A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine

Authors : Halil Ibrahim Çelik, Lale Canan Dülger, Burak Öztaş, Mehmet Kertmen, Elif Gültekin

Pages : 344-352

Doi:10.32710/tekstilvekonfeksiyon.1017016

View : 22 | Download : 25

Publication Date : 2022-12-31

Article Type : Research

Abstract :Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.
Keywords : Circular knitting machine, Knitted fabric, Defect detection, Deep learning, Convolutional neural network (CNNs)