Surface defect categorization of imperfections in high precision automotive iron foundries using best crossing line profile

Iron casting production is a very important industry that supplies critical products to other key sectors of the economy. In order to assure the quality of the final product, the castings are subject to strict safety controls. One of the most common flaws is the appearance of defects on the surface. In particular, our work focuses on three of the most typical defects in iron foundries: inclusions, cold laps and misruns. We propose a new approach that detects these imperfections on the surface by means of a segmentation method that flags the potential defective regions on the casting and, then, applies machine-learning techniques to classify the regions in correct or in the different types of faults. In this case, we applied BCLP technique. It provides good information to distinguish between edge structures and defects in this kind of images.