A Comparative Study of DNN-Based Models for Blind Image Quality Prediction

Xiaohan Yang; Fan Li; Hantao Liu

doi:10.1109/ICIP.2019.8804268

A Comparative Study of DNN-Based Models for Blind Image Quality Prediction

Xiaohan Yang
, Fan Li
, Hantao Liu

Faculty of Electronic and Information Engineering

Xi'an Jiaotong University
Cardiff University

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

6 Scopus citations

Abstract

Recently, deep learning methods have gained substantial attention in the research community and have proven useful for blind image quality assessment (BIQA). Although previous study of deep neural networks (DNN) methods is presented, some novelty methods, which are recently proposed, are not summarized. In this paper, we provide a comparative study on the application of DNN methods for BIQA. First, we systematically analyze the existing DNN-based quality assessment methods. Then, we compare the predictive performance of various methods in synthetic and authentic databases, providing important information that can help understand the underlying properties between different methods. Finally, we describe some emerging challenges in designing and training DNN-based BIQA, along with few directions that are worth further investigations in the future.

Original language	English
Title of host publication	2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
Publisher	IEEE Computer Society
Pages	1019-1023
Number of pages	5
ISBN (Electronic)	9781538662496
DOIs	https://doi.org/10.1109/ICIP.2019.8804268
State	Published - Sep 2019
Event	26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China Duration: 22 Sep 2019 → 25 Sep 2019

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2019-September
ISSN (Print)	1522-4880

Conference

Conference	26th IEEE International Conference on Image Processing, ICIP 2019
Country/Territory	Taiwan, Province of China
City	Taipei
Period	22/09/19 → 25/09/19

Keywords

blind image quality assessment (BIQA)
deep learning
deep neural networks (DNN)

Access to Document

10.1109/ICIP.2019.8804268

Cite this

Yang, X., Li, F., & Liu, H. (2019). A Comparative Study of DNN-Based Models for Blind Image Quality Prediction. In 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings (pp. 1019-1023). Article 8804268 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2019.8804268

@inproceedings{9f1c859bd7dc4f16a8d3674ba76f579a,

title = "A Comparative Study of DNN-Based Models for Blind Image Quality Prediction",

abstract = "Recently, deep learning methods have gained substantial attention in the research community and have proven useful for blind image quality assessment (BIQA). Although previous study of deep neural networks (DNN) methods is presented, some novelty methods, which are recently proposed, are not summarized. In this paper, we provide a comparative study on the application of DNN methods for BIQA. First, we systematically analyze the existing DNN-based quality assessment methods. Then, we compare the predictive performance of various methods in synthetic and authentic databases, providing important information that can help understand the underlying properties between different methods. Finally, we describe some emerging challenges in designing and training DNN-based BIQA, along with few directions that are worth further investigations in the future.",

keywords = "blind image quality assessment (BIQA), deep learning, deep neural networks (DNN)",

author = "Xiaohan Yang and Fan Li and Hantao Liu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 26th IEEE International Conference on Image Processing, ICIP 2019 ; Conference date: 22-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICIP.2019.8804268",

language = "英语",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "1019--1023",

booktitle = "2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings",

}

Yang, X, Li, F & Liu, H 2019, A Comparative Study of DNN-Based Models for Blind Image Quality Prediction. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8804268, Proceedings - International Conference on Image Processing, ICIP, vol. 2019-September, IEEE Computer Society, pp. 1019-1023, 26th IEEE International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, Province of China, 22/09/19. https://doi.org/10.1109/ICIP.2019.8804268

A Comparative Study of DNN-Based Models for Blind Image Quality Prediction. / Yang, Xiaohan; Li, Fan; Liu, Hantao.
2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings. IEEE Computer Society, 2019. p. 1019-1023 8804268 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2019-September).

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

TY - GEN

T1 - A Comparative Study of DNN-Based Models for Blind Image Quality Prediction

AU - Yang, Xiaohan

AU - Li, Fan

AU - Liu, Hantao

PY - 2019/9

Y1 - 2019/9

N2 - Recently, deep learning methods have gained substantial attention in the research community and have proven useful for blind image quality assessment (BIQA). Although previous study of deep neural networks (DNN) methods is presented, some novelty methods, which are recently proposed, are not summarized. In this paper, we provide a comparative study on the application of DNN methods for BIQA. First, we systematically analyze the existing DNN-based quality assessment methods. Then, we compare the predictive performance of various methods in synthetic and authentic databases, providing important information that can help understand the underlying properties between different methods. Finally, we describe some emerging challenges in designing and training DNN-based BIQA, along with few directions that are worth further investigations in the future.

AB - Recently, deep learning methods have gained substantial attention in the research community and have proven useful for blind image quality assessment (BIQA). Although previous study of deep neural networks (DNN) methods is presented, some novelty methods, which are recently proposed, are not summarized. In this paper, we provide a comparative study on the application of DNN methods for BIQA. First, we systematically analyze the existing DNN-based quality assessment methods. Then, we compare the predictive performance of various methods in synthetic and authentic databases, providing important information that can help understand the underlying properties between different methods. Finally, we describe some emerging challenges in designing and training DNN-based BIQA, along with few directions that are worth further investigations in the future.

KW - blind image quality assessment (BIQA)

KW - deep learning

KW - deep neural networks (DNN)

UR - https://www.scopus.com/pages/publications/85076801151

U2 - 10.1109/ICIP.2019.8804268

DO - 10.1109/ICIP.2019.8804268

M3 - 会议稿件

AN - SCOPUS:85076801151

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1019

EP - 1023

BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings

PB - IEEE Computer Society

T2 - 26th IEEE International Conference on Image Processing, ICIP 2019

Y2 - 22 September 2019 through 25 September 2019

ER -

A Comparative Study of DNN-Based Models for Blind Image Quality Prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this