An intelligent and automated 3D surface defect detection system for quantitative 3D estimation and feature classification of material surface defects

•An intelligent and automated 3D surface defect detection system for quantitative 3D estimation and feature classification of material surface defects is proposed, which transforms the defect detection from simple image detection to 3D detection.•A high-precision and high-efficiency global calibration algorithm and 3D reconstruction algorithm are proposed, which quickly reconstruct a complete 3D model of the object and establish the point-image mapping relationship between the color image and the reconstructed 3D object point.•This paper proposes a parallel image matching algorithm based on digital image correlation (DIC) method.•In the process of defect type detection, the detection image containing only the defect area is generated according to the segmentation results of the defect image, which not only improves the detection accuracy but also increases the detection speed.•This paper proposes a robust and fast algorithm for segmenting defect point clouds based on image segmentation results and point-image mapping relationships.