Using Cognex Deep Learning, it is easy to analyze metal piston weld seams by yourself. Engineers can use the Cognex Deep Learning defect detection tool in supervised mode to train the software on a set of "bad" sample images that represent various welding anomalies (including weld overlap) and a set of "good" sample images that do not have any anomalies. In this way, all anomalies, whether they are required or the main cause of rejection, can be identified as defects. In the second part of the inspection, engineers can use the classification tool to classify weld defects by category. By combining the defect detection tool with the classification tool, automotive manufacturers can ensure that the inspection system identifies all welds and successfully classifies overlapping welds.