Automated generation of inspection routines for SMD components

Automated Visual Inspection (AVI) systems are nowadays considered an integral part in the assembly of Surface Mounted Devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD based products with the consequent obsolescence of the inspection systems already in the production line. The general goal of this research is to develop a self-training system for the inspection of SMD components. In this paper we describe the general methodology being followed to develop such a system and in particular in the methodology being used for the first part of the process, i.e., automated feature selection. The objective of the feature selection process is to reduce the computational time and cost of the inspection systems such that the set of features selected minimizes the inspection errors of the systems in the inspection phase.