Chromatism Classification System Based on Hybrid Intelligent

Abstract

An online tile Chromatism classification system based on hybrid intelligent was presented. It combined artificial neural network with fuzzy technique and genetic algorithm technique to implement chromatism classification of tile image and added spatial distribution information of color to the old method to improve the precision. Artificial neural network was applied to solve the problem that there is no certain rule because the type of tile is various and the result needs accord to the ones of human vision. Fuzzy technique was applied in the input and output of artificial neural network to increase the precision. Genetic algorithm was introduced to optimize the linking weigh values between the layers, which improved the training speed of the network. The result showed that this method performed better in speed and precise than traditional method or only using neural network techniques.