Robust interactive image segmentation via iterative refinement

Image segmentation with user inputs gets more and more popular in recent years and always performs better compared with automatic methods. However, existing interactive image segmentation methods still might fail if the image contains messy textures, or the user inputs are sparse or at inappropriate locations. In this paper, we propose a novel iterative refinement framework which leads to robust segmentation performance even with sparse and improper input strokes. Specifically, a geodesic distance based energy is introduced and combined with convex active contour model, and an iterative seeds refinement technique is put forward to handle the sparse input problem. Extensive experiments using real world images, and segmentation benchmark dataset show that our proposed method has superior performance compared with representative state-of-the-art methods.