Title: Differential Morphological Decomposition Segmentation: A Multi-Scale Object Based Image Description
Authors: GUEGUEN LIONELSOILLE PierrePESARESI Martino
Citation: Pattern Recognition (ICPR), 2010 20th International Conference on - ISBN: 978-1-4244-7542-1 p. 938-941
Publisher: IEEE Computer Society
Publication Year: 2010
JRC N°: JRC56701
URI: http://www.icpr2010.org/
http://publications.jrc.ec.europa.eu/repository/handle/JRC56701
DOI: 10.1109/ICPR.2010.235
Type: Contributions to Conferences
Abstract: In this paper, we propose a novel approach for breaking up an image into multi-scale overlapping objects. The image is decomposed by granulometry or differential morphological pyramid, resulting in a discrete scale-space representation. Then, the scale-space transform is segmented by a region based method. Projecting the obtained scale-space partition into space constitutes the disintegrated image representation, which enables a multi-scale object based image description.
JRC Institute:Institute for the Protection and Security of the Citizen

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.