DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Jong Hee | ko |
dc.contributor.author | Eun, Hyun Jun | ko |
dc.contributor.author | Kim, Chang Ick | ko |
dc.date.accessioned | 2016-04-18T05:01:17Z | - |
dc.date.available | 2016-04-18T05:01:17Z | - |
dc.date.created | 2015-11-23 | - |
dc.date.created | 2015-11-23 | - |
dc.date.issued | 2015-09-18 | - |
dc.identifier.citation | 16th Pacific-Rim Conference on Multimedia, PCM 2015, pp.506 - 515 | - |
dc.identifier.uri | http://hdl.handle.net/10203/204350 | - |
dc.description.abstract | Recently no-reference image quality assessment (NR-IQA) methods take advantages of machine learning techniques. However, machine learning approaches need a number of human scored images and cause database dependency. In this paper, we propose a simple NR-IQA method that can estimate quality of distorted images without learning, producing comparable performance to learning based approaches. We employ singular value decomposition (SVD) since we have observed that singular values are commonly affected by various distortions. In detail, a decreasing rate of singular values is highly correlated to a degree of distortions regardless of their type. From the observation, our approach utilizes the decreasing rate of singular values to model a simple and reliable NR-IQA method. Experimental results show that the proposed method has reasonably high correlation to human scores. And the proposed method can secure simplicity and database independence. | - |
dc.language | English | - |
dc.publisher | Springer Verlag | - |
dc.title | No-reference Image Quality Assessment based on Singular Value Decomposition without Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000366085100051 | - |
dc.identifier.scopusid | 2-s2.0-84951871309 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 506 | - |
dc.citation.endingpage | 515 | - |
dc.citation.publicationname | 16th Pacific-Rim Conference on Multimedia, PCM 2015 | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | Oryong Hall, Gwangju Institute of Science and Technology (GIST) | - |
dc.identifier.doi | 10.1007/978-3-319-24078-7_51 | - |
dc.contributor.localauthor | Kim, Chang Ick | - |
dc.contributor.nonIdAuthor | Kim, Jong Hee | - |
dc.contributor.nonIdAuthor | Eun, Hyun Jun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.