No-reference quality assessment using natural scene statistics: JPEG2000

By Hamid R. Sheikh, A. Bovik, Lawrence K. Cormack. IEEE Transactions on Image Processing, 2005

652 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bb97c4190b044484d3bab756070a3f1f79797168

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

Citations in the corpus

Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “Quality is estimated in [257] by first computing features based on these probabilities from all wavelet subbands and then applying a nonlinear combination of the features.”
Image information and visual quality (2006, methodology): “In [31], an NSS model was used to design a no-reference image QA method for images distorted with the JPEG2000 compression artifacts.”
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, background): “Therefore, statistics of raw [4], [6], [46], [47] and normalized [48], [49] wavelet coefficients, and wavelet coefficient correlations in the neighborhood [10], [29], [50]–[52] can be individually or jointly modeled as image naturalness measurements.”
Blind image quality evaluation using perception based features (2015, methodology): “The algorithms in [1], [2], [3], [4], [5] require prior information about the type of distortion (like JPEG, JPEG2000, Blur, ringing, etc.”
Blind Image Quality Assessment Using a General Regression Neural Network (2011, methodology): “For example, in [ 20 ] a natural scene statistics (NSS) model is used to define a blind measure of the quality of images compressed by JPEG 2000.”
The SURE-LET Approach to Image Denoising (2007, background): “Besides the above mentioned general criterions, other reference-free quality assessment measures have been proposed, often bound to a specific type of distortion [10,11].”
F Mean Squared Error: Love It or Leave It? (2009, background): “For example, many image fidelity measurement methods have been developed specifically for block-discrete cosine transfer (DCT) [16], [17] and wavelet-based image compression [18], [19].”
Using Free Energy Principle For Blind Image Quality Assessment (2015, methodology): “We first evaluate the performance of the proposed NFERM with a total number of fifteen IQA approaches on the LIVE database [39]: 1) classical FR PSNR, SSIM [4], MS-SSIM [5]; 2) popular blind distortion-specific WNJE [21], MBBM [22], Sheikh [23], SINE [24], JNB [26], CPBD [27], NFEQM [17]; 3) state-o”
RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment (2012, methodology): “One approach is to devise NR algorithms for a specific type of distortion only [6], [7], [8].”
End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, background): “, JPEG/JPEG2000 compression [35], [36] and blurring artifacts [37].”
Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, background): “Early BIQA research aims to evaluate images corrupted by specific distortion types, e.g., blockiness [7], ringing effectiveness [8] and blurriness [9]–[11].”
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality (2011, methodology): “In the past, such NSS-based QA algorithms have been successfully deployed for FR IQA [5], [6], for RR IQA [3], [4], and to a small extent, for NR IQA [ 11 ].”
Assessing the aesthetic quality of photographs using generic image descriptors (2011, background): “salt and pepper noise, jpeg artifacts, ringing) [23].”
Learning without Human Scores for Blind Image Quality Assessment (2013, methodology): “The current blind image quality assessment (BIQA) methods can be classified into two categories: distortion specific methods [1,8,9,18,25] and distortion independent methods [4,10,13,14,16,17,21,27].”
An information fidelity criterion for image quality assessment using natural scene statistics (2005, methodology): “In [32], an NSS model was used to design a no-reference image QA method for images distorted with the JPEG2000 compression artifacts.”
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].”
Reduced-reference image quality assessment using a wavelet-domain natural image statistic model (2005, methodology): “Therefore, we extract the histogram bins of the wavelet coecients as the features at the receiver side and use them to numerically (similar to Eq. ( 6 )) evaluate d(pmkq).”
Quality-aware images (2006, background): “They have also been used for image quality assessment purposes (e.g., [8]).”