Does Dehazing Model Preserve Color Information?
| Autor: | Alamin Mansouri, Jessica El Khoury, Jean-Baptiste Thomas |
|---|---|
| Přispěvatelé: | Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Color histogram
Computer science Color balance 02 engineering and technology False color Color space perception 050105 experimental psychology [ INFO.INFO-TI ] Computer Science [cs]/Image Processing 0202 electrical engineering electronic engineering information engineering 0501 psychology and cognitive sciences Computer vision Hue Color difference business.industry Index Terms—dehazing saturation 05 social sciences 020207 software engineering hue Color model [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Lab color space colorimetry contrast enhancement Artificial intelligence business color fidelity |
| Zdroj: | SITIS 2014 SITIS 2014, Nov 2014, Marrakech, Morocco. 2014, 〈10.1109/SITIS.2014.78〉 SITIS SITIS 2014, Nov 2014, Marrakech, Morocco. ⟨10.1109/SITIS.2014.78⟩ |
| DOI: | 10.1109/SITIS.2014.78〉 |
| Popis: | International audience; —Image dehazing aims at estimating the image information lost caused by the presence of fog, haze and smoke in the scene during acquisition. Degradation causes a loss in contrast and color information, thus enhancement becomes an inevitable task in imaging applications and consumer photography. Color information has been mostly evaluated perceptually along with quality, but no work addresses specifically this aspect. We demonstrate how dehazing model affects color information on simulated and real images. We use a convergence model from perception of transparency to simulate haze on images. We evaluate color loss in terms of angle of hue in IPT color space, saturation in CIE LUV color space and perceived color difference in CIE LAB color space. Results indicate that saturation is critically changed and hue is changed for achromatic colors and blue/yellow colors, where usual image processing space are not showing constant hue lines. we suggest that a correction model based on color transparency perception could help to retrieve color information as an additive layer on dehazing algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|