Automatic defect detection for fabric printing using a deep convolutional neural network

Abstract

ABSTRACT Defect detection is a crucial step in textile and apparel quality control. An efficient defect detection system can ensure the overall quality of the processes and products that are acceptable to consumers. Existing techniques for real-time defect detection tend to vary according to unique manufacturing processes, focal defects and computational algorithms. Although the need is high, research related to automatic printed fabric defect detection processes is not prevalent in academic literatures. This research proposes a novel methodology that demonstrates the application of convolutional neural network (CNN) to classify printing defects based on the fabric images collected from industries. The research also integrated visual geometric group (VGG), DenseNet, Inception and Xception deep learning networks to compare model performance. The results exhibit that the VGG-based models perform better compared to a simple CNN model, suggesting promise for automatic defect detection (ADD) of printed fabrics that can improve profitability in fashion supply chains.