Learning to Rank for Blind Image Quality Assessment

doi:10.1109/TNNLS.2014.2377181

OPT OpenIR > 光谱成像技术研究室

	Learning to Rank for Blind Image Quality Assessment
	Gao, Fei 1; Tao, Dacheng2 ; Gao, Xinbo 3; Li, Xuelong4
	2015-10-01
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷号	26 期号:10 页码:2275-2290
摘要	Blind image quality assessment (BIQA) aims to predict perceptual image quality scores without access to reference images. State-of-the-art BIQA methods typically require subjects to score a large number of images to train a robust model. However, subjective quality scores are imprecise, biased, and inconsistent, and it is challenging to obtain a large-scale database, or to extend existing databases, because of the inconvenience of collecting images, training the subjects, conducting subjective experiments, and realigning human quality evaluations. To combat these limitations, this paper explores and exploits preference image pairs (PIPs) such as the quality of image I-a is better than that of image I-b for training a robust BIQA model. The preference label, representing the relative quality of two images, is generally precise and consistent, and is not sensitive to image content, distortion type, or subject identity; such PIPs can be generated at a very low cost. The proposed BIQA method is one of learning to rank. We first formulate the problem of learning the mapping from the image features to the preference label as one of classification. In particular, we investigate the utilization of a multiple kernel learning algorithm based on group lasso to provide a solution. A simple but effective strategy to estimate perceptual image quality scores is then presented. Experiments show that the proposed BIQA method is highly effective and achieves a performance comparable with that of state-of-the-art BIQA algorithms. Moreover, the proposed method can be easily extended to new distortion categories.
文章类型	Article
关键词	Image Quality Assessment (Iqa) Learning Preferences Learning To Rank Multiple Kernel Learning (Mkl) Universal Blind Iqa (bIqa)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2014.2377181
收录类别	SCI ; EI
关键词[WOS]	NATURAL SCENE STATISTICS ; FRAMEWORK ; ALGORITHMS ; DOMAIN
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000362358800005
引用统计	被引频次：100[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/25482
专题	光谱成像技术研究室
作者单位	1.Xidian Univ, Sch Elect Engn, Video & Image Proc Syst Lab, Xian 710071, Shaanxi, Peoples R China 2.Univ Technol Sydney, Fac Engn & Informat Technol, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia 3.Xidian Univ, Sch Elect Engn, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Gao, Fei,Tao, Dacheng,Gao, Xinbo,et al. Learning to Rank for Blind Image Quality Assessment[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2015,26(10):2275-2290.
APA	Gao, Fei,Tao, Dacheng,Gao, Xinbo,&Li, Xuelong.(2015).Learning to Rank for Blind Image Quality Assessment.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,26(10),2275-2290.
MLA	Gao, Fei,et al."Learning to Rank for Blind Image Quality Assessment".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 26.10(2015):2275-2290.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Learning to Rank for（4556KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	请求全文