Automatic Optical Phase Identification of Microdrill Bits in Printed Circuit Board Manufacturing

Abstract

Inspection of microdrill bits is very important for quality control in Printed Circuit Board (PCB) production. Traditional methods mainly focus on geometric defects inspection. This paper proposes a new automatic optical inspection scheme which can not only be used for geometric defects inspection but also identify the phase of microdrill bits. The paper also investigates the effect of a level set method as a reliable technique for exact segmentation of the cutting plane from the acquired microdrill bit image. Following cutting plane segmentation, we employ an image registration approach to align it, and then three features of the cutting plane, length, width, and normalized end area, are extracted for microdrill bits phase identification. Experimental results show that the proposed method is effective for automatic inspection of microdrill bits in Printed Circuit Board (PCB) manufacturing.