SoliDAIR Defect Detection Dataset for UC CIE

SoliDAIR Defect Detection Dataset for UC CIE. This dataset contains RGB images of aluminum High-Pressure Die-Casting (HPDC) automotive components, capturing surface defects, thread defects, and normal regions, intended for training and evaluating deep learning models for defect detection and anomaly detection. It includes 2767 images with bounding box annotations in YOLO format, acquired using an industrial area-scan camera under controlled lighting conditions.