Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

TL;DR

This paper presents a CNN-based system for detecting and segmenting manufacturing defects in X-ray images, leveraging transfer learning to improve accuracy and efficiency in quality control processes.

Contribution

It introduces a defect detection and segmentation system using Mask R-CNN with transfer learning, achieving state-of-the-art accuracy on X-ray datasets with reduced training data requirements.

Findings

Higher defect detection accuracy with combined detection and segmentation training

Transfer learning significantly improves model performance with limited data

System achieves real-time performance suitable for production environments

Abstract

Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, 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 GRIMA database of X-ray images (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.