A traffic sign detection system in the vehicle can be of great helpfor the driver. The number of accidents can be reduced by 20\% if thespeed limits are followed. A system that warns the driver about speeding could therefore save lives if the driver reduces the speed.
This work focus on the colour classification used in traffic signdetection methods. Existing methods are compared, and a GeneticAlgorithm is used for optimising parameters used in the existingcolour classification methods.
Cartesian Genetic Programming is used for evolving colour classifiersfor traffic signs, and compared to the existing methods. The evolvedclassifier is tested with three different luminance adjustmentalgorithms.
The results show that the GA is able to find better parameters thanthe reported parameters, and some of the evolved colour classifiers werebetter than the existing methods. The CGP architecture did find betterclassifiers than the existing. The luminance adjustment algorithms didnot result in better classification results.