An automated cotton contamination detection system based on co-occurrence Matrix contrast information

An automated cotton contamination detection system is economical and efficient to guarantee higher textile quality and lower production cost. A vision system is proposed to realize a fully automated cotton inspection scheme. In the system, cotton contamination is detected based on texture feature. Gray Level Co-occurrence Matrix (GLCM) algorithm is adopted to detect the sharp contrast objects. A rotating search filter based on contextual information is designed to remove the unwanted edges and locate the coordinate of impurities. Experiments using real imagery show that the proposed vision system is suitable to distinguish impurities mixed in cotton.