AUTOMATIC PCB DEFECT DETECTION USING IMAGE PROCESSING

Abstract

A zero defect PCB ensures a high quality PCB which reflects to reliability and quality of final product.PCB manufacturing is very costly and time consuming process. So that it is necessary to avoid defects during manufacturing process.Especially for products with high level complexity.There may be improper printing of PCB film while printing film for bare PCB from photo which may be result in production of defected PCBs. In this paper, we are processing a technique in which a scanned image of bare PCB film which is printed by photo plotter compareswith a image of PCB which is stored in a computer . From the results we can detect the possible defects like short circuit,track missing,open circuit,dry soldering etc. We apply the machine vision concept to inspect the bare PCB. We first compare a standard PCB image with a PCB image to be inspected using a simple difference algorithm that can detect the defected region.The purpose of this work is to detect defects in PCB film and finding out the defected area to avoid it before PCB fabrication.