A real-time neural system for color constancy
- 1 March 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 2 (2) , 237-247
- https://doi.org/10.1109/72.80334
Abstract
A neural network approach to the problem of color constancy is presented. Various algorithms based on Land's retinex theory are discussed with respect to neurobiological parallels, computational efficiency, and suitability for VLSI implementation. The efficiency of one algorithm is improved by the application of resistive grids and is tested in computer simulations; the simulations make clear the strengths and weaknesses of the algorithm. A novel extension to the algorithm is developed to address its weaknesses. An electronic system that is based on the original algorithm and that operates at video rates was built using subthreshold analog CMOS VLSI resistive grids. The system displays color constancy abilities and qualitatively mimics aspects of human color perception.Keywords
This publication has 34 references indexed in Scilit:
- A Two-Dimensional Analog VLSI Circuit for Detecting Discontinuities in Early VisionScience, 1990
- Quantitative studies of color constancyJournal of the Optical Society of America A, 1988
- Formal connections between lightness algorithmsJournal of the Optical Society of America A, 1986
- Analysis of the retinex theory of color visionJournal of the Optical Society of America A, 1986
- Mechanisms of color constancyJournal of the Optical Society of America A, 1986
- Simultaneous color constancyJournal of the Optical Society of America A, 1986
- Boundary conditions for lightness computation in Mondrian WorldComputer Vision, Graphics, and Image Processing, 1985
- Limitations of color constancyJournal of the Optical Society of America A, 1985
- Digital color image processing within the framework of a human visual modelIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979
- Lightness and Retinex TheoryJournal of the Optical Society of America, 1971