No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics

By Yuming Fang, Kede Ma, Zhou Wang, Weisi Lin, Zhijun Fang, Guangtao Zhai. IEEE Signal Processing Letters, 2015

359 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/3d92288070129469d43b39e58bbfdaab6f98e31f

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. Dacheng Tao
2. Kede Ma
3. Xiaokang Yang
4. Wangmeng Zuo
5. Luc Van Gool
6. Kai Zhang
7. Lei Zhang
8. Guangtao Zhai

In Media Technology

1. Weisi Lin
2. Kede Ma
3. Guangtao Zhai
4. Ke Gu
5. Xiaokang Yang
6. Dacheng Tao
7. Wangmeng Zuo
8. Kai Zhang

Citations in the corpus

• End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, background): “Early BIQA models are mainly based on hand-crafted features [3]–[6], which rely heavily on knowledge of the probabilistic structures of our visual world, the mechanisms”
• Reversible data hiding: Advances in the past two decades (2016, background): “In [154], a no-reference quality assessment of the contrast-distorted images is proposed based on natu-”
• A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images (2015, methodology): “The PCQI map produced by the proposed method also indicates local quality variations, which are useful in guiding the future design of advanced image enhancement algorithms.”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, background): “Recently [53], [54] made efforts to measure the contrast distortion and [55] tried to evaluate multiply distortions with gradient information.”
• Perceptual Quality Assessment of Smartphone Photography (2020, background): “Early BIQA models [4, 20–23, 39 ] mainly focus on synthetic distortions,”
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “The sample entropy of intensity histograms is used to identify image anisotropy [40], [41].”
• Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “Scatter plots of BIQME (proposed) and FANG [36] using a leave-one-out cross-validation experiment on six data sets.”
• No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, methodology): “Lately, the IQA of contrast distortion has attracted broad attentions [16-20], since this study can be used for image”