Fabric Defect Detection VIA Unsupervised Neural Networks

Surface defect detection is a necessary process for quality control in the industry. Currently, popular neural network based defect detection systems usually need to use a large number of defect samples for training, and it takes a lot of manpower to make marks and clean the subsequent data. This is a time-consuming process, and it makes the whole system less effective. In this paper, a deep neural network based model for fabric surface defect detection is proposed and it only uses positive clean samples for training. Since the proposed model does not collect negative defective samples for learning, the landing time of whole system is greatly reduced. In the experiment, we use RTX3080 in the TensorRT model with 250 FPS, and the detection accuracy is 99%, which is suitable for production lines with real time requirements.