Research on Intelligent Classification System of Ceramic Tiles Based on Machine Vision

摘要

An intelligent classification system of ceramic tiles is introduced in the light of the theory about multi-sensor information fusion. The system includes image acquisition, image processing and intelligent classification of ceramic tiles. The color features and shape features of tile image are synthetically processed using BP neural network. The topological structure of the neural network based on "681" structure is proposed in the system. The numerical calculation and simulation about classification of ceramic tiles is carried out based on MATLAB software. The results show this algorithm is fast and accurate, which can effectively accomplish the classification of comprehensive detection of ceramic tiles.