Parallel Implementation of Morphological Image Processing Algorithm for GPGPU

DOI

10.2991/racs-15.2016.22How to use a DOI?

Keywords

Morphology, Errosion, Dilation, GPGPU, CUDA , Parallel Programming

Abstract

Morphological Image Processing also known as Morphology is used as a tool for extracting image components that are useful in the representation and description of region such as shape, boundaries, skeleton etc. Morphological techniques are also used for pre- and post-processing of given data for morphological filtering, noise removal, thinning, pruning and edge detection. In this paper a parallel implementation of morphological algorithm for GPGPU is presented. The presented implementation identifies the unbroken pills and remove noise from the image in parallel. The result obtained shows the speedup of almost 85 for erosion operation and around 70 for dilation operations on GPGPU.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kamran Shamim
AU  - Muhammad Ismail
AU  - Saad Khan
PY  - 2015/11
DA  - 2015/11
TI  - Parallel Implementation of Morphological Image Processing Algorithm for GPGPU
BT  - Proceedings of the 2015 International Conference on Recent Advances in Computer Systems
PB  - Atlantis Press
SP  - 130
EP  - 134
SN  - 2352-538X
UR  - https://doi.org/10.2991/racs-15.2016.22
DO  - 10.2991/racs-15.2016.22
ID  - Shamim2015/11
ER  -