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

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.

Classification of Circular Knitting Fabric Defects Using MobileNetV2 Model

“…The proposed deep model has a balance in terms of fabric size, accuracy and speed for defect detection. In a recent study, circular knitting fabric defects were detected using 3 different deep learning architectures [20]. Detection of fabric defects with the machine vision mechanism installed on the circular knitting machine is an important and valuable task.…”