Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

We present a novel approach to image segmentation using iterated Graph Cuts based on multi-scale smoothing. We compute the prior probability obtained by the likelihood from a color histogram and a distance transform using the segmentation results from graph cuts in the previous process, and set the probability as the t-link of the graph for the next process. The proposed method can segment the regions of an object with a stepwise process from global to local segmentation by iterating the graph-cuts process with Gaussian smoothing using different values for the standard deviation. We demonstrate that we can obtain 4.7% better segmentation than that with the conventional approach.