A complete MLOps pipeline for steel surface defect detection using YOLOv8 and the NEU Steel Surface Defect Database. This project demonstrates end-to-end machine learning operations from data ...

Use ResNet50 deep learning model to predict defects on steel sheets and visually localize the defect using Res-UNET model. This project aims to predict surface defects on steel sheets from images.

Abstract: Surface defect detection is essential for industrial product quality assurance. To address challenges including large-scale variations, diverse defect morphologies, high inter-class ...

Abstract: With its excellent surface quality and good mechanical properties, steel has become an indispensable and important material in the machinery manufacturing industry. However, in the process ...

Dislocations can save lives. This stems from the fact that the one-dimensional defects in a metal play an important role when the material deforms: for example, when a car body panel crumples in an ...