Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Measuring and evaluating the compactness of superpixels

: Schick, Alexander; Fischer, M.; Stiefelhagen, Rainer

Postprint urn:nbn:de:0011-n-2279306 (1.8 MByte PDF)
MD5 Fingerprint: 8a4f2ec8d73538648e561b189b22e560
© 2012 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 12.2.2013

Institute of Electrical and Electronics Engineers -IEEE-; International Association for Pattern Recognition -IAPR-; IEEE Computer Society:
21st International Conference on Pattern Recognition, ICPR 2012. Vol.2 : Tsukuba, Japan, 11 - 15 November 2012
Los Alamitos, Calif.: IEEE Computer Society Press, 2012
ISBN: 978-1-4673-2216-4
ISBN: 978-4-9906441-0-9
International Conference on Pattern Recognition (ICPR) <21, 2012, Tsukuba>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Superpixel segmentation has become a popular preprocessing step in computer vision with a great variety of existing algorithms. Almost all algorithms claim to compute compact superpixels, but no one showed how to measure compactness and no one investigated the implications. In this paper, we propose a novel metric to measure superpixel compactness. With this metric, we show that there is a trade-off between compactness and boundary recall. In addition, we propose an algorithm that allows to precicely control this trade-off and that outperforms the current state-of-the-art. As a demonstration, we show the importance of considering compactness with the help of an example application.