DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hyung-Soo Lee | - |
dc.contributor.author | Kim, D | - |
dc.date.accessioned | 2016-04-01T08:38:44Z | - |
dc.date.available | 2016-04-01T08:38:44Z | - |
dc.date.created | 2009-08-20 | - |
dc.date.issued | 2009-06 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.other | 2009-OAK-0000018061 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/28443 | - |
dc.description.abstract | The Active appearance model (AAM) is a well-known model that can represent a nonrigid object effectively. However, because it uses a fixed model of shape and appearance, the fitting result is often unsatisfactory when an input image deviates from the training images. To obtain more robust AAM fitting, we propose a tensor-based AAM that can handle a variety of subjects, poses, expressions, and illuminations in the tensor algebra framework. It consists of an image tensor and a model tensor. The image tensor is used to estimate image variations such as pose, expression, and illumination of the input image. Here, we introduce two different variation estimation approaches: discrete and continuous variation estimation. Then, the model tensor generates a variation-specific AAM from a tensor representation, using the estimation results. This process ensures more accurate fitting results. To validate the usefulness of the tensor-based AAM, we performed variation-robust face recognition using the tensor-based AAM fitting results. To do this, we propose indirect AAM feature transformation. Experimental results show that the tensor-based AAM with continuous variation estimation outperforms that with discrete variation estimation and conventional AAM in terms of the average fitting error and the face recognition rate. | - |
dc.description.statementofresponsibility | X | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.subject | Tensor algebra | - |
dc.subject | multilinear analysis | - |
dc.subject | AAM | - |
dc.subject | indirect AAM feature transformation | - |
dc.subject | variation-robust face recognition | - |
dc.subject | ACTIVE APPEARANCE MODELS | - |
dc.title | Tensor-Based AAM with Continuous Variation Estimation: Application to Variation-Robust Face Recognition | - |
dc.type | Article | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.identifier.doi | 10.1109/TPAMI.2008.286 | - |
dc.author.google | Lee, HS | - |
dc.author.google | Kim, D | - |
dc.relation.volume | 31 | - |
dc.relation.issue | 6 | - |
dc.relation.startpage | 1102 | - |
dc.relation.lastpage | 1116 | - |
dc.contributor.id | 10054411 | - |
dc.relation.journal | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.relation.index | SCI급, SCOPUS 등재논문 | - |
dc.relation.sci | SCI | - |
dc.collections.name | Journal Papers | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.31, no.6, pp.1102 - 1116 | - |
dc.identifier.wosid | 000265100000011 | - |
dc.date.tcdate | 2019-02-01 | - |
dc.citation.endPage | 1116 | - |
dc.citation.number | 6 | - |
dc.citation.startPage | 1102 | - |
dc.citation.title | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.volume | 31 | - |
dc.contributor.affiliatedAuthor | Kim, D | - |
dc.identifier.scopusid | 2-s2.0-65549084966 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.wostc | 28 | - |
dc.type.docType | Article | - |
dc.subject.keywordAuthor | Tensor algebra | - |
dc.subject.keywordAuthor | multilinear analysis | - |
dc.subject.keywordAuthor | AAM | - |
dc.subject.keywordAuthor | indirect AAM feature transformation | - |
dc.subject.keywordAuthor | variation-robust face recognition | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
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.