Title: Concurrent computation of connected pattern spectra for very large image information mining
Authors: WILKINSON MichaelMOSCHINI UgoOUZOUNIS GEORGIOSPESARESI Martino
Citation: Proceedings of ESA-EUSC-JRC 8th Conference on Image Information Mining p. 21-25
Publisher: Publications Office of the European Union
Publication Year: 2012
JRC N°: JRC73691
ISBN: 978-92-79-26419-1
ISSN: 1831-9424
URI: http://bookshop.europa.eu/en/esa-eusc-jrc-8th-conference-on-image-information-mining-pbLBNA25514/
http://publications.jrc.ec.europa.eu/repository/handle/JRC73691
DOI: 10.2788/49465
Type: Articles in periodicals and books
Abstract: This paper presents a shared-memory parallel algorithm for computing connected pattern spectra from the Max-Tree structure. The pattern spectrum is an aggregated feature space derived directly from the tree-based image representation and is a powerful tool for interactive image information mining. An application example along with timings on experiments with Gpixel input imagery are given. On images of 0.87 to 1.29 Gpixel, wall-clock times of 8.13 to 15.17s, and a speed up of between 27.5 and 33.5 were achieved on a single 2U 64 core rack server.
JRC Directorate:Space, Security and Migration

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.