are calculated separately to reduce the computational cost. In addition, we analyze that the pixel layer has little effect on data estimation, so we remove it to further reduce the complexity of the algorithm. We employ the label consistency between pixels and their corresponding regions in smooth term estimation, which can be regard as a higher order potential for pixels. The data term and the smooth term are then performed together in Conditional Random Fields (CRFs) as a fine-tuning of the results. Experimental results show that the proposed method can segment images efficiently and accurately with fewer user inputs.