A weakly supervised geodesic level set framework for interactive image segmentation

Abstract

Interactive image segmentation is growingly useful for selecting objects of interest in images, facilitating spatially localized media manipulation especially on touch screen devices. We present a robust and efficient approach for segmenting image with less and intuitive user interaction. Our approach combines geodesic distance information with the flexibility of level set methods in energy minimization, leveraging the complementary strengths of each to promote accurate boundary placement and strong region connectivity while requiring less user interaction. We harness weakly supervised segment annotation to maximize the user-provided prior knowledge. This leads to a seed generation algorithm which enables image object segmentation without user-provided background seeds. We demonstrate that our approach is less sensitive to seed placement and better at edge localization, whilst requiring less user interaction, compared with the state-of-the-art methods.