No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization

The general purpose of seeing a picture is to attain information as much as possible. With it, we in this paper devise a new no-reference/blind metric for image quality assessment (IQA) of contrast distortion. For local details, we lirst roughly remove predicted regions in an image since unpredicted...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2017-12, Vol.47 (12), p.4559-4565
Main Authors: Gu, Ke, Lin, Weisi, Zhai, Guangtao, Yang, Xiaokang, Zhang, Wenjun, Chen, Chang Wen
Format: Article
Language:English
Subjects:
Brain modeling
Contrast distortion
Distortion
Divergence
Entropy
Entropy (Information theory)
Histograms
Image contrast
Image quality
image quality assessment (IQA)
information maximization
no-reference/blind
Predictive models
Quality assessment
saliency
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The general purpose of seeing a picture is to attain information as much as possible. With it, we in this paper devise a new no-reference/blind metric for image quality assessment (IQA) of contrast distortion. For local details, we lirst roughly remove predicted regions in an image since unpredicted remains are of much information. We then compute entropy of particular unpredicted areas of maximum information via visual saliency. From global perspective, we compare the image histogram with the uniformly distributed histogram of maximum information via the symmetric Kullback-Leibler divergence. The proposed blind IQA method generates an overall quality estimation of a contrast-distorted image by properly combining local and global considerations. Thorough experiments on live databases/subsets demonstrate the superiority of our training-free blind technique over state-of-the-art fulland no-reference IQA methods. Furthermore, the proposed model is also applied to amend the performance of general-purpose blind quality metrics to a sizable margin.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2016.2575544