Presentation 2014-02-18
PSNR Prediction of H.264/AVC Compressed Video using Image Analysis
Masahiro Wakabayashi, Takahiro Kumekawa, Jiro Katto, Naofumi Wada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In video coding, image quality degradation is inevitable due to quantization steps in the encoding process. We had proposed a blind type (no-reference type) PSNR estimation method which uses SVM and natural image statistics. In this paper, as an application of the blind PSNR estimation, we propose a method to predict PSNRs of video sequences before applying video compression by using image features of the original video sequences. As a result, we reveal that we can predict sufficient PSNRs for more than 80% frames within 5dB prediction errors.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) PSNR / SVM / Blind Estimation / H.264/AVC / Region Segmentation
Paper # ITS2013-62,IE2013-127
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) PSNR Prediction of H.264/AVC Compressed Video using Image Analysis
Sub Title (in English)
Keyword(1) PSNR
Keyword(2) SVM
Keyword(3) Blind Estimation
Keyword(4) H.264/AVC
Keyword(5) Region Segmentation
1st Author's Name Masahiro Wakabayashi
1st Author's Affiliation School of Science and Engineering, Waseda University()
2nd Author's Name Takahiro Kumekawa
2nd Author's Affiliation School of Science and Engineering, Waseda University
3rd Author's Name Jiro Katto
3rd Author's Affiliation School of 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 # ITS2013-62,IE2013-127
Volume (vol) vol.113
Number (no) 434
Page pp.pp.-
#Pages 6
Date of Issue