Automatic Image Inspection Method for Detection of Superficial Defects on Circular Top Sides of Cylindrical Ceramic Rods

In the last decades, new computer vision technologies and image processing techniques have been very important in the improvement and automation of manual processes in many technical areas, e.g., in the semiconductor industry. In this paper, we propose an automation method for a currently deployed manual inspection procedure by using image processing techniques, in order to detect and measure superficial defects in the circular surface of circular cylinder RF ceramic rods. In the first step of this method, a color image is acquired from a proposed CCD camera setup, then preprocessing and image processing techniques are applied in order to find curvatures and areas over the circular surface of a cylindrical ceramic rod. Then a features comparison is computed to detect defects in the ceramic rod material. Finally, our results show that the proposed automatic vision method reduces more than ~90% the manual inspection time, as well as reduces in ~75% the number of required factory operators related with the manual inspection. Keywords— machine vision; ceramic rods; defects detection; image processing.