A no-reference perceptual blur metric
By Pina Marziliano, Frédéric Dufaux, Stefan Winkler, Touradj Ebrahimi. Proceedings. International Conference on Image Processing, 2002
679 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/c9ea728db0b0848fc2e69abf2428a634f2a5c8f1
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
In Media Technology
Citations in the corpus
- 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].”
- Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content (2010, background): “Objective quality [2] and sharpness metrics [3], [4] have been developed recently and can generally be divided into three categories: full-reference, reduced-reference and no-reference.”
- Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, background): “[218] estimate blurriness based on average edge widths.”
- UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, background): “Almost all of the earliest BVQA models have been ‘distortion specific,’ meaning they were designed to quantify a specific type of distortion such as blockiness [27], blur [28], ringing [29], banding [30]–[32], or noise [33], [34] in distorted videos, or to assess multiple specific coincident distort”
- ${\bf S}_{3}$: A Spectral and Spatial Measure of Local Perceived Sharpness in Natural Images (2012, methodology): “Another common technique of validating the ability of a sharpness estimator is to examine the algorithm’s performance in monotonically predicting increasing amounts of blur applied to the same image (see, e.g., [3] and [37]).”
- No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, methodology): “In [13], a perceptual model was developed based on a pair of edge detectors for vertical and horizontal directions.”
- Perceptual visual quality metrics: A survey (2011, methodology): “The signal-driven PVQMs can be of FR [140,162], RR [185] or NR [15,100,189].”
- The blur effect: perception and estimation with a new no-reference perceptual blur metric (2007, positive): “Among them, Marziliano et al [3] took into account the edge spreading using the inflection points delimiting an edge.”
- An Underwater Color Image Quality Evaluation Metric (2015, background): “The widely used quality metrics for grayscale images are contrast [19]–[21] or edge sharpness [22]–[24].”
- Perceptual blur and ringing metrics: application to JPEG2000 (2004, methodology): “We then describe the perceptual blur metric, which was initially defined in [7], and use it in the design of a new ringing metric.”
- Using Free Energy Principle For Blind Image Quality Assessment (2015, methodology): “proposed a Blind Blur Metric (MBBM) [22] to measure the spread of image edges from horizontal and vertical directions.”
- Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features (2014, background): “For example, blur can be measured by edge width in the spatial domain [3] or kurtosis in some transformed domain [4]; blockiness introduced by JPEG/JPEG2000 compression can be quantified by statistical differences between adjacent pixels or by the zero-crossing rate around block boundaries [5].”
- Face Spoof Detection With Image Distortion Analysis (2015, methodology): “We utilize two types of blurriness features (denoted as b 1 and b 2 ) that were proposed in [33] and [34], respectively.”