Reduced reference image quality assessment via Boltzmann Machines

Decebal Constantin Mocanu; Georgios Exarchakos; Haitham Bou Ammar; Antonio Liotta

doi:10.1109/INM.2015.7140481

Reduced reference image quality assessment via Boltzmann Machines

Decebal Constantin Mocanu, Georgios Exarchakos, Haitham Bou Ammar, Antonio Liotta

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

17 Citations (Scopus)

Abstract

Monitoring and controlling the user's perceived quality, in modern video services is a challenging proposition, mainly due to the limitations of current Image Quality Assessment (IQA) algorithms. Subjective Quality of Experience (QoE) is widely used to get a right impression, but unfortunately this can not be used in real world scenarios. In general, objective QoE algorithms represent a good substitution for the subjective ones, and they are split in three main directions: Full Reference (FR), Reduced Reference (RR), and No Reference (NR). From these three, the RR IQA approach offers a practical solution to assess the quality of an impaired image due to the fact that just a small amount of information is needed from the original image. At the same time, keeping in mind that we need automated QoE algorithms which are context independent, in this paper we introduce a novel stochastic RR IQA metric to assess the quality of an image based on Deep Learning, namely Restricted Boltzmann Machine Similarity Measure (RBMSim). RBMSim was evaluated on two benchmarked image databases with subjective studies, against objective IQA algorithms. The results show that its performance is comparable, or even better in some cases, with widely known FR IQA methods.

Original language	English
Title of host publication	2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015
Editors	Filip De Turck, Remi Badonnel, Carlos Raniery P. dos Santos, Jin Xiao, Shingo Ata, Voicu Groza
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	1278-1281
Number of pages	4
ISBN (Electronic)	9783901882760
DOIs	https://doi.org/10.1109/INM.2015.7140481
Publication status	Published - 29 Jun 2015
Externally published	Yes
Event	14th IFIP/IEEE International Symposium on Integrated Network Management, IM 2015: Integrated Management in the Age of Big Data - Shaw Centre, Ottawa, Canada Duration: 11 May 2015 → 15 May 2015 Conference number: 14 http://im2015.ieee-im.org/

Publication series

Name	Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM)
Publisher	IEEE
Volume	2015
ISSN (Print)	1573-0077

Conference

Conference	14th IFIP/IEEE International Symposium on Integrated Network Management, IM 2015
Abbreviated title	IM 2015
Country	Canada
City	Ottawa
Period	11/05/15 → 15/05/15
Internet address	http://im2015.ieee-im.org/

Keywords

Deep learning
Quality of experience
Reduced reference image quality assessment
Restricted Boltzmann machines
Similarity measure

Access to Document

10.1109/INM.2015.7140481

Cite this

Mocanu, D. C., Exarchakos, G., Ammar, H. B., & Liotta, A. (2015). Reduced reference image quality assessment via Boltzmann Machines. In F. De Turck, R. Badonnel, C. R. P. dos Santos, J. Xiao, S. Ata, & V. Groza (Eds.), 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015 (pp. 1278-1281). [7140481] (Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM); Vol. 2015). IEEE. https://doi.org/10.1109/INM.2015.7140481

Mocanu, Decebal Constantin ; Exarchakos, Georgios ; Ammar, Haitham Bou ; Liotta, Antonio. / Reduced reference image quality assessment via Boltzmann Machines. 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015. editor / Filip De Turck ; Remi Badonnel ; Carlos Raniery P. dos Santos ; Jin Xiao ; Shingo Ata ; Voicu Groza. Piscataway, NJ : IEEE, 2015. pp. 1278-1281 (Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM)).

@inproceedings{4060061fc1f5428ba827c9425161d519,

title = "Reduced reference image quality assessment via Boltzmann Machines",

abstract = "Monitoring and controlling the user's perceived quality, in modern video services is a challenging proposition, mainly due to the limitations of current Image Quality Assessment (IQA) algorithms. Subjective Quality of Experience (QoE) is widely used to get a right impression, but unfortunately this can not be used in real world scenarios. In general, objective QoE algorithms represent a good substitution for the subjective ones, and they are split in three main directions: Full Reference (FR), Reduced Reference (RR), and No Reference (NR). From these three, the RR IQA approach offers a practical solution to assess the quality of an impaired image due to the fact that just a small amount of information is needed from the original image. At the same time, keeping in mind that we need automated QoE algorithms which are context independent, in this paper we introduce a novel stochastic RR IQA metric to assess the quality of an image based on Deep Learning, namely Restricted Boltzmann Machine Similarity Measure (RBMSim). RBMSim was evaluated on two benchmarked image databases with subjective studies, against objective IQA algorithms. The results show that its performance is comparable, or even better in some cases, with widely known FR IQA methods.",

keywords = "Deep learning, Quality of experience, Reduced reference image quality assessment, Restricted Boltzmann machines, Similarity measure",

author = "Mocanu, {Decebal Constantin} and Georgios Exarchakos and Ammar, {Haitham Bou} and Antonio Liotta",

year = "2015",

month = jun,

day = "29",

doi = "10.1109/INM.2015.7140481",

language = "English",

series = "Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM)",

publisher = "IEEE",

pages = "1278--1281",

editor = "{De Turck}, Filip and Remi Badonnel and {dos Santos}, {Carlos Raniery P.} and Jin Xiao and Shingo Ata and Voicu Groza",

