Detecting of Circular Knitting Fabric Defects Using VGG16 Architecture

Abstract

Although the conventional image processing methods can detect fabric defects, fabric defect detection is an open research problem due to the diversity of defect types. In this paper, the feasibility of VGG16 deep learning architecture for fabric defect detection has been demonstrated. A new fabric defect database is used. The pre-trained model of VGG16 architecture on the new database is built. Thus, the training time of the model is reduced. The experimental results show that the VGG16 model outperforms the traditional Shearlet transform and GLCM methods.

Classification of Circular Knitting Fabric Defects Using MobileNetV2 Model

“…Recently, deep learning-based defect detection models have been developed. Vgg16 deep learning model was used to detect circular knitting fabric defects [17]. The proposed method produced better results than shearlet transform and GLCM methods.…”