Measuring colorfulness in natural images
Open accessAbstract
We want to integrate colourfulness in an image quality evaluation framework. This quality framework is meant to evaluate the perceptual impact of a compression algorithm or an error prone communication channel on the quality of an image. The image might go through various enhancement or compression algorithms, resulting in a different -- but not necessarily worse -- image. In other words, we will measure quality but not fidelity to the original picture. While modern colour appearance models are able to predict the perception of colourfulness of simple patches on uniform backgrounds, there is no agreement on how to measure the overall colourfulness of a picture of a natural scene. We try to quantify the colourfulness in natural images to perceptually qualify the effect that processing or coding has on colour. We set up a psychophysical category scaling experiment, and ask people to rate images using 7 categories of colourfulness. We then fit a metric to the results, and obtain a correlation of over 90% with the experimental data. The metric is meant to be used real time on video streams. We ignored any issues related to hue in this paper.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
The CIECAM02 color appearance model
Moroney, N. M., Fairchild, M. D., Hunt, R. W. G., et al. (2002) · RIT Scholar Works (Rochester Institute of Technology) · Cited by 311 · see citing works
Psychometric Scaling: A Toolkit for Imaging Systems Development
Engeldrum, P. G. (2000) · Medical Entomology and Zoology · Cited by 266 · see citing works
Meet iCAM: A Next-Generation Color Appearance Model
Fairchild, M. D., & Johnson, G. M. (2002) · Color and Imaging Conference · doi:10.2352/cic.2002.10.1.art00008 · Cited by 85 · see citing works
Video quality evaluation for Internet streaming applications
WINKLER, S. S., & Campos, R. (2003) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.477766 · Cited by 67 · see citing works
Perceptually optimal color reproduction
Yendrikhovski, S. N., Blommaert, F. J. J., & de Ridder, H. (1998) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.320117 · Cited by 53 · see citing works
Li, C., Luo, M. R., Hunt, R. W. G., et al. (2002) · Color and Imaging Conference · doi:10.2352/cic.2002.10.1.art00007 · Cited by 33 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · see citing works
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3072221 · Cited by 363 · see citing works
“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”
Background
- Authors
- Hasler, D., & Suesstrunk, S. E.
- Venue
- SPIE Proceedings
- Publisher
- SPIE
- Published
- 2003-06-12
- Volume
- 5007
- Pages
- 87
- ISSN
- 0277-786X (ISSN-L)
- OpenAlex
- W2245625259
- Cited by
- 729
- References
- 6
- Citations by year
- 2026: 59 · 2025: 86 · 2024: 67 · 2023: 68 · 2022: 61 · 2021: 60 · 2020: 46 · 2019: 47 · 2018: 37 · 2017: 53 · 2016: 27 · 2015: 35 · 2014: 17 · 2013: 18 · 2012: 11
- FWCI
- 1.48
- Type
- conference paper
- Language
- en
- Open access
- green
- infoscience.epfl.ch
- Locations
- Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Color Science and Applications
- Social Sciences › Psychology › Social Psychology › Color perception and design
- Keywords
- colourfulness, image quality assessment, natural images, color appearance models, psychophysical scaling, image compression, real-time video streams, color perception
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
