YOLO-Based Defect Detection for Metal Sheets
Po-Heng Chou, Chun-Chi Wang, Wei-Lung Mao
TL;DR
This work tackles metal-sheet defect detection in industrial QA where labeled defect data are scarce. It introduces a YOLO-based detection framework augmented by ConSinGAN, comparing YOLOv3, v4, v7, and v9 variants and showing that YOLOv9 with ConSinGAN achieves a high mAP$_{0.5}$ of 91.3% and a fast detection time of 146 ms. The approach is integrated into manufacturing hardware and a SCADA-based AOI system, enabling practical, real-time inspection on an automated line. The results highlight the practical impact of single-image GAN augmentation for data-scarce industrial defect detection and suggest applicability to other metal components and surface geometries.
Abstract
In this paper, we propose a YOLO-based deep learning (DL) model for automatic defect detection to solve the time-consuming and labor-intensive tasks in industrial manufacturing. In our experiments, the images of metal sheets are used as the dataset for training the YOLO model to detect the defects on the surfaces and in the holes of metal sheets. However, the lack of metal sheet images significantly degrades the performance of detection accuracy. To address this issue, the ConSinGAN is used to generate a considerable amount of data. Four versions of the YOLO model (i.e., YOLOv3, v4, v7, and v9) are combined with the ConSinGAN for data augmentation. The proposed YOLOv9 model with ConSinGAN outperforms the other YOLO models with an accuracy of 91.3%, and a detection time of 146 ms. The proposed YOLOv9 model is integrated into manufacturing hardware and a supervisory control and data acquisition (SCADA) system to establish a practical automated optical inspection (AOI) system. Additionally, the proposed automated defect detection is easily applied to other components in industrial manufacturing.