The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement

By Ke Gu, Guangtao Zhai, Weisi Lin, Min Liu. IEEE Transactions on Cybernetics, 2016

374 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/4dfffc8ce3a2f1b788963058d5dd2d96f326bd4c

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. Xiaokang Yang
3. Weisi Lin
4. Ke Gu
5. Guangtao Zhai
6. Peyman Milanfar
7. J. Qiao
8. Wenjun Zhang

In Media Technology

1. Ke Gu
2. Weisi Lin
3. Guangtao Zhai
4. Xiaokang Yang
5. Dacheng Tao
6. J. Qiao
7. Wenjun Zhang
8. Hossein Talebi

Citations in the corpus

• Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “In this comparison, apart from our BIQME method, we mainly consider the following 13 state-of-the-art IQA models, which encompass: 1) FR FSIM [8], LTG [9], VSI [10], PSIM [11], and C-PCQI; 2) RR RRED [15], FTQM [16], RIQMC [30], and QMC [34]; and 3) NR NIQE [19], IL-NIQE [20],”
• NIMA: Neural Image Assessment (2017, background): “Similarly, image quality predictors can be used to adjust parameters of enhancement techniques [24].”
• No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, methodology): “Spearman rank-order correlation coefficient (SRCC), one of the most popular performance metrics and has been used to find the suitable parameters in quite a few IQA approaches such as [9] and [10], is employed for optimization in this implementation.”
• A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement (2017, background): “VIF provides consistently high value of correlation be-tween subjective MOS (Mean Opinion Score) and its scores, as shown in [51].”
• No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, neutral): “To cope with this task, the RR image quality metric for contrast change (RIQMC) was devised based on phase congruency and information statistics of the histogram, acquiring superior performance beyond existing models and managing to enhance original natural images [20].”