Connected Morphological Attribute Filters on Distributed Memory Parallel Machines

Jan J. Kazemier, Georgios K. Ouzounis, Michael H. F. Wilkinson

OnderzoeksoutputAcademicpeer review

8 Citaten (Scopus)

Samenvatting

We present a new algorithm for attribute filtering of extremely large images, using a forest of modified max-trees, suitable for distributed memory parallel machines. First, max-trees of tiles of the image are computed, after which messages are exchanged to modify the topology of the trees and update attribute data, such that filtering the modified trees on each tile gives exactly the same results as filtering a regular max-tree of the entire image. On a cluster, a speed-up of up to 53x is obtained on 64, and up to 100x on 128 single CPU nodes. On a shared memory machine a peak speed-up of 50x on 64 cores was obtained.
Originele taal-2English
TitelMathematical Morphology and Its Applications to Signal and Image Processing
Subtitel13th International Symposium, ISMM 2017, Fontainebleau, France, May 15–17, 2017, Proceedings
RedacteurenJesús Angulo, Santiago Velasco-Forero, Fernand Meyer
Plaats van productieCham
UitgeverijSpringer International Publishing AG
Pagina's357-368
Aantal pagina's12
ISBN van elektronische versie978-3-319-57240-6
ISBN van geprinte versie978-3-319-57240-6
DOI's
StatusPublished - 2017
Evenement13th International Symposium, ISMM 2017 - Fontainebleau, France
Duur: 15-mei-201717-mei-2017

Publicatie series

NaamImage Processing, Computer Vision, Pattern Recognition, and Graphics
UitgeverijSpringer International Publishing
Volume10225

Conference

Conference13th International Symposium, ISMM 2017
Land/RegioFrance
StadFontainebleau
Periode15/05/201717/05/2017

Vingerafdruk

Duik in de onderzoeksthema's van 'Connected Morphological Attribute Filters on Distributed Memory Parallel Machines'. Samen vormen ze een unieke vingerafdruk.

Citeer dit