Detection clustering analysis algorithm and system parameters study of the near-point multi-class foreign fiber

In this paper, we investigate a detection algorithm for foreign fiber during the processing of cotton textile. By collecting a large number of samples, we determine the color model and establish its characteristic parameters of a foreign fiber. We found foreign fibers of multiple types (classes) and proposed a classification–recognition algorithm based on clustering analysis. The maximum error of the studied recognition algorithm is 0.012, which meets the requirement to recognize foreign fibers. Through many experiments, the optimal parameters for the foreign fiber detection system were determined, and the fiber recognition rates for different types were obtained. The lowest recognition rate is 85%. This is sufficiently high to reject foreign fibers and reach the standards of the textile industry. Experimental results show that foreign fiber clustering analysis algorithm is feasible, and it not only improves the quality of foreign fiber detection significantly, but also has high theoretical value and practical value.