Parallel Laplacian Edge Detection Performance Analysis on Green Cluster Architecture
The current trend of computer hardware declining and the speed of personal computer increasing had lead to opportunity of parallel programming. This paper presents the implementation of parallel Laplacian edge detection on cluster of four used personal computers. The algorithm was developed using C# language and had utilized the Message Passing Interface (MPI) library for parallel implementation. Comparison between sequential versus parallel implementation had been made based on sequential time taken for varies of images sizes. Results show significant time improvement as well as performance efficiency earned using parallel computing platform focusing on image processing Laplacian edge detection algorithm.
KeywordsParallel computing Image processing Edge Detection Cluster
Unable to display preview. Download preview PDF.
- 1.Abbas, A.: Grid Computing: A practical Guide to Technology and Applications. Charles River Media, Hingham (2003)Google Scholar
- 5.Wilkinson, B., Allen, M.: Parallel Programming Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice Hall, Englewood Cliffs (2005)Google Scholar
- 6.Johnson, A.L.: A Parallel Algorithm for Fast Edge Detection on the Graphics Processing Unit, Thesis for Honors in Computer Science, The Faculty of the Department of Computer Science Washington and Lee University (2010), http://www.gpucomputing.net/?q=node/554
- 7.Han, C.T., Hong, J.T.K., Akma, F., Shamsir, M.S.: BirgHPC: Creating Instant Computing Clusters for Bioinformatics and Molecular Dynamics. Oxford University Press, Oxford (2011)Google Scholar
- 8.Haron, N., Amir, R., Aziz, I.A., Jung, L.T., Shukri, S.R.: Parallelization of Edge Detection Algorithm using MPI on Beowulf Cluster. Innovation Science and Software Engineering (2010)Google Scholar
- 9.Zhang, N., Wang, J., Chen, Y.: Image Parallel Processing Based on GPU. In: 2nd International Conference on Advanced Computer Control (ICACC), pp. 367–370 (2010)Google Scholar
- 10.Osman, M.A., Mohamad, M.Y., Abdullah, R.: Parallelizing en edge detection algorithm for image recognition to classify paddy and weeds leaf on Sun Fire Cluster System. In: Proceedings of the 7th WSEAS International Conference on Software Engineering, Parallel and Distributed Systems, World Scientific and Engineering Academy and Society, pp. 56–60 (2008)Google Scholar
- 11.Galizia, A., Clematis, A., Viti, F., Milanesi, L.: A dynamic parallel approach to recognize tubular breast cancer for Tissue Micro Array (TMA) image building. In: 2010, 18th Euromico Conference on Parallel, Distributed and Network-based Processing, pp. 403–410 (2010)Google Scholar
- 12.Xiao, Y., Chen, Z., Zhang, L.: Accelerated CT Reconstruction Using GPU SIMD Parallel Computing with Bilinear Wrapping Method. In: The 1st International Conference on Information Science and Engineering (ICISE 2009), pp. 95–98 (2009)Google Scholar