Blind Image Quality Assessment Using a General Regression Neural Network

By Chaofeng Li, A. Bovik, Xiaojun Wu. IEEE Transactions on Neural Networks, 2011

299 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/e4f91e4b0311cb50923a1e46531ef899d61bdce4

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. Jongyoo Kim
4. Sanghoon Lee
5. Guangtao Zhai
6. Lei Zhang
7. Weisi Lin
8. Zhou Wang

In Media Technology

1. Jongyoo Kim
2. Sanghoon Lee
3. Kede Ma
4. Guangtao Zhai
5. Weisi Lin
6. Dacheng Tao
7. Ke Gu
8. Zhou Wang

Citations in the corpus

• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “Phase congruency [58] is such a feature that identifies perceptually significant image features at spatial locations where Fourier components are maximally in-phase [40].”
• Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “Typical objective IQA approaches are developed using mathematical models, neural networks [4], and learning systems [5] to approximate real human judgments of image quality.”
• Unsupervised feature learning framework for no-reference image quality assessment (2012, background): “Existing general-purpose NR-IQA algorithms can be broadly classified as (1) Natural scene statistics (NSS) based approaches [13, 14, 17, 18] and (2) Training-based approaches [7, 22, 29].”
• RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution (2019, unknown): “In [23], Li et al.”
• Deep CNN-Based Blind Image Quality Predictor (2019, methodology): “[13] employed a general regression neural network relative to phase congruency, entropy, and image gradients.”
• Fully Deep Blind Image Quality Predictor (2017, background): “Li et al. employed a general regression neural network relative to phase congruency (PC), entropy, and image gradients [34].”
• A Feature-Enriched Completely Blind Image Quality Evaluator (2015, methodology): “Representative methods belonging to this category include [11]–[18] and they share a similar architecture.”
• Blind Image Quality Assessment via Deep Learning (2015, methodology): “[11] used a general regression network to regress the image features to quality scores.”
• Convolutional Neural Networks for No-Reference Image Quality Assessment (2014, methodology): “[8] applied a general regression neural network that takes as input perceptual features including phase congruency, entropy and the image gradients.”
• The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement (2016, methodology): “In fact, the PC has been validly incorporated into many IQA techniques [51], [52].”