DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hui-Jin | - |
dc.contributor.author | Hong, Ki-Sang | - |
dc.date.accessioned | 2018-07-17T10:43:03Z | - |
dc.date.available | 2018-07-17T10:43:03Z | - |
dc.date.created | 2017-09-14 | - |
dc.date.issued | 2017-08 | - |
dc.identifier.issn | 1433-7541 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/92060 | - |
dc.description.abstract | We propose a new class-specific image representation for image classification using multiple region detectors. The new representation is designed to solve the problem of increasing variation in object location and size within images of a class, for which traditional spatial pyramid matching shows limited classification accuracy. We propose a new region-division method that divides the image region into two class-specific regions, called class-specific region-of-interest (C-ROI) and focal region (FR). Using multiple region detectors and appropriate mixing of their responses avoids the problem of selecting a region detector that gives the best classification accuracy for a given image class, and thereby yields better results than using only one region detector. Several scale-invariant region detectors are used to obtain C-ROI and FR by considering their importance over a given image class. In experiments using several well-known datasets, the proposed method improved the accuracy and achieved results that were better than or comparable to those achieved by the related methods. | - |
dc.language | English | - |
dc.publisher | SPRINGER | - |
dc.relation.isPartOf | PATTERN ANALYSIS AND APPLICATIONS | - |
dc.title | Class-specific image representation for image classification using multiple scale-invariant region detectors | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s10044-016-0529-z | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | PATTERN ANALYSIS AND APPLICATIONS, v.20, no.3, pp.717 - 732 | - |
dc.identifier.wosid | 000405607000007 | - |
dc.date.tcdate | 2018-03-23 | - |
dc.citation.endPage | 732 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 717 | - |
dc.citation.title | PATTERN ANALYSIS AND APPLICATIONS | - |
dc.citation.volume | 20 | - |
dc.contributor.affiliatedAuthor | Hong, Ki-Sang | - |
dc.identifier.scopusid | 2-s2.0-84954509097 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | MATRIX FACTORIZATION | - |
dc.subject.keywordPlus | PICTORIAL STRUCTURES | - |
dc.subject.keywordPlus | RECOGNITION | - |
dc.subject.keywordPlus | FEATURES | - |
dc.subject.keywordAuthor | Image representation | - |
dc.subject.keywordAuthor | Class-specific region-of-interest (C-ROI) | - |
dc.subject.keywordAuthor | Focal region (FR) | - |
dc.subject.keywordAuthor | Classification accuracy | - |
dc.subject.keywordAuthor | Bag-of-words | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
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.