This Article 
 Bibliographic References 
 Add to: 
A Complete and Extendable Approach to Visual Recognition
May 1992 (vol. 14 no. 5)
pp. 534-548

A framework for 3D object recognition is presented. Its flexibility and extensibility are accomplished through a uniform, parallel, and modular recognition architecture. Concurrent and stacked parameter transforms reconstruct a variety of features from the input scene. At each stage, constraint satisfaction networks collect and fuse the evidence obtained through the parameter transforms, ensuring a globally consistent interpretation of the input scene and allowing for the integration of diverse types of information. The final interpretation of the scene is a small consistent subset of the many initial hypotheses about partial features, primitive features, feature assemblies, and 3D objects computed by the various parameter transforms. A complete, integrated, and implemented system that extracts planar surfaces, patches of quadrics of revolution, and planar intersection curves of these surfaces from a depth map viewing 3D objects is described. Experimental results on the recognition behavior of the system are presented.

[1] J. Aloimonos, I. Weiss, and A. Bandyopadhyay, "Active vision," inProc. First Int. Conf. Comput. Vision, June 1987, pp. 35-54.
[2] J. Aloimonos, "Visual shape computation,"Proc. IEEE, vol. 76, no. 8, pp. 899-916, Aug. 1988.
[3] H. S. Baird,Model-Based Image Matching Using Location, Cambridge, MA: MIT Press, 1986.
[4] D. H. Ballard, "Parameter nets: A theory of low level vision," inProc. 7th Int. Joint Conf. Artificial Intell., Aug. 1981, pp. 1068-1078.
[5] B. Bhanu and O. D. Faugeras, "Shape matching of two-dimensional objects,"IEEE Trans. Patt. Anal. Machine Intell., vol. 8, no. 2, pp. 137-155, Mar. 1984.
[6] P. J. Besl and R. C. Jain, "Three-dimensional object recognition,"ACM Comput. Surveys, vol. 17, no. 1, pp. 75-145, Mar. 1985.
[7] P. J. Besl, J. B. Birch, and L. T. Watson, "Robust window operations," inProc. IEEE 2nd Int. Conf. Comp. vision, Dec. 1988, pp. 591-600.
[8] T. O. Binford, "Survey of model-based image analysis systems,"Int. J. Robotics Res., vol. 1, no. 1, pp. 18-64, Spring 1982.
[9] 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 Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 619-638, Sept. 1986.
[10] R. M. Bolle and S. S. Murthy, "Curvature extraction from approximations to image or range data," Tech. Rep. RC 12002, IBM, June 1986.
[11] R. M. Bolle, R. Kjeldsen, and D. Sabbah, "Primitive shape extraction from range data," inProc. IEEE Workshop Comp. Vision, Nov./Dec. 1987, pp. 324-326.
[12] R. M. Bolle, A. Califano, R. Kjeldsen, and R. W. Taylor, "Visual recognition using concurrent and layered parameter networks," IBM Tech. Rep., Nov. 1988; IEEE Conf. Computer Vision and Pattern Recognition, 1989.
[13] R. C. Bolles, P. Horaud, and M. J. Hannah, "3DPO: A three-dimensional part orientation system," inProc. 8th Int. Joint Conf. Artificial Intell., Aug. 1983, pp. 1116-1120.
[14] F. L. Bookstein, "Fitting conic sections to scattered data,"Comp. Graphics Image Processing, vol. 9, no. 1, pp. 56-71, Jan. 1979.
[15] A. Califano, "Feature recognition using correlated information contained in multiple neighborhoods," inProc. 7th Nat. Conf. Artificial Intell., July 1988, pp. 831-836.
[16] A. Califano, R. M. Bolle, and R. W. Taylor, "Generalized neighborhoods: A new approach to complex feature extraction," inProc. IEEE Conf. Comp. Vision Patt. Recogn., June 1989, pp. 192-199.
[17] A. Califano, R. Kjeldsen, and R. M. Bolle, "Data and model driven foveation," inProc. 10th Int. Conf. Patt. Recogn., June 1990, pp. 1-7.
[18] A. Califano and R. M. Bolle, "The multiple window transform," IBM Tech. Rep. RC 16185, Oct. 1990.
[19] A. Califano and R. Mohan, "Multidimesional indexing for recognizing visual shapes," inProc. IEEE Conf. Comp. Vision Patt. Recogn., June 1991, pp. 28-33.
[20] R.T. Chin and C. R. Dyer, "Model-based recognition in robot vision,"ACM Comput. Surveys, vol. 18, no. 1, pp. 67-108, Mar. 1986.
[21] F. S. Cohen and D. B. Cooper, "A decision theoretic approach for 3-D vision," inProc. IEEE Conf. Comp. Vision Patt. Recogn., June 1988, pp. 964-972.
[22] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[23] M. P. Do Carmo,Differential Geometry of Curves and Surfaces. Englewood Cliffs, NJ: Prentice-Hall, 1976.
