A computer vision based online quality control system for textile yarns

Yarn quality control is a crucial step in producing high quality textile end products. Online yarn testing can reduce latency in necessary process control by providing rapid insights into yarn quality, leading to pro-duction of superior quality yarns. However, both widely used capacitance based evenness testers and emerging imaging based evenness testing systems are largely offline in operation (i.e. a posteriori). A suitable online system that could be employed to test quality of a variety of yarns in normal industrial processing conditions does not yet exist. In this study, we propose an online evenness testing system for measurement of a certain type of yarn defect called nep by using imaging and computer vision techniques. The developed system directly captures yarn images on a spinning frame and uses Viola-Jones object detection algorithm for real-time detection of nep defects. The validation of nep detection algorithms and comparison of the new method with an existing evenness tester in terms of nep count demonstrated its reasonable defect detection accuracy and promising potential for application in wider yarn spinning industry. (c) 2021 The Authors. Published by Elsevier B.V. CC_BY_NC_ND_4.0