Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise

Sheyda Ghanbaralizadeh Bahnemiri; Mykola Ponomarenko; Karen Egiazarian

doi:10.1007/978-3-031-31435-3_14

Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise

Sheyda Ghanbaralizadeh Bahnemiri, Mykola Ponomarenko, Karen Egiazarian

Computing Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

A problem of no-reference image visual quality assessment when images are corrupted by noise is considered in this paper. A specialized image set is proposed for the following two tasks: automatic verification of sensitivity of no-reference image visual quality metrics to noise, and analysis of blind noise level estimation methods. As a result, a method to improve the sensitivity of a given no reference quality metric to the presence of noise is proposed by combining this metric with a noise level estimator. The proposed method allows to significantly decrease a probability of wrong quality predictions for noisy images. Efficiency of usage of different noise level estimators in the proposed combined metrics is analyzed.

Original language	English
Title of host publication	Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings
Editors	Rikke Gade, Michael Felsberg, Joni-Kristian Kämäräinen
Publisher	Springer
Pages	201-214
Number of pages	14
ISBN (Print)	978-3-031-31434-6
DOIs	https://doi.org/10.1007/978-3-031-31435-3_14
Publication status	Published - 2023
Publication type	A4 Article in conference proceedings
Event	Scandinavian Conference on Image Analysis - Lapland, Finland Duration: 18 Apr 2023 → 21 Apr 2023

Publication series

Name	Lecture Notes in Computer Science
Volume	13885 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Scandinavian Conference on Image Analysis
Country/Territory	Finland
City	Lapland
Period	18/04/23 → 21/04/23

Keywords

Blind noise level estimation
Deep neural networks
Image visual quality assessment
No-reference image quality metrics

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-031-31435-3_14

Cite this

Bahnemiri, S. G., Ponomarenko, M., & Egiazarian, K. (2023). Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise. In R. Gade, M. Felsberg, & J.-K. Kämäräinen (Eds.), Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings (pp. 201-214). (Lecture Notes in Computer Science; Vol. 13885 LNCS). Springer. https://doi.org/10.1007/978-3-031-31435-3_14

Bahnemiri, Sheyda Ghanbaralizadeh ; Ponomarenko, Mykola ; Egiazarian, Karen. / Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise. Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings. editor / Rikke Gade ; Michael Felsberg ; Joni-Kristian Kämäräinen. Springer, 2023. pp. 201-214 (Lecture Notes in Computer Science).

@inproceedings{1568eecea91f49d981a26fc0b268dcbf,

title = "Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise",

abstract = "A problem of no-reference image visual quality assessment when images are corrupted by noise is considered in this paper. A specialized image set is proposed for the following two tasks: automatic verification of sensitivity of no-reference image visual quality metrics to noise, and analysis of blind noise level estimation methods. As a result, a method to improve the sensitivity of a given no reference quality metric to the presence of noise is proposed by combining this metric with a noise level estimator. The proposed method allows to significantly decrease a probability of wrong quality predictions for noisy images. Efficiency of usage of different noise level estimators in the proposed combined metrics is analyzed.",

keywords = "Blind noise level estimation, Deep neural networks, Image visual quality assessment, No-reference image quality metrics",

author = "Bahnemiri, {Sheyda Ghanbaralizadeh} and Mykola Ponomarenko and Karen Egiazarian",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Scandinavian Conference on Image Analysis ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1007/978-3-031-31435-3_14",

language = "English",

isbn = "978-3-031-31434-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "201--214",

editor = "Rikke Gade and Michael Felsberg and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",

booktitle = "Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings",

}

Bahnemiri, SG, Ponomarenko, M & Egiazarian, K 2023, Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise. in R Gade, M Felsberg & J-K Kämäräinen (eds), Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings. Lecture Notes in Computer Science, vol. 13885 LNCS, Springer, pp. 201-214, Scandinavian Conference on Image Analysis, Lapland, Finland, 18/04/23. https://doi.org/10.1007/978-3-031-31435-3_14

Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise. / Bahnemiri, Sheyda Ghanbaralizadeh; Ponomarenko, Mykola ; Egiazarian, Karen.
Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings. ed. / Rikke Gade; Michael Felsberg; Joni-Kristian Kämäräinen. Springer, 2023. p. 201-214 (Lecture Notes in Computer Science; Vol. 13885 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise

AU - Bahnemiri, Sheyda Ghanbaralizadeh

AU - Ponomarenko, Mykola

AU - Egiazarian, Karen

PY - 2023

Y1 - 2023

N2 - A problem of no-reference image visual quality assessment when images are corrupted by noise is considered in this paper. A specialized image set is proposed for the following two tasks: automatic verification of sensitivity of no-reference image visual quality metrics to noise, and analysis of blind noise level estimation methods. As a result, a method to improve the sensitivity of a given no reference quality metric to the presence of noise is proposed by combining this metric with a noise level estimator. The proposed method allows to significantly decrease a probability of wrong quality predictions for noisy images. Efficiency of usage of different noise level estimators in the proposed combined metrics is analyzed.

AB - A problem of no-reference image visual quality assessment when images are corrupted by noise is considered in this paper. A specialized image set is proposed for the following two tasks: automatic verification of sensitivity of no-reference image visual quality metrics to noise, and analysis of blind noise level estimation methods. As a result, a method to improve the sensitivity of a given no reference quality metric to the presence of noise is proposed by combining this metric with a noise level estimator. The proposed method allows to significantly decrease a probability of wrong quality predictions for noisy images. Efficiency of usage of different noise level estimators in the proposed combined metrics is analyzed.

KW - Blind noise level estimation

KW - Deep neural networks

KW - Image visual quality assessment

KW - No-reference image quality metrics

U2 - 10.1007/978-3-031-31435-3_14

DO - 10.1007/978-3-031-31435-3_14

M3 - Conference contribution

AN - SCOPUS:85161375798

SN - 978-3-031-31434-6

T3 - Lecture Notes in Computer Science

SP - 201

EP - 214

BT - Image Analysis - 23rd Scandinavian Conference, SCIA 2023, Proceedings

A2 - Gade, Rikke

A2 - Felsberg, Michael

A2 - Kämäräinen, Joni-Kristian

PB - Springer

T2 - Scandinavian Conference on Image Analysis

Y2 - 18 April 2023 through 21 April 2023

ER -

Improved Sensitivity of No-Reference Image Visual Quality Metrics to the Presence of Noise

Abstract

Publication series

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this