Journalartikel

Jahr der Veröffentlichung: 2023

Seiten: A48-A56

Zeitschrift: Journal of the Optical Society of America A Optics, Image Science and Vision

Bandnummer: 40

Heftnummer: 3

ISSN: 1084-7529

eISSN: 1520-8532

DOI Link: https://doi.org/10.1364/JOSAA.479451

Verlag: Optica Publishing Group

Abstract: 
Color constancy refers to our capacity to see consistent colors under different illuminations. In computer vision and image processing, color constancy is often approached by explicit estimation of the scene's illumination, followed by an image correction. In contrast, color constancy in human vision is typically measured as the capacity to extract color information about objects and materials in a scene consistently throughout various illuminations, which goes beyond illumination estimation and might require some degree of scene and color understanding. Here, we pursue an approach with deep neural networks that tries to assign reflectances to individual objects in the scene. To circumvent the lack of massive ground truth datasets labeled with reflectances, we used computer graphics to render images. This study presents a model that recognizes colors in an image pixel by pixel under different illumination conditions. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

Harvard-Zitierstil: Heidari-Gorji, H. and Gegenfurtner, K. (2023) Object-based color constancy in a deep neural network, Journal of the Optical Society of America A Optics, Image Science and Vision, 40(3), pp. A48-A56. https://doi.org/10.1364/JOSAA.479451

APA-Zitierstil: Heidari-Gorji, H., & Gegenfurtner, K. (2023). Object-based color constancy in a deep neural network. Journal of the Optical Society of America A Optics, Image Science and Vision. 40(3), A48-A56. https://doi.org/10.1364/JOSAA.479451