Metal stamping parts can have a wide variety of defects in different shapes and sizes, and oil and water stains are even more difficult to observe. On the other hand, the brightness of the workpiece also varies during imaging, which makes it very difficult to perform defect detection.By using the Segmentation technology of SolVision AI image platform, AI models are trained with images of various defects with different brightness. After training, the AI model can easily detect various defects on stamping parts, such as: shallow scratches, oil stains, water stains, burrs, etc., which greatly improves the surface quality of the product.