MACHINE VISION SYSTEM FOR SEAM WELD DETECTION IN LONGITUDINALLY WELDED PIPES

This paper presents the development of machine vision system fir seam weld defection in longitudinally welded pipes. The system is to be used for positioning operations prior to mechanical working of such parts. Application which uses several different approaches is developed fir this purpose. Experimental results show that robust seam weld defection system can be achieved using simple algorithms with low computational cost.