DipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs

Ma, K; Liu, W; Liu, T; Wang, Z; Tao, D

DipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs

Ma, K Liu, W Liu, T Wang, Z Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Image Processing, 2017, 26 (8), pp. 3951 - 3964
Issue Date:: 2017-08-01

Closed Access

	Filename	Description	Size
	07934456.pdf	Published Version	2.51 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ma, K	en_US
dc.contributor.author	Liu, W	en_US
dc.contributor.author	Liu, T	en_US
dc.contributor.author	Wang, Z	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2017-08-01	en_US
dc.identifier.citation	IEEE Transactions on Image Processing, 2017, 26 (8), pp. 3951 - 3964	en_US
dc.identifier.issn	1057-7149	en_US
dc.identifier.uri	http://hdl.handle.net/10453/123821
dc.description.abstract	© 2017 IEEE. Objective assessment of image quality is fundamentally important in many image processing tasks. In this paper, we focus on learning blind image quality assessment (BIQA) models, which predict the quality of a digital image with no access to its original pristine-quality counterpart as reference. One of the biggest challenges in learning BIQA models is the conflict between the gigantic image space (which is in the dimension of the number of image pixels) and the extremely limited reliable ground truth data for training. Such data are typically collected via subjective testing, which is cumbersome, slow, and expensive. Here, we first show that a vast amount of reliable training data in the form of quality-discriminable image pairs (DIPs) can be obtained automatically at low cost by exploiting large-scale databases with diverse image content. We then learn an opinion-unaware BIQA (OU-BIQA, meaning that no subjective opinions are used for training) model using RankNet, a pairwise learning-to-rank (L2R) algorithm, from millions of DIPs, each associated with a perceptual uncertainty level, leading to a DIP inferred quality (dipIQ) index. Extensive experiments on four benchmark IQA databases demonstrate that dipIQ outperforms the state-of-the-art OU-BIQA models. The robustness of dipIQ is also significantly improved as confirmed by the group MAximum Differentiation competition method. Furthermore, we extend the proposed framework by learning models with ListNet (a listwise L2R algorithm) on quality-discriminable image lists (DIL). The resulting DIL inferred quality index achieves an additional performance gain.	en_US
dc.relation.ispartof	IEEE Transactions on Image Processing	en_US
dc.relation.isbasedon	10.1109/TIP.2017.2708503	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	DipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs	en_US
dc.type	Journal Article
utslib.citation.volume	8	en_US
utslib.citation.volume	26	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1702 Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	8	en_US
pubs.publication-status	Published	en_US
pubs.volume	26	en_US

Abstract:

© 2017 IEEE. Objective assessment of image quality is fundamentally important in many image processing tasks. In this paper, we focus on learning blind image quality assessment (BIQA) models, which predict the quality of a digital image with no access to its original pristine-quality counterpart as reference. One of the biggest challenges in learning BIQA models is the conflict between the gigantic image space (which is in the dimension of the number of image pixels) and the extremely limited reliable ground truth data for training. Such data are typically collected via subjective testing, which is cumbersome, slow, and expensive. Here, we first show that a vast amount of reliable training data in the form of quality-discriminable image pairs (DIPs) can be obtained automatically at low cost by exploiting large-scale databases with diverse image content. We then learn an opinion-unaware BIQA (OU-BIQA, meaning that no subjective opinions are used for training) model using RankNet, a pairwise learning-to-rank (L2R) algorithm, from millions of DIPs, each associated with a perceptual uncertainty level, leading to a DIP inferred quality (dipIQ) index. Extensive experiments on four benchmark IQA databases demonstrate that dipIQ outperforms the state-of-the-art OU-BIQA models. The robustness of dipIQ is also significantly improved as confirmed by the group MAximum Differentiation competition method. Furthermore, we extend the proposed framework by learning models with ListNet (a listwise L2R algorithm) on quality-discriminable image lists (DIL). The resulting DIL inferred quality index achieves an additional performance gain.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/123821