Number of the records: 1
Illumination Invariant Unsupervised Segmenter
- 1.
SYSNO ASEP 0331807 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Illumination Invariant Unsupervised Segmenter Title Neřízený segmentační algoritmus invariantní ke změně osvětlení Author(s) Haindl, Michal (UTIA-B) RID, ORCID
Mikeš, Stanislav (UTIA-B) RID
Vácha, Pavel (UTIA-B) RIDSource Title Proceedings of the 16th International Conference on Image Processing, ICIP 2009. - Los Alamitos : IEEE, 2009 - ISSN 1522-4880 - ISBN 978-1-4244-5655-0 Pages s. 4025-4028 Number of pages 4 s. Action ICIP 2009 Event date 07.11.2009-11.11.2009 VEvent location Cairo Country EG - Egypt Event type WRD Language eng - English Country US - United States Keywords unsupervised image segmentation ; Illumination Invariants Subject RIV BD - Theory of Information R&D Projects 1M0572 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) GA102/08/0593 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10750506 - UTIA-B (2005-2011) Annotation A novel illumination invariant unsupervised multispectral texture segmentation method with unknown number of classes is presented. Multispectral texture mosaics are locally represented by illumination invariants derived from four directional causal multispectral Markovian models recursively evaluated for each pixel. Resulted parametric space is segmented using a Gaussian mixture model based unsupervised segmenter. The segmentation algorithm starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached. The performance of the presented method is extensively tested on the large illumination invariant benchmark from the Prague Segmentation Benchmark using 21 segmentation criteria and compares favourably with an alternative segmentation method. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2010
Number of the records: 1