Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning
Max K. Ferguson, Ronay Ak, Yung-Tsun Lee, Kincho H. Law
Automatic detection of defects in metal castings is a challenging task, owing to the rare occurrence and variation in appearance of defects. However, automatic defect detection systems can lead to significant increases in final product quality. Convolutional neural networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this work, a system is proposed for the identification of casting defects in X-ray images, based on the mask region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GDXray Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.
The ASTM Journal of Smart and Sustainable Manufacturing
, Ak, R.
, Lee, Y.
and Law, K.
Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning, The ASTM Journal of Smart and Sustainable Manufacturing, [online], https://doi.org/10.1520/SSMS20180033, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=926369
(Accessed December 3, 2023)