Accelerating 'Intelligent Scissors' Using Slimmed Graphs

In this paper, we describe an acceleration technique for the semi-automatic image segmentation algorithm, intelligent scissors. Using intelligent scissors, user can accurately and interactively extract the object from the digitized image. However, the original algorithm suffers from slow performance when large images are treated. In practice, pixels within the non-edge regions are seldom involved in the determination of boundaries (segmentation curves). If these pixels are removed before boundary determination, the performance of intelligent scissors can be sped up. We generate a slimmed graph to achieve such goal. Significant improvement in response time is resulted using the slimmed graph.