A Composite 3D-2D Visual Surface Defects Inspection Method for Steel Bar Intelligent Manufacturing

Abstract

A composite 3D-2D visual surface defects inspection scheme based on combining active 3D visual inspection with 2D image texture extraction is presented for steel bar intelligent manufacturing. The active 3D visual inspection method is used to detect the surface defects with poor contrast; the 2D image texture extraction method is used to detect the surface defects with tiny width. The variable defects can be identified through fusion of the acquired 3D and 2D information of steel bar. The fundamental derivation of composite 3D-2D visual inspection is given. The experimental results validate and demonstrate the feasibility of the proposed approach.