3D INSPECTION SYSTEM IN CERAMIC TILES SURFACES WITH RANGE IMAGES

Computer Vision Group,Universidad Polit´ecnica de Valencia, Spainarodas, jvalient, floreal f@disca.upv.esgKeywords: Surface inspection, computer vision system, 3D defect detection, quality control, range images.Abstract: In this paper we propose a system to characterize 3D defects of range images, which can be combined withtraditional surface inspection methods in an industrial environment for ceramic tiles inspection. Our applica-tion has the advantage of learning the geometric features of the ceramic pieces, creating a unique 3D modelagainst which we compare the test pieces. In addition to this, the system includes a robust learning phase,which discards tiles with defects impossible to see from a human expert and a more stringent inspection inareas with low uncertainty. Experiments with real data were performed. Our data consist of tiles of differenttypes, shapes and silk-screen of ceramic tiles. Results are promising for tiles with a straight orientation, over99 % of defects are correctly classified.