Presentation | 2016-12-16 Application of Classification Algorithm for the Image Quality Assessment of Multi-view 3D CG Images and 5K Images by Using S-CIELAB Color Space Norifumi Kawabata, Masaru Miyao, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Toward the 2020 Tokyo Olympic Games, it is expected that general broadcasting of 4K picture quality will be started. Therefore, it becomes important to assess high-definition image quality. On the other hand, thanks to improvement of screen resolution, 3D image and video quality also improve. It is advanced to study for the glassless 3D and multi-view 3D image and video quality assessment. Previously, we studied for the multi-view 3D coded image quality assessment. On the other hand, there were some studies for high-definition image quality, however, it is not clear for mutual relationship among the image resolution, the number of viewpoint, and color information. In this paper, first, we carried out the subjective quality assessment of 3D CG images coded and decoded by H.265/HEVC with both 8 viewpoints parallax barrier method and 5K high-definition retina method, and then, we analyzed their results, and classified by using Support Vector Machine (SVM). Next, we carried out the objective quality assessment by measuring luminance $L^ast$ by using S-CIELAB color space, and then, by measuring color difference $Delta E_{00}$ by using CIEDE2000. And then, we considered the relation between subjective and objective assessments. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Multi-view 3D Image / 5K Image / Super Resolution / Luminance / CIEDE2000 / Support Vector Machine |
Paper # | IMQ2016-18 |
Date of Issue | 2016-12-09 (IMQ) |
Conference Information | |
Committee | IMQ |
---|---|
Conference Date | 2016/12/16(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tokyo University of Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Computer Graphics and overall ontent of IMQ |
Chair | Yuukou Horita(Univ. of Toyama) |
Vice Chair | Kenji Sugiyama(Seikei Univ.) / Toshiya Nakaguchi(Chiba Univ.) |
Secretary | Kenji Sugiyama(Canon) / Toshiya Nakaguchi(Nagoya Univ.) |
Assistant | Shinichiro Saito(Sony) / Masaru Tsuchida(NTT) |
Paper Information | |
Registration To | Technical Committee on Image Media Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Application of Classification Algorithm for the Image Quality Assessment of Multi-view 3D CG Images and 5K Images by Using S-CIELAB Color Space |
Sub Title (in English) | |
Keyword(1) | Multi-view 3D Image |
Keyword(2) | 5K Image |
Keyword(3) | Super Resolution |
Keyword(4) | Luminance |
Keyword(5) | CIEDE2000 |
Keyword(6) | Support Vector Machine |
1st Author's Name | Norifumi Kawabata |
1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
2nd Author's Name | Masaru Miyao |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2016-12-16 |
Paper # | IMQ2016-18 |
Volume (vol) | vol.116 |
Number (no) | IMQ-369 |
Page | pp.pp.13-18(IMQ), |
#Pages | 6 |
Date of Issue | 2016-12-09 (IMQ) |