Measuring colorfulness in natural images

By D. Hasler, Sabine Süsstrunk. IS&T/SPIE Electronic Imaging, 2003

713 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6e67e8c1f3381822725576f271a9deb21d05c0d3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

An Underwater Color Image Quality Evaluation Metric (2015, methodology): “Hasler and Suesstrunk [16] show that colourfulness can be represented effectively with a combination of image statistics.”
Human-Visual-System-Inspired Underwater Image Quality Measures (2016, methodology): “UICM, Hasler’s color measure [12], and the CIQI colorfulness measure [13] values are listed in Table II.”
The Konstanz natural video database (KoNViD-1k) (2017, methodology): “2) Colorfulness: For this attribute we used Hasler and Suesstrunk’s metric reported in [6].”
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, background): “Here we expand the set of attributes to include six low-level features including brightness, contrast, colorfulness [17], sharpness, spatial information (SI), and temporal information (TI), thereby providing a larger visual space in which to plot and analyze content diversities of the three”
A study on the impact of product images on user clicks for online shopping (2011, methodology): “We use an expression that appeared in a paper by Hasler [2] based on sRGB color space.”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, methodology): “• colorfulness using the popular model in [58].”
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “Through key features extraction and a psychophysical category scaling experiment, Hasler and Suesstrunk [48] have contributed a practical met-”
Stable Bias: Evaluating Societal Representations in Diffusion Models (2023, positive): “Users can choose a specific image as a starting point—for example, a photo of a Black woman generated by a specific TTI system—and explore that photo’s neighborhood either by colorfulness (as defined by [27]), or by a bag-of-visual-words [61] TF-IDF index.”
GANalyze: Toward Visual Definitions of Cognitive Image Properties (2019, methodology): “For colorfulness, we used the metric proposed by [21], and for redness we computed the normalized number of red pixels.”
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment (2019, methodology): “We conducted preliminary subjective studies and kept four measures that are well-correlated with human perception, namely brightness, col-orfulness [49], Root Mean Square (RMS) contrast, and sharpness [50].”
Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging (2015, methodology): “5(R + G)− B [30], and the range of pixel values is x = 1 .”
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (2019, background): “We directly estimate the color according to [30] to select images with rich color.”