{"title":"Performance Analysis of the Revisited Tone Mapped Quality Index for Tone Mapped HDR Images Evaluation","authors":"B. Thai, Anissa Zergaïnoh-Mokraoui","doi":"10.1109/ICT.2019.8798770","DOIUrl":null,"url":null,"abstract":"This paper discusses the appropriate choice of the Tone Mapped Quality Index (TMQI) parameters. The TMQI metric has been developed to evaluate and compare the visual quality of the Tone Mapped (TM) High Dynamic Range (HDR) images. However, the parameters of this metric have been adjusted on a specific and reduced set of Tone Mapping Operators (TMO) and a restricted base of HDR images. The visual rendering evaluation of the TM images is then no longer consistent with the metric when new TMO (excluded from the initial training process) are used. To better adjust these parameters, discussions and experiments have been conducted on a large extension of the initial TMOs set and tone mapped HDR images dataset. The new parameters show a strong correlation between the revisited metric and the Mean Opinion Score (MOS).","PeriodicalId":127412,"journal":{"name":"2019 26th International Conference on Telecommunications (ICT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 26th International Conference on Telecommunications (ICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICT.2019.8798770","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper discusses the appropriate choice of the Tone Mapped Quality Index (TMQI) parameters. The TMQI metric has been developed to evaluate and compare the visual quality of the Tone Mapped (TM) High Dynamic Range (HDR) images. However, the parameters of this metric have been adjusted on a specific and reduced set of Tone Mapping Operators (TMO) and a restricted base of HDR images. The visual rendering evaluation of the TM images is then no longer consistent with the metric when new TMO (excluded from the initial training process) are used. To better adjust these parameters, discussions and experiments have been conducted on a large extension of the initial TMOs set and tone mapped HDR images dataset. The new parameters show a strong correlation between the revisited metric and the Mean Opinion Score (MOS).