ADAPTIVE CHANNEL SELECTION FOR IMPROVING CHROMATIC DISCRIMINATION IN COLOR PATTERN-RECOGNITION

A new method to select colour channels in colour pattern recognition s ystems is presented to improve the chromatic discrimination capability . Instead of using the conventional RGB decomposition, we propose to u se other narrow-band channels that can show more variations of the obj ects of a scene. This method exploits the spectral information of the objects and is useful in discriminating objects with similar colour. S imulated and experimental optical correlation results, for scenes with objects of similar colours, are presented and discussed. Model and na tural objects are considered and a variety of ranges are studied.