The paper descries a novel method to extract line segments and circular arcs from the image taken by CCD camera for object recognition. Model based matching is one of the widely used techniques of the object recognition in computer vision, and the position and orientation of the objects are decided with referring the extracted line segments and circular arcs. For the precise and stable decisions of the position and orientation, the accurate extractions of characters are required. These characters are. fast and accurately extracted in the proposed method, while its validity is confirmed in some experiments.
We have focuced to the model based matching technique to detect and locate casting parts in the image. To accomplish this, we have explored the edge based optimized feature extraction procedure and feature based model matching technique for object recognition, so that we have realized a practical visual positioning system for castings. Our system is insensitive to changes in lightings or backgrounds in the real works. In this paper, the system, experiments and some applications are described.