Universal Blind Image Quality Assessment Metrics Via Natural Scene Statistics and Multiple Kernel Learning

Universal blind image quality assessment (IQA) metrics that can work for various distortions are of great importance for image processing systems, because neither ground truths are available nor the distortion types are aware all the time in practice. Existing state-of-the-art universal blind IQA al...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transaction on neural networks and learning systems Vol. 24; no. 12; pp. 2013 - 2026
Main Authors:	Gao, Xinbo, Gao, Fei, Tao, Dacheng, Li, Xuelong
Format:	Journal Article
Language:	English
Published:	New York, NY IEEE 01.12.2013 Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Applied sciences Artificial intelligence Blinds Computer science; control theory; systems Data processing. List processing. Character string processing Distortion Exact sciences and technology Exponential decay characteristic (EDC) Feature extraction Image coding Image quality image quality assessment (IQA) Information theory Information, signal and communications theory Learning Learning and adaptive systems Mathematical models Measurement Memory organisation. Data processing multiple kernel learning (MKL) Mutual information natural scene statistics (NSS) Pattern recognition. Digital image processing. Computational geometry Similarity Software Telecommunications and information theory Transform coding Wavelet Wavelet transforms Density estimation Automatic classification Error estimation Image processing Local theory Probability distribution Modeling multiple kernel learning (MKL) Information measure Structural similarity Marginal distribution Natural scenes Learning algorithm Distance Pattern extraction image quality assessment (IQA) Mixed distribution Computer vision Statistical analysis Redundancy Image databank Blind identification Discrete wavelet transforms Ground truth Blurred image Exponential decay characteristic (EDC) natural scene statistics (NSS) Kernel method Image quality Experimental result Gaussian process Wavelet transformation Scene analysis Quality control Structural model Metric Mutual information Information theory
ISSN:	2162-237X, 2162-2388, 2162-2388
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!