An objective IQA framework based on noise clusters estimation for still images

Naho Ito, Yasuhiro Inazumi, Yuukou Horita

研究成果: 書籍の章/レポート/会議録会議への寄与査読

抄録

Recently, various objective image quality assessment (IQA) metrics have been proposed for measuring the quality of a captured image. Moreover, IQA databases have been made available to enable researchers develop and test IQA metrics. For instance, the TID2013 database was used in the experiments conducted in this study. It contains many test images obtained from 25 reference images, each having 24 types of distortion and five levels of noise for each distortion. However, estimating a subjective evaluation score for many types of noise is a difficult task. Therefore, this study proposes an objective IQA framework for evaluating noise clusters using image features. Experimental results confirmed the effectiveness of the proposed framework.

本文言語英語
ホスト出版物のタイトル2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1-2
ページ数2
ISBN(電子版)9781509040452
DOI
出版ステータス出版済み - 2017/12/19
イベント6th IEEE Global Conference on Consumer Electronics, GCCE 2017 - Nagoya, 日本
継続期間: 2017/10/242017/10/27

出版物シリーズ

名前2017 IEEE 6th Global Conference on Consumer Electronics, GCCE 2017
2017-January

学会

学会6th IEEE Global Conference on Consumer Electronics, GCCE 2017
国/地域日本
CityNagoya
Period2017/10/242017/10/27

ASJC Scopus 主題領域

  • メディア記述
  • 器械工学
  • 電子工学および電気工学

フィンガープリント

「An objective IQA framework based on noise clusters estimation for still images」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル