Concurrent computation of connected pattern spectra for very large image information mining
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.
WILKINSON Michael;
MOSCHINI Ugo;
OUZOUNIS Georgios;
PESARESI Martino;
2013-08-12
Publications Office of the European Union
JRC73691
978-92-79-26419-1,
1831-9424,
http://bookshop.europa.eu/en/esa-eusc-jrc-8th-conference-on-image-information-mining-pbLBNA25514/,
https://publications.jrc.ec.europa.eu/repository/handle/JRC73691,
10.2788/49465,
Additional supporting files
| File name | Description | File type | |
|---|
