Presentation 2014-02-18
Blind PSNR Estimation of Compressed Motion Pictures and Its Fast Implementation
Takahiro KUMEKAWA, Masahiro Wakabayashi, Jiro KATTO, Naofumi WADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Generally, PSNR (Peak Signal-to-Noise Ratio) is used as an index of the image quality objective evaluation, and it is necessary to prepare an original image. However, it is usually difficult to prepare the original images in case of CGM (Consumer Generated Media) movies such as YouTube etc. The authors have been working on blind PSNR estimation which estimates PSNRs of compressed and decoded videos without using original images and bit-stream analysis. In our previous study, we have estimated the quality of all frames to investigate its estimation accuracy, but we focus on quasi real-time implementation of our approach in this paper. In contrast with our conventional method, we sample the results of our blind PSNR estimation at a certain interval and interpolate PSNRs of other frames based on their AC power levels.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Blind PSNR estimation / AC power levels / SVM / Acceleration / Real time implementation
Paper # ITS2013-63,IE2013-128
Date of Issue

Conference Information
Committee IE
Conference Date 2014/2/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Blind PSNR Estimation of Compressed Motion Pictures and Its Fast Implementation
Sub Title (in English)
Keyword(1) Blind PSNR estimation
Keyword(2) AC power levels
Keyword(3) SVM
Keyword(4) Acceleration
Keyword(5) Real time implementation
1st Author's Name Takahiro KUMEKAWA
1st Author's Affiliation Graduate School of Fundamental Science and Engineering, Waseda University()
2nd Author's Name Masahiro Wakabayashi
2nd Author's Affiliation Graduate School of Fundamental Science and Engineering, Waseda University
3rd Author's Name Jiro KATTO
3rd Author's Affiliation Graduate School of Fundamental Science and Engineering, Waseda University
4th Author's Name Naofumi WADA
4th Author's Affiliation SAMSUNG R&D INSTITUTE JAPAN
Date 2014-02-18
Paper # ITS2013-63,IE2013-128
Volume (vol) vol.113
Number (no) 434
Page pp.pp.-
#Pages 6
Date of Issue