An Advanced Auto-Inspection System for Fishtail Collapse of Micro-router

Abstract

In this paper, an auto-optical inspection system for fishtail collapse of router was proposed. The proposed AOI system first extracts the fishtail image of router by developed mechanism. A method for identifying the center of fishtail was proposed. The I D profile formed by the boundary and center of fishtail is used to segment the fishtail into several blades. We used the end gash to identify one of the blades as the reference blade, so as to provide an orientation-invariant method to solve fishtail image rotation problem. Three invariant features of blade were used as indicators of quality control. The blade with collapse, which area is as small as 0.02 mm x 0.02 mm, could be identified based on the constructed quality control charts. Twenty-five fishtails were used to validate the proposed AOI system. The successful detection rate of the implemented AOI system is up to 99.2% that demonstrated this system achieves the collapse detection accurately and robustly.