Artificial Color Constancy via GoogLeNet with Angular Loss Function
release_76k7rppz7vfiflaodbxwi2oyym
by
Oleksii Sidorov
2018
Abstract
Color Constancy is the ability of the human visual system to perceive colors
unchanged independently of the illumination. Giving a machine this feature will
be beneficial in many fields where chromatic information is used. Particularly,
it significantly improves scene understanding and object recognition. In this
paper, we propose transfer learning-based algorithm, which has two main
features: accuracy higher than many state-of-the-art algorithms and simplicity
of implementation. Despite the fact that GoogLeNet was used in the experiments,
given approach may be applied to any CNN. Additionally, we discuss design of a
new loss function oriented specifically to this problem, and propose a few the
most suitable options.
In text/plain
format
Archived Files and Locations
application/pdf 749.8 kB
file_75s763i3vnbdnogsuq766euykm
|
arxiv.org (repository) web.archive.org (webarchive) |
1811.08456v1
access all versions, variants, and formats of this works (eg, pre-prints)