Enhanced Vision-Based Quality Inspection: A Multiview Artificial Intelligence Framework for Defect Detection

Automated defect detection is a critical component of modern industrial quality control. However, it is particularly difficult to identify subtle defects such as scratches on metallic surfaces. Therefore, this paper investigates the effectiveness of multiview deep learning approaches for improved defect detection by implementing and comparing early and late fusion methodologies. We propose MV-UNet, a novel early fusion architecture that aligns and aggregates multiview features using a transformation block to enhance detection accuracy. To evaluate performance, we conduct our experiments on a recorded metallic plates dataset, comparing the traditional single-view inspection to both late and early fusion methods. Our results demonstrate that both the early and late fusion methods improve detection accuracy over the mono-view baseline, with our MV-UNet achieving the hightest F1-score (0.942). Additionally, we introduce adapted precision-recall metrics designed for segmentation-based defect detection, addressing the limitations of traditional IoU-based evaluations. These tailored metrics more accurately reflect defect localization performance, particularly for thin, elongated scratches. Our findings highlight the advantages of early fusion for industrial defect detection, providing a robust and scalable approach to multiview analysis.