Show simple item record

dc.contributor.authorNarwaria, M.en_US
dc.contributor.authorLin, W.en_US
dc.contributor.authorÇetin, A. Enisen_US
dc.date.accessioned2016-02-08T09:49:13Z
dc.date.available2016-02-08T09:49:13Z
dc.date.issued2011-07-19en_US
dc.identifier.issn0031-3203
dc.identifier.urihttp://hdl.handle.net/11693/21646
dc.description.abstractMeasurement of image quality is of fundamental importance to numerous image and video processing applications. Objective image quality assessment (IQA) is a two-stage process comprising of the following: (a) extraction of important information and discarding the redundant one, (b) pooling the detected features using appropriate weights. These two stages are not easy to tackle due to the complex nature of the human visual system (HVS). In this paper, we first investigate image features based on two-dimensional (2D) mel-cepstrum for the purpose of IQA. It is shown that these features are effective since they can represent the structural information, which is crucial for IQA. Moreover, they are also beneficial in a reduced-reference scenario where only partial reference image information is used for quality assessment. We address the second issue by exploiting machine learning. In our opinion, the well established methodology of machine learning/pattern recognition has not been adequately used for IQA so far; we believe that it will be an effective tool for feature pooling since the required weights/parameters can be determined in a more convincing way via training with the ground truth obtained according to subjective scores. This helps to overcome the limitations of the existing pooling methods, which tend to be over simplistic and lack theoretical justification. Therefore, we propose a new metric by formulating IQA as a pattern recognition problem. Extensive experiments conducted using six publicly available image databases (totally 3211 images with diverse distortions) and one video database (with 78 video sequences) demonstrate the effectiveness and efficiency of the proposed metric, in comparison with seven relevant existing metrics.en_US
dc.language.isoEnglishen_US
dc.source.titlePattern Recognitionen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.patcog.2011.06.023en_US
dc.subject2D mel-cepstral featuresen_US
dc.subjectFeature extractionen_US
dc.subjectImage quality assessmenten_US
dc.subjectMachine learningen_US
dc.subject2D mel-cepstral featuresen_US
dc.subjectComplex natureen_US
dc.subjectEffective toolen_US
dc.subjectGround truthen_US
dc.subjectHuman visual systemsen_US
dc.subjectImage and video processingen_US
dc.subjectImage databaseen_US
dc.subjectImage featuresen_US
dc.subjectImage quality assessmenten_US
dc.subjectMachine-learningen_US
dc.subjectObjective image quality assessmenten_US
dc.subjectPattern recognition problemsen_US
dc.subjectQuality assessmenten_US
dc.subjectReduced referenceen_US
dc.subjectReference imageen_US
dc.subjectScalable imageen_US
dc.subjectStructural informationen_US
dc.subjectTwo stageen_US
dc.subjectTwo-stage processen_US
dc.subjectVideo databaseen_US
dc.subjectVideo sequencesen_US
dc.subjectFeature extractionen_US
dc.subjectLearning systemsen_US
dc.subjectRatingen_US
dc.subjectVideo recordingen_US
dc.subjectImage qualityen_US
dc.titleScalable image quality assessment with 2D mel-cepstrum and machine learning approachen_US
dc.typeArticleen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.citation.spage299en_US
dc.citation.epage313en_US
dc.citation.volumeNumber45en_US
dc.citation.issueNumber1en_US
dc.identifier.doi10.1016/j.patcog.2011.06.023en_US
dc.publisherElsevieren_US
dc.contributor.bilkentauthorÇetin, A. Enis
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record