DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hanjoo Cho, | - |
dc.contributor.author | Suk-Ju Kang | - |
dc.contributor.author | Sung In Cho | - |
dc.contributor.author | Kim, YH | - |
dc.date.accessioned | 2016-04-01T07:37:43Z | - |
dc.date.available | 2016-04-01T07:37:43Z | - |
dc.date.created | 2016-03-08 | - |
dc.date.issued | 2014-11 | - |
dc.identifier.issn | 0098-3063 | - |
dc.identifier.other | 2014-OAK-0000032177 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/26707 | - |
dc.description.abstract | This paper proposes a new approach to mean-shift-based image segmentation that uses a non-iterative process to determine the maxima of the underlying density, which are called modes. To identify the mode, the proposed approach performs a mean-shift process on each pixel only once, and uses the resulting mean-shift vectors to construct links for the pairs of pixels, instead of iteratively performing the mean-shift process. Then, it groups the pixels of the same mode, connected through the links, into the same cluster. Although the proposed approach performs the mean-shift process only once, it provides comparable segmentation quality to the conventional approaches. In experiments using benchmark images, the processing time was reduced to a quarter, while probabilistic rand index and segmentation covering were well maintained; they were degraded by only 0.38% and 1.87%, respectively. Furthermore, the proposed algorithm improves the locality of the required data and compute-intensity of the algorithm, which are important factors for utilizing the GPU effectively. The proposed algorithm, when implemented on a GPU, improved the processing speed by over 75 times compared to implementation on a CPU, while the conventional approach was accelerated by about 15 times(1). | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | IEEE Transactions on Consumer Electronics | - |
dc.relation.isPartOf | IEEE Transactions on Consumer Electronics | - |
dc.title | Image segmentation using linked mean-shift vectors and its implementation on GPU | - |
dc.type | Article | - |
dc.contributor.college | 전자전기공학과 | - |
dc.identifier.doi | 10.1109/TCE.2014.7027348 | - |
dc.author.google | Hanjoo Cho | - |
dc.author.google | Suk-Ju Kang | - |
dc.author.google | Sung In Cho | - |
dc.author.google | Young Hwan Kim | - |
dc.relation.volume | 60 | - |
dc.relation.issue | 4 | - |
dc.relation.startpage | 719 | - |
dc.relation.lastpage | 727 | - |
dc.contributor.id | 10176127 | - |
dc.relation.journal | IEEE Transactions on Consumer Electronics | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Consumer Electronics, v.60, no.4, pp.719 - 727 | - |
dc.identifier.wosid | 000349624500023 | - |
dc.date.tcdate | 2019-02-01 | - |
dc.citation.endPage | 727 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 719 | - |
dc.citation.title | IEEE Transactions on Consumer Electronics | - |
dc.citation.volume | 60 | - |
dc.contributor.affiliatedAuthor | Kim, YH | - |
dc.identifier.scopusid | 2-s2.0-84923767001 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 7 | - |
dc.description.scptc | 6 | * |
dc.date.scptcdate | 2018-05-121 | * |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Mean-shift algorithm | - |
dc.subject.keywordAuthor | parallel processing | - |
dc.subject.keywordAuthor | image segmentation | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.