Presentation 2017-07-28
Objective Image Quality Assessment Framework based on Noise Cluster Estimation
Naho Ito, Yasuhiro Inazumi, Yuukou Horita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, various objective image quality assessment (IQA) methods for evaluating image quality have been proposed. IQA databases have been proposed to develop and test IQA metrics. There is TID2013 as a publicly available database. TID2013 has 25 types of original images and 3000 degraded images. There are 24 types of noise, and there are five noise levels. For databases with many types of noise, the prediction accuracy of subjective evaluation values tends to be low. Therefore, this study proposes an objective IQA framework based on estimating noise clusters using image features. Experimental results confirmed the effectiveness of the proposed framework under the conditions of this research.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) objective Image Quality Assessment / noise cluster / TID2013
Paper # CQ2017-46
Date of Issue 2017-07-20 (CQ)

Conference Information
Committee CQ
Conference Date 2017/7/27(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kobe University
Topics (in Japanese) (See Japanese page)
Topics (in English) Assessment, Measurement and Control of QoE and QoS, etc.
Chair Takanori Hayashi(HIT)
Vice Chair Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT)
Secretary Hideyuki Shimonishi(Keio Univ.) / Jun Okamoto(NTT)
Assistant Norihiro Fukumoto(KDDI Research) / Kenko Ota(NIT) / Ryo Yamamoto(UEC)

Paper Information
Registration To Technical Committee on Communication Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Objective Image Quality Assessment Framework based on Noise Cluster Estimation
Sub Title (in English)
Keyword(1) objective Image Quality Assessment
Keyword(2) noise cluster
Keyword(3) TID2013
1st Author's Name Naho Ito
1st Author's Affiliation University of Toyama(Univ. of Toyama)
2nd Author's Name Yasuhiro Inazumi
2nd Author's Affiliation University of Toyama(Univ. of Toyama)
3rd Author's Name Yuukou Horita
3rd Author's Affiliation University of Toyama(Univ. of Toyama)
Date 2017-07-28
Paper # CQ2017-46
Volume (vol) vol.117
Number (no) CQ-159
Page pp.pp.95-98(CQ),
#Pages 4
Date of Issue 2017-07-20 (CQ)