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

By Ke Gu, Weisi Lin, Guangtao Zhai, Xiaokang Yang, Wenjun Zhang, Chang Wen Chen. IEEE Transactions on Cybernetics, 2017

313 citations recorded by the source corpus.

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 first 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 five databases/subsets demonstrate the superiority of our training-free blind technique over state-of-the-art full- and 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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/984ccc4a9a3c6c4541c5efa1f11eb9172ce89d5e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Wenhan Yang
2. Jiaying Liu
3. Zongming Guo
4. Wen-Huang Cheng
5. Mading Li
6. Xutong Ren
7. Xiaoyan Sun
8. Chongyi Li

In Media Technology

1. Wenhan Yang
2. Jiaying Liu
3. Zongming Guo
4. Chongyi Li
5. Vishal M. Patel
6. Chen Change Loy
7. Chunle Guo

Citations in the corpus

• LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model (2020, background): “Namely, blind tone-mapped quality index (BTMQI) [44], no-reference image quality metric for contrast distortion (NIQMC) [45] and blind sharpness metric in the autoregressive parameter space (ARISMC) [46] to evaluate the enhancement results comprehensively.”
• Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model (2018, background): “From NIQMC and CPCQI values, we can discover a certain pattern with respect to ω. Fig.”