Quality Estimation Model of Monochrome Still Picture Based on Distortion Factors and Texture Features

Yuukou Horita; Yasuhiro Inazumi; Kazunori Kotani; Tadakuni Murai; V. R. Algazi

Quality Estimation Model of Monochrome Still Picture Based on Distortion Factors and Texture Features

Yuukou Horita^*, Yasuhiro Inazumi, Kazunori Kotani, Tadakuni Murai, V. R. Algazi

^*この論文の責任著者

都市・交通デザイン学科

研究成果: 会議への寄与 › 学会論文 › 査読

5 被引用数 (Scopus)

抄録

In this paper, we investigate the improvement of the estimation accuracy of the objective quality metric method named "the Picture Quality Scale (PQS)". To eliminate the dependence of the picture content of the PQS, we newly employ the texture features as the independent variance and combine with the distortion factors. For constructing new PQS, we apply the nonlinear combination model between the Mean Opinion Score (MOS) and factors, which is based on the logistic function. Then, to discuss the improvement of the PQS, we carry out the subjective estimation experiment for 144 pictures and obtain the MOS. Finally, the proposed PQSnew closely approximate well the MOS, with a correlation coefficient of more than 0.98.

本文言語	英語
ページ	419-424
ページ数	6
出版ステータス	出版済み - 1999
イベント	Final Program and Proceedings: IS and T's 52nd Annual Conference - Savannah, GA, 米国継続期間: 1999/04/25 → 1999/04/28

学会

学会	Final Program and Proceedings: IS and T's 52nd Annual Conference
国/地域	米国
City	Savannah, GA
Period	1999/04/25 → 1999/04/28

ASJC Scopus 主題領域

コンピュータサイエンス一般
工学一般

引用スタイル

@conference{32c6ed7894ed43a992487eb847486a9e,

title = "Quality Estimation Model of Monochrome Still Picture Based on Distortion Factors and Texture Features",

abstract = "In this paper, we investigate the improvement of the estimation accuracy of the objective quality metric method named {"}the Picture Quality Scale (PQS){"}. To eliminate the dependence of the picture content of the PQS, we newly employ the texture features as the independent variance and combine with the distortion factors. For constructing new PQS, we apply the nonlinear combination model between the Mean Opinion Score (MOS) and factors, which is based on the logistic function. Then, to discuss the improvement of the PQS, we carry out the subjective estimation experiment for 144 pictures and obtain the MOS. Finally, the proposed PQSnew closely approximate well the MOS, with a correlation coefficient of more than 0.98.",

author = "Yuukou Horita and Yasuhiro Inazumi and Kazunori Kotani and Tadakuni Murai and Algazi, {V. R.}",

year = "1999",

language = "英語",

pages = "419--424",

note = "Final Program and Proceedings: IS and T's 52nd Annual Conference ; Conference date: 25-04-1999 Through 28-04-1999",

}

TY - CONF

T1 - Quality Estimation Model of Monochrome Still Picture Based on Distortion Factors and Texture Features

AU - Horita, Yuukou

AU - Inazumi, Yasuhiro

AU - Kotani, Kazunori

AU - Murai, Tadakuni

AU - Algazi, V. R.

PY - 1999

Y1 - 1999

N2 - In this paper, we investigate the improvement of the estimation accuracy of the objective quality metric method named "the Picture Quality Scale (PQS)". To eliminate the dependence of the picture content of the PQS, we newly employ the texture features as the independent variance and combine with the distortion factors. For constructing new PQS, we apply the nonlinear combination model between the Mean Opinion Score (MOS) and factors, which is based on the logistic function. Then, to discuss the improvement of the PQS, we carry out the subjective estimation experiment for 144 pictures and obtain the MOS. Finally, the proposed PQSnew closely approximate well the MOS, with a correlation coefficient of more than 0.98.

AB - In this paper, we investigate the improvement of the estimation accuracy of the objective quality metric method named "the Picture Quality Scale (PQS)". To eliminate the dependence of the picture content of the PQS, we newly employ the texture features as the independent variance and combine with the distortion factors. For constructing new PQS, we apply the nonlinear combination model between the Mean Opinion Score (MOS) and factors, which is based on the logistic function. Then, to discuss the improvement of the PQS, we carry out the subjective estimation experiment for 144 pictures and obtain the MOS. Finally, the proposed PQSnew closely approximate well the MOS, with a correlation coefficient of more than 0.98.

UR - http://www.scopus.com/inward/record.url?scp=1542363203&partnerID=8YFLogxK

M3 - 学会論文

AN - SCOPUS:1542363203

SP - 419

EP - 424

T2 - Final Program and Proceedings: IS and T's 52nd Annual Conference

Y2 - 25 April 1999 through 28 April 1999

ER -

Quality Estimation Model of Monochrome Still Picture Based on Distortion Factors and Texture Features

抄録

学会

ASJC Scopus 主題領域

フィンガープリント

引用スタイル