Back to articles
JPI-first
Volume: 29 | Article ID: art00016
Image
Color Conversion in Deep Autoencoders
  DOI :  10.2352/J.Percept.Imaging.2021.4.2.020401  Published OnlineMarch 2021
Abstract

While RGB is the status quo in machine vision, other color spaces offer higher utility in distinct visual tasks. Here, the authors have investigated the impact of color spaces on the encoding capacity of a visual system that is subject to information compression, specifically variational autoencoders (VAEs) with a bottleneck constraint. To this end, they propose a framework-color conversion-that allows a fair comparison of color spaces. They systematically investigated several ColourConvNets, i.e. VAEs with different input-output color spaces, e.g. from RGB to CIE L* a* b* (in total five color spaces were examined). Their evaluations demonstrate that, in comparison to the baseline network (whose input and output are RGB), ColourConvNets with a color-opponent output space produce higher quality images. This is also evident quantitatively: (i) in pixel-wise low-level metrics such as color difference (ΔE), peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM); and (ii) in high-level visual tasks such as image classification (on ImageNet dataset) and scene segmentation (on COCO dataset) where the global content of reconstruction matters. These findings offer a promising line of investigation for other applications of VAEs. Furthermore, they provide empirical evidence on the benefits of color-opponent representation in a complex visual system and why it might have emerged in the human brain.

Subject Areas :
Views 51
Downloads 10
 articleview.views 51
 articleview.downloads 10
  Cite this article 

Arash Akbarinia, Raquel Gil-Rodríguez, "Color Conversion in Deep Autoencodersin Proc. IS&T 29th Color and Imaging Conf.,  2021,  pp 89 - 98,  https://doi.org/10.2352/J.Percept.Imaging.2021.4.2.020401

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
72010350
Color and Imaging Conference
color imaging conf
2166-9635
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA