DISCOV: A Neural Model of Colour Vision, with Applications to Image Processing and Classification
OA Version
Citation
Abstract
The DISCOV (Dimensionless Shunting Colour Vision) system models a cascade of primate colour vision cells: retinal ganglion, thalamic single opponent, and two classes of cortical double opponents. A unified model fotmalism derived from psychophysical axioms produces transparent network dynamics and principled parameter settings. DISCOV fits an array of physiological data for each cell type, and makes testable experimental predictions. Properties of DISCOV model cells are compared with properties of conesponding components in the alternative Neural Fusion model. A benchmark testbed demonstrates the marginal computational utility of each model cell type on a recognition task derived from orthophoto imagery.
Description
License
Copyright 2005 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.