SuperSelect: An Interactive Superpixel-Based Segmentation Method for Touch Displays

Korinke, Christoph and Stratmann, Tim Claudius and Laue, Tim and Boll, Susanne
Proceedings of the 2016 ACM on Multimedia Conference
We present the concept of an interactive image segmentation method, which allows a fast and precise extraction of foreground objects from natural images. The method is especially suited for mobile, touch-based devices. The approach combines automatic image segmentation with interactive refinement. In a first step, the user extracts an object using the first stage of the GrabCut algorithm. Any errors in the resulting segmentation can then be corrected via a novel correction step in which the underlying image is over-segmented into superpixels using the SLIC algorithm. The user can select individual superpixels in order to adjust the image segmentation. This image segmentation method is implemented as a full working demo on a Microsoft Surface Pro 3.
MM '16