Affiliation:
1. Hubei Digital Textile Equipment Key Laboratory, Wuhan Textile University, China
2. The Advanced Textile Technology Innovation Center, Jianhu Laboratory, China
3. School of Mechanical and Electrical Engineering, Zhongyuan University of Technology, China
Abstract
We focus in this review on the pre-processing devices used, the cotton pipeline, the rejection system, the acquisition and processing of information from images of raw cotton, and measurements of the rate of dynamic flow of the cotton stream. The results show that raw cotton fluffs into a material with a more uniform thickness, and adequately separating the cotton bunch can improve the subsequent detection and removal of foreign fibers in it. Moreover, research that combines the structure of the cotton pipeline with the optimization of the structure of the nozzle plate is important for improving the rejection of foreign fibers in cotton. Furthermore, a combination of multiple light sources and arrays of charge-coupled device cameras can improve the quality of images of raw cotton, but such key parameters as the power and wavelength of the source of light need to be optimized. As any single algorithm for image segmentation and feature extraction struggles to adapt to the identification of different kinds of foreign fibers, it is important to explore a combination of algorithms to this end, and to develop new techniques of foreign fiber detection based on deep learning. Finally, the structure and parameters of processing of the system for the identification and removal of foreign fibers are important, including the relative distance between the sensor and the nozzle, the width of the detection channel, and the rate of flow of the cotton stream.