1 April 1998 Model for a color perception system with learning capabilities
Author Affiliations +
Abstract
We present a model for color vision system with learning capabilities. The system adapts to statistical properties of its input. The adaptation is done by utilizing unsupervised learning techniques, as self-organizing feature maps and vectorial boundary adaptation maps. A color difference reflecting statistical properties of input to the system is defined. The model was tested by using color data with different statistics and two different sets of rhodopsin- based color sensors.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Michael Frydrych, Michael Frydrych, Jussi P. S. Parkkinen, Jussi P. S. Parkkinen, Sinikka Parkkinen, Sinikka Parkkinen, Pertti Silfsten, Pertti Silfsten, Timo Jaeaeskelaeinen, Timo Jaeaeskelaeinen, } "Model for a color perception system with learning capabilities", Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304979; https://doi.org/10.1117/12.304979
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Biological models for automatic target detection
Proceedings of SPIE (April 13 2008)
Hexagonal tessellations in image algebra
Proceedings of SPIE (October 31 1990)
Adaptation and perceptual norms
Proceedings of SPIE (February 15 2007)
Color-subspace-based color-coordinate system
Proceedings of SPIE (August 31 1990)

Back to Top