Improving robotic welding in the shipbuilding industry through the recognition of shipbuilding parts by pre-locating corners in images

摘要

A system is proposed that uses a combination of techniques to suggest weld requirements for ships parts. These suggestions are evaluated, decisions are made and then weld parameters are sent to a program generator. A pattern recognition system recognizes shipbuilding parts using shape contour information. Fourier-descriptors provide information and neural networks make decisions about shapes. The system has distinguished between various parts and programs have been generated so that the methods have proved to be valid approaches. The system has recently been improved by pre-processing using a simple and accurate corner-finder to find corners in an edge detected image.