M. Ebner. Pattern Recognition Letters, 27 (11):
1220--1229(августа 2006)Evolutionary Computer Vision and Image Understanding.
DOI: doi:10.1016/j.patrec.2005.07.020
Аннотация
The ability to compute colour constant descriptors of
objects in view irrespective of the light illuminating
the scene is called color constancy. We have used
genetic programming to evolve an algorithm for colour
constancy. The algorithm runs on a grid of processing
elements. Each processing element is connected to
neighbouring processing elements. Information exchange
can therefore only occur locally. Randomly generated
colour Mondrians were used as test cases. The evolved
individual was tested on synthetic as well as real
input images. Encouraged by these results we developed
a parallel algorithm for colour constancy. This
algorithm is based on the computation of local space
average colour. Local space average colour is used to
estimate the illuminant locally for each image pixel.
Given an estimate of the illuminant, we can compute the
reflectances of the corresponding object points. The
algorithm can be easily mapped to a neural architecture
and could be implemented directly in CCD or CMOS chips
used in todays cameras.
%0 Journal Article
%1 Ebner:2006:PRL
%A Ebner, Marc
%D 2006
%J Pattern Recognition Letters
%K Colour Local algorithms, average colour constancy, genetic programming, space
%N 11
%P 1220--1229
%R doi:10.1016/j.patrec.2005.07.020
%T Evolving color constancy
%V 27
%X The ability to compute colour constant descriptors of
objects in view irrespective of the light illuminating
the scene is called color constancy. We have used
genetic programming to evolve an algorithm for colour
constancy. The algorithm runs on a grid of processing
elements. Each processing element is connected to
neighbouring processing elements. Information exchange
can therefore only occur locally. Randomly generated
colour Mondrians were used as test cases. The evolved
individual was tested on synthetic as well as real
input images. Encouraged by these results we developed
a parallel algorithm for colour constancy. This
algorithm is based on the computation of local space
average colour. Local space average colour is used to
estimate the illuminant locally for each image pixel.
Given an estimate of the illuminant, we can compute the
reflectances of the corresponding object points. The
algorithm can be easily mapped to a neural architecture
and could be implemented directly in CCD or CMOS chips
used in todays cameras.
@article{Ebner:2006:PRL,
abstract = {The ability to compute colour constant descriptors of
objects in view irrespective of the light illuminating
the scene is called color constancy. We have used
genetic programming to evolve an algorithm for colour
constancy. The algorithm runs on a grid of processing
elements. Each processing element is connected to
neighbouring processing elements. Information exchange
can therefore only occur locally. Randomly generated
colour Mondrians were used as test cases. The evolved
individual was tested on synthetic as well as real
input images. Encouraged by these results we developed
a parallel algorithm for colour constancy. This
algorithm is based on the computation of local space
average colour. Local space average colour is used to
estimate the illuminant locally for each image pixel.
Given an estimate of the illuminant, we can compute the
reflectances of the corresponding object points. The
algorithm can be easily mapped to a neural architecture
and could be implemented directly in CCD or CMOS chips
used in todays cameras.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Ebner, Marc},
biburl = {https://www.bibsonomy.org/bibtex/2e801527698fbefec0ae6a27193d22594/brazovayeye},
doi = {doi:10.1016/j.patrec.2005.07.020},
interhash = {97ad9a4b5ae02b384b10646991faf393},
intrahash = {e801527698fbefec0ae6a27193d22594},
journal = {Pattern Recognition Letters},
keywords = {Colour Local algorithms, average colour constancy, genetic programming, space},
month = {August},
note = {Evolutionary Computer Vision and Image Understanding},
number = 11,
pages = {1220--1229},
timestamp = {2008-06-19T17:39:05.000+0200},
title = {Evolving color constancy},
volume = 27,
year = 2006
}