MACHINE PERCEPTION AND ROBOTICS GROUP

Dept. of Robotics Science and Technology,
Chubu University

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.