RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment

By Rajiv Soundararajan, A. Bovik. IEEE Transactions on Image Processing, 2012

338 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/fa34db4aad1414c88392e0583f5f28c780c7e2e6

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. A. Bovik
2. Guangtao Zhai
3. Ke Gu
4. Weisi Lin
5. Kede Ma
6. Dacheng Tao
7. Xiaokang Yang
8. Lei Zhang

In Media Technology

1. A. Bovik
2. Guangtao Zhai
3. Ke Gu
4. Weisi Lin
5. Dacheng Tao
6. Deepti Ghadiyaram
7. Xiaokang Yang
8. Zhou Wang

Citations in the corpus

• Image Quality Assessment for Fake Biometric Detection: Application to Iris, Fingerprint, and Face Recognition (2014, neutral): “3.”
• No-Reference Image Quality Assessment in the Spatial Domain (2012, methodology): “Our work on NSS based FR QA algorithms [9], [23], [24], more recent RR models [3] and very recent work on NSS based NR QA [12], [13], [25] have led us to the conclusion that visual features derived from NSS lead to particularly potent and simple QA models [26].”
• Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing (2013, methodology): “Let D̄mkf denote a vector of wavelet coefficients in block m of subband k and frame f .”
• Blind Prediction of Natural Video Quality (2014, methodology): “Successful RR-I/VQA algorithms include the wavelet-based RR-IQA algorithm in [14], the divisive normalization transform-based RR-IQA algorithm in [15], the information theoretic RRED index in [16], and the waveletbased RR-VQA method in [17].”
• Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “In [291], Soundarararajan and Bovik presented a framework for RR IQA based on information-theoretic measures of differences between the reference and distorted images by using the entropies of wavelet coefficients.”
• KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment (2019, methodology): “According to the availability of pristine reference images, objective IQA methods are categorized as Full-Reference (FR), e.g., SSIM [5], Reduced-Reference (RR), e.g., RRED [6], and No-Reference (NR), e.g., CORNIA [7], HOSA [8].”
• Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “The second type consists of two RR-IQA models, RRED [15] and FTQM [16].”
• Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (2016, background): “Although there are studies analyzing the influence of the numbers of used features on the performance of RR IQM [33], commonly NR and FR approaches are not studied in an unified framework.”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “Typical FR and RR methods include SSIM [3], FSIM [4], RRED [5] and GMSD [6].”
• Massive Online Crowdsourced Study of Subjective and Objective Picture Quality (2015, background): “This is also true of competitive reduced-reference IQA models [11].”
• The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement (2016, methodology): “vations and analyses on transform domains that have a wide application in image/video processing, RR entropicdifference indexes (RRED) [18], and Fourier transform-based”