Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers
This paper parallelizes the spatial pyramid match kernel (SPK) implementation. SPK is one of the most usable kernel methods, along with support vector machine classifier, with high accuracy in object recognition. MATLAB parallel computing toolbox has been used to parallelize SPK. In this implementat...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Shahrood University of Technology
2019-03-01
|
Series: | Journal of Artificial Intelligence and Data Mining |
Subjects: | |
Online Access: | http://jad.shahroodut.ac.ir/article_1159_169528cafc621bc8706b75fb43a5d686.pdf |
id |
doaj-a9c94d9e7aac49d19741500f6b494e9e |
---|---|
record_format |
Article |
spelling |
doaj-a9c94d9e7aac49d19741500f6b494e9e2020-11-24T21:00:18ZengShahrood University of TechnologyJournal of Artificial Intelligence and Data Mining2322-52112322-44442019-03-01719710810.22044/jadm.2017.4152.15031159Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of ComputersA. Asilian Bidgoli0H. Ebrahimpour-Komle1M. Askari2Seyed J. Mousavirad31) Department of Computer Engineering, University of Kashan, Kashan, Iran 2)Instructor, Faculty of Elecronic and Computer Engineering Pooyesh Higher Education Institute Qom, IranDepartment of Computer Engineering, University of Kashan, Kashan, IranDepartment of Computer Engineering, University of Kashan, Kashan, IranDepartment of Computer Engineering, University of Kashan, Kashan, IranThis paper parallelizes the spatial pyramid match kernel (SPK) implementation. SPK is one of the most usable kernel methods, along with support vector machine classifier, with high accuracy in object recognition. MATLAB parallel computing toolbox has been used to parallelize SPK. In this implementation, MATLAB Message Passing Interface (MPI) functions and features included in the toolbox help us obtain good performance by two schemes of task-parallelization and dataparallelization models. Parallel SPK algorithm ran over a cluster of computers and achieved less run time. A speedup value equal to 13 is obtained for a configuration with up to 5 Quad processors.http://jad.shahroodut.ac.ir/article_1159_169528cafc621bc8706b75fb43a5d686.pdfObject recognitionSpatial pyramid match kernelParallel computingCluster of computersSupport Vector Machine |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
A. Asilian Bidgoli H. Ebrahimpour-Komle M. Askari Seyed J. Mousavirad |
spellingShingle |
A. Asilian Bidgoli H. Ebrahimpour-Komle M. Askari Seyed J. Mousavirad Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers Journal of Artificial Intelligence and Data Mining Object recognition Spatial pyramid match kernel Parallel computing Cluster of computers Support Vector Machine |
author_facet |
A. Asilian Bidgoli H. Ebrahimpour-Komle M. Askari Seyed J. Mousavirad |
author_sort |
A. Asilian Bidgoli |
title |
Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers |
title_short |
Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers |
title_full |
Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers |
title_fullStr |
Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers |
title_full_unstemmed |
Parallel Spatial Pyramid Match Kernel Algorithm for Object Recognition using a Cluster of Computers |
title_sort |
parallel spatial pyramid match kernel algorithm for object recognition using a cluster of computers |
publisher |
Shahrood University of Technology |
series |
Journal of Artificial Intelligence and Data Mining |
issn |
2322-5211 2322-4444 |
publishDate |
2019-03-01 |
description |
This paper parallelizes the spatial pyramid match kernel (SPK) implementation. SPK is one of the most usable kernel methods, along with support vector machine classifier, with high accuracy in object recognition. MATLAB parallel computing toolbox has been used to parallelize SPK. In this implementation, MATLAB Message Passing Interface (MPI) functions and features included in the toolbox help us obtain good performance by two schemes of task-parallelization and dataparallelization models. Parallel SPK algorithm ran over a cluster of computers and achieved less run time. A speedup value equal to 13 is obtained for a configuration with up to 5 Quad processors. |
topic |
Object recognition Spatial pyramid match kernel Parallel computing Cluster of computers Support Vector Machine |
url |
http://jad.shahroodut.ac.ir/article_1159_169528cafc621bc8706b75fb43a5d686.pdf |
work_keys_str_mv |
AT aasilianbidgoli parallelspatialpyramidmatchkernelalgorithmforobjectrecognitionusingaclusterofcomputers AT hebrahimpourkomle parallelspatialpyramidmatchkernelalgorithmforobjectrecognitionusingaclusterofcomputers AT maskari parallelspatialpyramidmatchkernelalgorithmforobjectrecognitionusingaclusterofcomputers AT seyedjmousavirad parallelspatialpyramidmatchkernelalgorithmforobjectrecognitionusingaclusterofcomputers |
_version_ |
1716780263453753344 |