890 IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, VOL. 18, NO. 6, DECEMBER 2002 Automated Flaw Detection in Aluminum Castings Based on the Tracking of Potential Defects in a Radioscopic Image Sequence Domingo Mery, Member, IEEE, and Dieter Filbert Abstract—This paper presents a new method for inspecting aluminum castings automatically from a sequence of radioscopic images taken at different positions of the casting. The classic image-processing methods for flaw detection of aluminum castings use a bank of filters to generate an error-free reference image. This reference image is compared with the real radioscopic image, and flaws are detected at the pixels where the difference between them is considerable. However, the configuration of each filter depends strongly on the size and shape of the structure of the casting under inspection. A new two-step technique is proposed to detect flaws automatically and that uses a single filter. First, the method identifies potential defects in each image of the sequence, and second, it matches and tracks them from image to image. The key idea of this paper is to consider as false alarms those potential defects which cannot be tracked in the sequence. The robustness and reliability of the method have been verified on both real data in which synthetic flaws have been added and real radioscopic image sequences recorded from cast aluminum wheels with known defects. Using this method, the real defects can be detected with high certainty. This approach achieves good discrimination from false alarms. Index Terms—Aluminum castings, automated inspection, com- puter vision, flaw detection, image segmentation, X-ray testing. I. INTRODUCTION R ADIOSCOPY is increasingly being used as a tool for non- destructive testing in industrial production. An example is the serial examination of cast light-alloy workpieces used in the car industry, like aluminum wheels and steering gears [1]. The material defects occurring in the casting process such as cavi- ties, gas, inclusions, and sponging must be detected to satisfy the safety requirements; consequently, it is necessary to check 100% of the parts. Since most defects are not visible, X-ray imaging is used for this task. An example of a radioscopic image is shown in Figs. 1 and 2. Manuscript received December 5, 2000; revised February 21, 2002. This paper was recommended for publication by Associate Editor P. Allen and Editor S. Hutchinson upon evaluation of the reviewers’ comments. This work was supported in part by the German Academic Exchange Service (DAAD), in part by the Technical University of Berlin, in part by YXLON International X-Ray GmbH, Hamburg, and in part by the Universidad de Santiago de Chile, Santiago, Chile. This paper was presented in part at the 15th World Conference on Non-Destructive Testing, Rome, Italy, October 15–21, 2000. D. Mery is with the Universidad de Santiago de Chile, Departamento de In- geniería Informática, Santiago, Chile (e-mail: dmery@ieee.org). D. Filbert is with the Technische Universität Berlin, Fakultät IV Elek- trotechnik und Informatik, Institut für Energie- und Automatisierungstechnik, D-10587 Berlin, Germany (e-mail: dieter.filbert@tu-berlin.de). Digital Object Identifier 10.1109/TRA.2002.805646 Fig. 1. Radioscopic image of a casting (see zoom in Fig. 2). Fig. 2. Zoom of Fig. 1 and gray level profile along three rows crossing defects. Over the past decade, radioscopic systems have been intro- duced in the automotive manufacturing industry in order to 1042-296X/02$17.00 © 2002 IEEE