Image-Based Inspection of Machined Metal Surfaces

Abstract

The purpose of this study is to acquire images through a simple set-up and conduct surface inspection through two techniques based on image processing. First, the shape of the reflected light and the intensity of the surface are used to determine the machined surface state and the presence or absence of a tool mark from different reflection characteristics depending on the machined surface. Second, the photometric stereo technique is used to detect surface scratches through the normal map that recovered the surface.