One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. This input bounding box facilitates the estimation of the appearance models of the foreground and background, with which a binary labeling is finally performed to achieve a refined segmentation. One major issue of the existing algorithms for such interactive image segmentation, including the widely used GrabCut, is their preference of an input bounding box that tightly encloses the foreground object. This increases the annotation burden, and prevents these algorithms from utilizing automatically detected bounding boxes. In this paper, we develop a new LooseCut algorithm that can handle cases where the input bounding box only loosely covers the foreground object. We propose a new Markov Random Fields (MRF) based segmentation energy function, including a global energy term to better distinguish the foreground and background, and a high-order energy term to encourage the label spatial consistency. This MRF energy function is then minimized by an iterated max-flow algorithm. In the experiments, we evaluate LooseCut in three publicly-available image datasets, and compare its performance against several state-of-the-art interactive image segmentation algorithms. We also show that LooseCut can be used for enhancing the performance of unsupervised video segmentation and image-based saliency detection.
View on arXiv