Korinke, Christoph and Stratmann, Tim Claudius and Laue, Tim and Boll, Susanne (2016) SuperSelect - an interactive superpixel-based segmentation method for touch displays. In: MM'16 proceedings of the 2016 ACM Conference & Workshops on Multimedia. ACM, Association for Computing Machinery, New York, NY, pp. 717-719. ISBN 978-1-4503-3603-1

Full text not available from this repository. (Request a copy)

Abstract

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.

Item Type:	Book Section
Uncontrolled Keywords:	human computer interaction, OFFIS, segmentation, UNI, user interface
Divisions:	School of Computing Science, Business Administration, Economics and Law > Department of Computing Science
Date Deposited:	06 Apr 2017 09:35
Last Modified:	06 Apr 2017 10:50
URI:	https://oops.uni-oldenburg.de/id/eprint/3107
URN:	urn:nbn:de:gbv:715-oops-31889
DOI:
Nutzungslizenz:

Actions (login required)

View Item