A No-Reference Objective Image Sharpness Metric Based on the Notion of Just Noticeable Blur (JNB)

By Rony Ferzli, Lina Karam. IEEE Transactions on Image Processing, 2009

794 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/cc8cf162ad4446744cb74b589a071bd9ffc7f543

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. Xiaokang Yang
2. Ming-Hsuan Yang
3. Lei Zhang
4. Guangtao Zhai
5. Dacheng Tao
6. Ke Gu
7. Luc Van Gool
8. Weisi Lin

In Media Technology

1. Guangtao Zhai
2. Xiaokang Yang
3. Ke Gu
4. Weisi Lin
5. A. Bovik
6. Lei Zhang
7. Kede Ma
8. Ming-Hsuan Yang

Citations in the corpus

• 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”
• Perceptual quality prediction on authentically distorted images using a bag of features approach (2016, background): “There are several models proposed in the past that assume a particular kind of distortion and thus extract distortion-specific features (Ferzli & Karam, 2009; Narvekar & Karam, 2009; Varadarajan & Karam, 2008a, 2008b; Sheikh, Bovik, & Cormack, 2005; Chen et al., 2008; Barland & Saadane, 2006;…”
• Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “Ferzli and Karam [224] estimate sharpness based on an HVS-based model which predicts thresholds for just noticeable blur (JNB) the JNB for each edge block is used to estimate the block perceived blur distortions, and the final sharpness estimate is based on a probabilistic combination of these disto”
• Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception (2020, methodology): “ents. The literature offers several solutions for evaluating image sharpness based on norm/histogram of gradients or frequency-domain analysis. In particular, the notions of Just Noticable Blur (JNB) [22] and Perceptual Sharpness Index (PSI) [21] are widely used; they apply non-linear transformation”
• A Feature-Enriched Completely Blind Image Quality Evaluator (2015, background): “Early no-reference IQA (NR-IQA) models commonly operated under the assumption that the image quality is affected by one or several particular kinds of distortions, such as blockiness [1], [2], ringing [3], blur [4], [5], or compression [6]–[9].”
• Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “On the other hand, since SR images usually contain blur and ringing artifacts, the proposed algorithm bears some resemblance to existing metrics for blur and sharpness estimation [29, 30, 31].”
• Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content (2010, methodology): “Evaluations of Q, MSE and JNB [12] on the image Man (256 2 256), and its successively degraded versions.”
• Blind Quality Assessment Based on Pseudo-Reference Image (2018, background): “Ferzli and Karam [20] introduced a concept of just noticeable blur (JNB), which described the minimum blurring needed to be perceived near the edge given a contrast higher than the just noticeable difference (JND).”
• ${\bf S}_{3}$: A Spectral and Spatial Measure of Local Perceived Sharpness in Natural Images (2012, methodology): “The JNB is defined as the threshold with which a human can perceive blurriness around an edge, given a contrast higher than the just noticeable difference.”
• No-Reference Image Quality Assessment in the Spatial Domain (2012, background): “Most existing blind IQA models proposed in the past assume that the image whose quality is being assessed is afflicted by a particular kind of distortion [5]–[11], [17].”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, background): “, blockiness [7], ringing effectiveness [8] and blurriness [9] [10] [11].”
• Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality (2011, methodology): “Edge strengths are quantified using a variety of techniques, including blockkurtosisofDCTcoefficients[15],iterativethresholdingof a gradient image [24], and measuring the probability of blur detection [25] or model the just-noticeable-blur [ 26 ] in an image.”
• A No-Reference Image Blur Metric Based on the Cumulative Probability of Blur Detection (CPBD) (2011, methodology): “However, the metric of [ 2 ] ignores the fact that the blur is not likely to be perceived when it is below the JNB.”
• Perceptual visual quality metrics: A survey (2011, background): “The concepts of just noticeable blockiness and blur have been proposed in [199,46], respectively.”
• No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, methodology): “Inspired by the successfulness of JNB, the cumulative probability of detecting blur (CPDB) algorithm [16] predicts the image sharpness by calculating the probability of blurriness at each edge.”
• Blind/Referenceless Image Spatial Quality Evaluator (2011, background): “The preliminary work in the area of no reference quality assessment started by modeling blur, noise or compression artifacts to address the blurriness, graininess, blockiness and ringing in images [4, 10, 19, 13, 3, 18].”