A robust detection method of yarn residue for automatic bobbin management system

With the development of technology in the field of textile industry, roboticized level of textile industry has been paid more attention. In order to improve the production efficiency and reduce the production cost, a robust detection method of yarn residue for automatic bobbin management system is proposed in paper. Specifically, gradient extraction, threshold processing and maximum connected domain analysis are developed to achieve high-efficient detecting of yarn residues. Furthermore, the processing time of yarn detection algorithm is about 30ms, which can fully meet detection speed of 5 pieces per second in the actual bobbin management system. A large number of production tests demonstrate proposed method has a good performance for automatic yarn detecting.