booktitle = "2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015",

address = "United States",

note = "14th IFIP/IEEE International Symposium on Integrated Network Management, IM 2015 : Integrated Management in the Age of Big Data, IM 2015 ; Conference date: 11-05-2015 Through 15-05-2015",

url = "http://im2015.ieee-im.org/",

}

Mocanu, DC, Exarchakos, G, Ammar, HB & Liotta, A 2015, Reduced reference image quality assessment via Boltzmann Machines. in F De Turck, R Badonnel, CRP dos Santos, J Xiao, S Ata & V Groza (eds), 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015., 7140481, Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM), vol. 2015, IEEE, Piscataway, NJ, pp. 1278-1281, 14th IFIP/IEEE International Symposium on Integrated Network Management, IM 2015, Ottawa, Canada, 11/05/15. https://doi.org/10.1109/INM.2015.7140481

Reduced reference image quality assessment via Boltzmann Machines. / Mocanu, Decebal Constantin; Exarchakos, Georgios; Ammar, Haitham Bou; Liotta, Antonio.

2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015. ed. / Filip De Turck; Remi Badonnel; Carlos Raniery P. dos Santos; Jin Xiao; Shingo Ata; Voicu Groza. Piscataway, NJ : IEEE, 2015. p. 1278-1281 7140481 (Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM); Vol. 2015).

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

TY - GEN

T1 - Reduced reference image quality assessment via Boltzmann Machines

AU - Mocanu, Decebal Constantin

AU - Exarchakos, Georgios

AU - Ammar, Haitham Bou

AU - Liotta, Antonio

N1 - Conference code: 14

PY - 2015/6/29

Y1 - 2015/6/29

N2 - Monitoring and controlling the user's perceived quality, in modern video services is a challenging proposition, mainly due to the limitations of current Image Quality Assessment (IQA) algorithms. Subjective Quality of Experience (QoE) is widely used to get a right impression, but unfortunately this can not be used in real world scenarios. In general, objective QoE algorithms represent a good substitution for the subjective ones, and they are split in three main directions: Full Reference (FR), Reduced Reference (RR), and No Reference (NR). From these three, the RR IQA approach offers a practical solution to assess the quality of an impaired image due to the fact that just a small amount of information is needed from the original image. At the same time, keeping in mind that we need automated QoE algorithms which are context independent, in this paper we introduce a novel stochastic RR IQA metric to assess the quality of an image based on Deep Learning, namely Restricted Boltzmann Machine Similarity Measure (RBMSim). RBMSim was evaluated on two benchmarked image databases with subjective studies, against objective IQA algorithms. The results show that its performance is comparable, or even better in some cases, with widely known FR IQA methods.

AB - Monitoring and controlling the user's perceived quality, in modern video services is a challenging proposition, mainly due to the limitations of current Image Quality Assessment (IQA) algorithms. Subjective Quality of Experience (QoE) is widely used to get a right impression, but unfortunately this can not be used in real world scenarios. In general, objective QoE algorithms represent a good substitution for the subjective ones, and they are split in three main directions: Full Reference (FR), Reduced Reference (RR), and No Reference (NR). From these three, the RR IQA approach offers a practical solution to assess the quality of an impaired image due to the fact that just a small amount of information is needed from the original image. At the same time, keeping in mind that we need automated QoE algorithms which are context independent, in this paper we introduce a novel stochastic RR IQA metric to assess the quality of an image based on Deep Learning, namely Restricted Boltzmann Machine Similarity Measure (RBMSim). RBMSim was evaluated on two benchmarked image databases with subjective studies, against objective IQA algorithms. The results show that its performance is comparable, or even better in some cases, with widely known FR IQA methods.

KW - Deep learning

KW - Quality of experience

KW - Reduced reference image quality assessment

KW - Restricted Boltzmann machines

KW - Similarity measure

UR - http://www.scopus.com/inward/record.url?scp=84942645422&partnerID=8YFLogxK

U2 - 10.1109/INM.2015.7140481

DO - 10.1109/INM.2015.7140481

M3 - Conference contribution

AN - SCOPUS:84942645422

T3 - Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM)

SP - 1278

EP - 1281

BT - 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015

A2 - De Turck, Filip

A2 - Badonnel, Remi

A2 - dos Santos, Carlos Raniery P.

A2 - Xiao, Jin

A2 - Ata, Shingo

A2 - Groza, Voicu

PB - IEEE

CY - Piscataway, NJ

T2 - 14th IFIP/IEEE International Symposium on Integrated Network Management, IM 2015

Y2 - 11 May 2015 through 15 May 2015

ER -

Mocanu DC, Exarchakos G, Ammar HB, Liotta A. Reduced reference image quality assessment via Boltzmann Machines. In De Turck F, Badonnel R, dos Santos CRP, Xiao J, Ata S, Groza V, editors, 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015. Piscataway, NJ: IEEE. 2015. p. 1278-1281. 7140481. (Proceedings of the IFIP/IEEE International Symposium on Integrated Network Management (IM)). https://doi.org/10.1109/INM.2015.7140481

Reduced reference image quality assessment via Boltzmann Machines

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this