Two-Level Image Segmentation Based on Region and Edge Integration

This paper introduces a two-level approach for image segmentation based on region and edge integration. Edges are first detected in the original image using a combination of operators for intensity gradient and texture discontinuities. To preserve the spatial coherence of the edges and their surrounding image regions, the detected edges are vectorized into connected line segments which serve as the basis for a constrained Delaunay triangulation. Segmentation is first performed on the triangulation using graph cuts. Our method favors segmentations that pass through more vectorized line segments. Finally, the obtained segmentation on the triangulation is projected onto the original image and region boundaries are refined to achieve pixel accuracy. Experimental results show that the two-level approach can achieve accurate edge localization, better spatial coherence and improved efficiency.