Computer Vision Analysis of 3D Scanned Circuit Boards for Functional Testing and Redesign

Abstract Testing, repair and overhaul of long-living printed circuit boards (PCBs) is a laborious task if no schematics or layout plans are available. Existing Reverse Engineering (RE) methods are time-consuming, error-prone, and destructive and require reference samples which makes them not feasible for non-OEM users of electronic devices. The Fraunhofer Institute for Production Systems and Design Technology (IPK) in Berlin and the Technical University Berlin have defined a new process for automated and non-destructive schematic and layout reconstruction based on electrical and optical measuring techniques. Current results and innovative approaches using computer vision analysis for recognition of PCB structure aiming to build error-free net lists through a net list merging algorithm are depicted in this paper.