[24] G. J. Ettinger, "Large hierarchical object recognition using libraries of parameterized model sub-parts,"Patt. Recog., pp. 32-41, 1988.
[25] S. E. Fahlman and G. E. Hinton, "Connectionist architectures for artificial intelligence,"IEEE Comput. Mag., vol. 20, no. 1, pp. 100-109, 1987.
[26] O. D. Faugeras and M. Hebert, "A 3-D recognition and positioning algorithm using geometric matching between primitive surfaces," inProc. 8th Int. Joint Conf. Artificial Intell., Aug. 1983, pp. 996-1002.
[27] J. A. Feldman and D. H. Ballard, "Connectionist models and their properties,"Cognitive Sci., vol. 6, pp. 205-254, 1981.
[28] P. J. Flynn and A. K. Jain, "3D object recognition using invariant indexing of interpretation tables," inProc. IEEE Workshop Directions Automated 'CAD-Based' Vision, June 1991, pp. 115-123.
[29] K. S. Fu, "Robot vision for machine part recognition,"Robotics Sensing Syst., vol. 441, pp. 2-14, Aug. 1983.
[30] R. N. Goldman, "Quadrics of revolution,"IEEE Comp. Graphics Applications, vol. 3, no. 2, pp. 68-76, Mar./Apr. 1983.
[31] W. E. L. Grimson and T. Lozano-Perez, "Model-based recognition and localization from sparse range data or tactile data,"Int. J. Robotics Res., vol. 3, no. 3, pp. 3-34, Fall 1984.
[32] D. G. Hakala, R. C. Hillyard, P. F. Malraison, and B. F. Nource, "Natural quadrics in mechanical design," inProc. CAD/CAM VII, pp. 363-378.
[33] A. R. Hanson and E. M. Riseman, "Visions: A computer system for interpreting scenes," inComputer Vision Systems(A. R. Hanson and E. M. Riseman, Eds.). New York: Academic, 1987.
[34] R. Horaud and R.C. Bolles, "3DPO's strategy for matching three-dimensional objects in range data," inProc. Int. Conf. Robotics, (Atlanta, GA), Mar. 1984, pp. 78-85.
[35] P. V. C. Hough, "Methods and means for recognizing complex patterns, U. S. Patent 3 069 654, 1962.
[36] K. Ikeuchi, "Recognition of 3-D objects using the extended Gaussian image," inProc. 7th Int. Joint. Conf. Artificial Intell., Aug. 1981, pp. 595-600.
[37] J. R. Kender and R. Kjeldsen, "On seeing spaghetti: A radius-finding transform for flexible extruded objects," IBM Tech. Rep. RC 16579, Feb. 1991.
[38] J. Knapman, "3D model identification from stereo data," inProc. First Int. Conf. Comput. Vision, June 1987, pp. 547-551.
[39] J. Koenderink and A. van Doorn, "The internal representation of solid shape with respect to vision,"Biol. Cybern., vol. 32, pp. 211-216, 1979.
[40] D. G. Lowe and T. O. Binford, "The interpretation of three-dimensional structure from image curves," inProc. 7th Int. Joint. Conf. Artificial Intell., Aug. 1981, pp. 613-618.
[41] D. Marr,Vision. New York: W. H. Freeman, 1982.
[42] R. Mohan and R. Nevatia, "Segmentation and description based on perceptual organization," inProc. IEEE Conf. Comput. Vision Patt. Recogn. (San Diego, CA), June 1989.
[43] M. Oshima and Y. Shirai, "Object recognition using three-dimensional information,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-3, no. 4, pp. 353-361, July 1983.
[44] D. Sabbah, "Computing with connections in visual recognition of origami objects,"Cognitive Sci., vol. 9, no. 1, pp. 25-50, Jan./Mar. 1985.
[45] K. Sugihara, "Range-data analysis guided by junction directory,"Artificial Intell., vol. 12, no. 1, pp. 41-69, 1979.
[46] G. Taubin, "Algebraic nonplanar curve and surface estimation in 3-space with applications to position estimation," Tech. Rep. RC 13873, IBM, July 1988.
[47] Technical Arts Corp.,100X 3D Scanner: User's manual and application programming guide. Redmond, WA: 1986.
[48] T. P. Wallace and P. A. Wintz, "An efficient three-dimensional aircraft recognition algorithm using normalized Fourier descriptors,"Comp. Graphics Image Processing, vol. 13, pp. 99-126, 1980.

Index Terms:
uniform parallel architecture; concurrent transforms; information integration; feature extraction; visual recognition; 3D object recognition; flexibility; extensibility; modular recognition architecture; stacked parameter transforms; constraint satisfaction networks; partial features; primitive features; feature assemblies; planar surfaces; quadrics of revolution; planar intersection curves; depth map; parallel processing; pattern recognition; picture processing
R.M. Bolle, A. Califano, R. Kjeldsen, "A Complete and Extendable Approach to Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 5, pp. 534-548, May 1992, doi:10.1109/34.134058
Usage of this product signifies your acceptance of the Terms of Use.