No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks

Wael Suliman; Mohamed Deriche; Mohamed Mohandes

doi:10.1109/SSD49366.2020.9364267

No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks

Wael Suliman
, Mohamed Deriche
, Mohamed Mohandes

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

Abstract

Images and videos are seen as the most reliable source of visual information as they are a fundamental part of the multimedia world. For instance, face recognition technology utilizes images for security purposes. However, due to either the physical properties of the acquisition equipment (internal) or the nature of the environment (external), images can be affected by a wide range of distortions. Researchers have enumerated more than 24 distortions that can affect images. Among which four types are the most prominent ones. In this paper, a novel no-reference color image quality assessment technique is introduced. The technique is based on extracting a set of features from the High Order Singular Value Decomposition (HOSVD) of images. Such features are then used with a neural network regressor to predict the quality score. The results show excellent performance exceeding traditional techniques based only on gray-scale images.

Original language	English
Title of host publication	Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	474-478
Number of pages	5
ISBN (Electronic)	9781728110806
DOIs	https://doi.org/10.1109/SSD49366.2020.9364267
State	Published - 20 Jul 2020

Publication series

Name	Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Artificial Neural Networks
Higher Order SVD
Image Quality Assessment
NR-IQA
Tensors

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Signal Processing
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/SSD49366.2020.9364267

Cite this

Suliman, W., Deriche, M., & Mohandes, M. (2020). No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks. In Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020 (pp. 474-478). Article 9364267 (Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD49366.2020.9364267

Suliman, Wael ; Deriche, Mohamed ; Mohandes, Mohamed. / No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks. Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 474-478 (Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020).

@inproceedings{28b6f51b02b94e4ebe6652556288c270,

title = "No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks",

abstract = "Images and videos are seen as the most reliable source of visual information as they are a fundamental part of the multimedia world. For instance, face recognition technology utilizes images for security purposes. However, due to either the physical properties of the acquisition equipment (internal) or the nature of the environment (external), images can be affected by a wide range of distortions. Researchers have enumerated more than 24 distortions that can affect images. Among which four types are the most prominent ones. In this paper, a novel no-reference color image quality assessment technique is introduced. The technique is based on extracting a set of features from the High Order Singular Value Decomposition (HOSVD) of images. Such features are then used with a neural network regressor to predict the quality score. The results show excellent performance exceeding traditional techniques based only on gray-scale images.",

keywords = "Artificial Neural Networks, Higher Order SVD, Image Quality Assessment, NR-IQA, Tensors",

author = "Wael Suliman and Mohamed Deriche and Mohamed Mohandes",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.",

year = "2020",

month = jul,

day = "20",

doi = "10.1109/SSD49366.2020.9364267",

language = "English",

series = "Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "474--478",

booktitle = "Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020",

address = "United States",

}

Suliman, W, Deriche, M & Mohandes, M 2020, No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks. in Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020., 9364267, Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020, Institute of Electrical and Electronics Engineers Inc., pp. 474-478. https://doi.org/10.1109/SSD49366.2020.9364267

No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks. / Suliman, Wael; Deriche, Mohamed; Mohandes, Mohamed.
Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 474-478 9364267 (Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020).

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

TY - GEN

T1 - No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks

AU - Suliman, Wael

AU - Deriche, Mohamed

AU - Mohandes, Mohamed

PY - 2020/7/20

Y1 - 2020/7/20

N2 - Images and videos are seen as the most reliable source of visual information as they are a fundamental part of the multimedia world. For instance, face recognition technology utilizes images for security purposes. However, due to either the physical properties of the acquisition equipment (internal) or the nature of the environment (external), images can be affected by a wide range of distortions. Researchers have enumerated more than 24 distortions that can affect images. Among which four types are the most prominent ones. In this paper, a novel no-reference color image quality assessment technique is introduced. The technique is based on extracting a set of features from the High Order Singular Value Decomposition (HOSVD) of images. Such features are then used with a neural network regressor to predict the quality score. The results show excellent performance exceeding traditional techniques based only on gray-scale images.

AB - Images and videos are seen as the most reliable source of visual information as they are a fundamental part of the multimedia world. For instance, face recognition technology utilizes images for security purposes. However, due to either the physical properties of the acquisition equipment (internal) or the nature of the environment (external), images can be affected by a wide range of distortions. Researchers have enumerated more than 24 distortions that can affect images. Among which four types are the most prominent ones. In this paper, a novel no-reference color image quality assessment technique is introduced. The technique is based on extracting a set of features from the High Order Singular Value Decomposition (HOSVD) of images. Such features are then used with a neural network regressor to predict the quality score. The results show excellent performance exceeding traditional techniques based only on gray-scale images.

KW - Artificial Neural Networks

KW - Higher Order SVD

KW - Image Quality Assessment

KW - NR-IQA

KW - Tensors

UR - https://www.scopus.com/pages/publications/85103031097

U2 - 10.1109/SSD49366.2020.9364267

DO - 10.1109/SSD49366.2020.9364267

M3 - Conference contribution

AN - SCOPUS:85103031097

T3 - Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020

SP - 474

EP - 478

BT - Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Suliman W, Deriche M, Mohandes M. No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks. In Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 474-478. 9364267. (Proceedings of the 17th International Multi-Conference on Systems, Signals and Devices, SSD 2020). doi: 10.1109/SSD49366.2020.9364267

No-ReferenceColor Image Quality Assessment Using HOSVD Based Features and Neural Networks

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this