Interactive image segmentation based on superpixel grouping for mobile devices with touchscreen

This paper proposes a novel method for semi-supervised image segmentation that is particularly targeted for interaction on mobile devices with touchscreen. In order to extract an object from a complicated scene with minimal user input, superpixels are first grouped into overlapping regions based on their visual similarity and the groups belonging to the object are then selected via user scribbles. By moving the user interaction to the end of the whole process, users' idle time is minimized hence an engaging user experience is achieved. The proposed method can effortlessly handle imprecise and inaccurate scribbles and is inherently suitable for touchscreen devices since it eliminates the necessity of a separate brush for marking the background as majority of state-of-the-art methods do. A novel fine-tuning method is also proposed where both foreground and background corrections are possible without entailing the user to change the brush. Experimental results prove that successful results are achieved with a slick and pleasant user experience.