Symbolic Surface Descriptors
Object recognition plays a very important role in many stages of manufacturing. In this paper, we discuss our approach to recognizing objects in range images using CAD databases. The models in the databases will be used to generate recognition strategies. We present some results on symbolic surface descriptors that will play an important role in both the generation of the strategy and in the recognition of objects. Symbolic surface descriptors represent global features of an object and do not change when the object is partially occluded, while local features (such as corners or edges) may disappear entirely. We have developed a technique to segment surfaces and compute their polynomial surface descriptors. In this paper we present results of our study to determine which different types of surface descriptors (such as cylindrical, spherical, elliptical, hyperbolic, etc.) can be reliably recovered from biquadratic equation models of various surfaces.
KeywordsObject Recognition Surface Type Range Image Quadric Surface Symbolic Descriptor
Unable to display preview. Download preview PDF.
- P. Allen and R. Bajcsy. “Object Recognition Using Vision and Touch”, Proc. 9th Intl. Joint Conf. on Artificial Intelligence, pp. 1131–1137, 1985.Google Scholar
- P.J. Besl and R. Jain. “Segmentation Through Symbolic Surface Descriptions”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 77–85, June 1986.Google Scholar
- R.M. Bolle and D.B. Cooper. “On Optimally Combining Pieces of Information, with Application to Estimating 3-D Complex-Object Position from Range Data”, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 619–638, Sept. 1986.Google Scholar
- M. Brady, J. Ponce, A. Yuille and H. Asada. “Describing Surfaces”, Proc. 2nd Intl. Symp. on Robotics Research, M.I.T. Press, 1985.Google Scholar
- T.J. Fan, G. Medioni and R. Nevatia. “Description of Surfaces from Range Data Using Curvature Properties”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 86–91, 1986.Google Scholar
- O.D. Faugeras and M. Hebert. “A 3-D Recognition and Positioning Algorithm Using Geometrical Matching between Primitive Surfaces”, Proc. 8th Intl. Joint Conf. on Artificial Intelligence, pp. 992–1002, 1983.Google Scholar
- O.D. Faugeras, N. Ayache and B. Faverjon. “A Geometric Matcher for Recognizing and Positioning 3-D Rigid Objects”, IEEE Conf. on Artificial Intelligence Applications, pp. 218–224, 1984.Google Scholar
- M. Hebert and T. Kanade. “The 3D-Pronle Method for Object Recognition”, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 458–463, 1985.Google Scholar
- P. Horaud and R.C. Bolles. “3DPO’s Strategy for Matching Three-Dimensional Objects in Range Data”, Proc. Intl. Conf. on Robotics, pp. 78–85, 1984.Google Scholar
- T.F. Knoll and R. Jain. “Recognizing Partially Visible Objects Using Feature Indexed Hypotheses”, IEEE J. Robotics and Automation, Vol. RA-2, No. 1, pp. 3–13, 1986.Google Scholar
- D.E. Rumelhart and J.L. McClelland. Parallel Distributed Processing, Vol. 1, M.I.T. Press, 1986.Google Scholar
- J. Ponce and M. Brady. “Toward a Surface Primal Sketch”, Proc. IEEE Intl. Conf. on Robotics and Automation, pp. 420–425, 1985.Google Scholar