This Article 
 Bibliographic References 
 Add to: 
Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings
January 1993 (vol. 15 no. 1)
pp. 19-36

Primal access recognition of visual objects (PARVO), a computer vision system that addresses the problem of fast and generic recognition of unexpected 3D objects from single 2D views, is considered. Recently, recognition by components (RBC), which is a new human image understanding theory, based on some psychological results, has been proposed as an explanation of how PARVO works. However, no systematic computational evaluation of its many aspects has yet been reported. The PARVO system discussed is a first step toward this goal, since its design respects and makes explicit the main assumptions of the proposed theory. It analyzes single-view 2D line drawings of 3D objects typical of the ones used in human image understanding studies. It is designed to handle partially occluded objects of different shape and dimension in various spatial orientations and locations in the image plane. The system is shown to successfully compute generic descriptions and then recognize many common man-made objects.

[1] M. D. Levine,Vision in Man and Machine. New York: McGraw-Hill, 1985.
[2] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[3] S. W. Zucker, "Early vision," inEncyclopedia of Artificial Intelligence(S. Shapiro, Ed.). Wiley, 1986.
[4] I. Biederman, "Human image understanding: recent research and a theory,"Comput. Vision Graphics Image Processing, vol. 32, pp. 29-73, 1985.
[5] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[6] D. Mar and H. Nishihara, "Representation and recognition of the spatial organization of three dimensional shapes," MIT Al Memo 377, MIT Artificial Intell. Lab., Cambridge, MA, Aug. 1976.
[7] J. J. Koenderink, "What does the occluding contour tell us about solid shape,"Perception, vol. 13, pp. 321-330, 1984.
[8] J. G. Snodgrass and M. Vanderwart, "A standardized set of 260 pictures: Norms for name agreement, image agreement, familiarity, and visual complexity,"J. Experimental Psych: Human Learning Memory, vol. 6, no. 2, pp. 174-215, 1980.
[9] J. E. Hummel, I. Biederman, P. C. Gerhardstein, and H. J. Hilton, "From image edges to geons: A connectionist approach," inProc. 1988 Connectionist Models Summer Sch.(San Mateo), 1988, pp. 462-471.
[10] S. J. Dickinson, A. P. Pentland, and A. Rosenfeld, "3-D object recognition using distributed aspect graph matching," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(Maui, HI, June 3-6, 1991.
[11] M.D. Levine, R. Bergevin, and Q. L. Nguyen, "Shape description using geons as 3D primitives," inProc. Int. Forum Visual Form(Capri, Italy), May 27-30, 1991.
[12] G.D. Godin and M. D. Levine, "Structured edge maps of curved objects in a range image," inProc. IEEE Conf. Comput. Vision Patt. Recogn.(San Diego), June 4-8, 1989.
[13] L. G. Roberts, "Machine perception of three-dimensional objects," inOptical and Electrooptical Information(Tippet, Ed.). Cambridge, MA MIT Press, 1966, pp. 159-197.
[14] R.A. Brooks, "Symbolic reasoning among 3-D models and 2-D images,"Artif Intell., vol. 17, pp. 285-348, 1981.
[15] C. Goad, "Special-purpose automatic programming for 3D model-based vision," inProc. Image Understanding Workshop(Washington DC, 1983, pp. 94-104.
[16] J. Koenderink and A. V. Doorn, "The internal representation of solid shape with respect to vision,"Biol. Cybern., vol. 32, pp. 211-216, 1979.
[17] I. Chakravarty and H. Freeman, "Characteristic views as a basis for three-dimensional object recognition," inProc. Soc. Photo-Opt. Instrum. Eng. Conf. Robot Vision, pp. 37-45, vol. SPIE-336.
[18] K. Bowyer, J. Stewman, L. Stark, and D. Eggert, "ERRORS-2: A 3-D object recognition system using aspect graphs," inProc. 9th Int. Conf. Patt. Recogn.(Rome, Italy), Nov. 1988, pp. 6-10.
[19] Z. Gigus, J.F. Canny, and R. Seidel, "Efficiently computing and representing aspect graphs of polyhedral objects," inProc. Second Int. Conf. Computer Vision, IEEE, New York, Dec. 1988, pp. 30-39.
[20] K. Ikeuchi and T. Kanade, "Automatic generation of object recognition programs,"Proc. IEEE, vol. 76, no. 8, pp. 1016-1035, Aug. 1988.
[21] N. A. Watts, "Calculating the principal views of a polyhedron," inProc. 9th Int. Conf. Patt. Recogn(Rome, Italy), 14-17 Nov. 1988 pp. 316-322.
[22] A. Guzman, "Decomposition of a visual scene into bodies," AI Memo 139, MIT Artificial Intell. Lab., Cambridge, MA, Sept. 1967.
[23] D. Huffman, "Impossible objects as nonsense sentences,"Machine Intell., vol. 6, pp. 295-323, 1971.
[24] M. Clowes, "On seeing things,"Artificial Intell., vol. 2, pp. 79-116, 1971.
[25] A. Mackworth, "Interpreting pictures of polyhedral scenes,"Artificial Intell., vol. 4, pp. 121-137, 1973.
[26] D. Waltz, "Generating semantic descriptions from drawings of scenes with shadows," MAC-AI-TR-271, Mass. Inst. Technol., Cambridge, 1972.
[27] J. Malik, "Interpreting line drawings of curved objects,"Int. J. Comput. Vision, vol. 1, pp. 73-103, 1987.
[28] V.S. Nalwa, "Line-drawing interpretation: A mathematical framework," inProc. IEEE Comput. Soc. Conf. Comput. Vision Patt. Recogn.(Ann Arbor, MI), June 5-9, 1988, pp. 18-31.
[29] S. J. Lee, R. M. Haralick, and M. C. Zhang, "Understanding objects with curved surfaces from a single perspective view of boundaries,"Artificial Intell., vol. 26, pp. 145-169, 1985.
[30] K. Rao and R. Nevatia, "Computing volume descriptions from sparse 3-D Data,"Int. J. Comput. Vision, vol. 2, pp. 33-50, 1988.
[31] R. Horaud and M. Brady, "On the geometric interpretation of image contours," inProc. of First Conf. Comput. Vision(London, England), June 8-11, 1987, pp. 374-382.
[32] H. Barrow and J. Tenebaum, "Interpreting line drawings as three-dimensional surfaces,"Artificial Intell., vol. 17, pp. 75-116, 1981.
[33] K. Sugihara,Machine Interpretation of Line Drawings. Cambridge, MA: MIT Press, 1986.
[34] T. Kanade, "Recovery of three-dimensional shape of an object from a single view,"Artificial Intell., vol. 17, pp. 409-460, 1981.
[35] F. Ulupinar and R. Nevatia, "Using symmetries for analysis of shape from contour," inProc. 2nd ICCV, Tarpon Springs, FL, 1988, pp. 414-426.
[36] I. Weiss, "Projective invariants of shapes," inProc. IEEE Comput. Soc. Conf. Comput. Vision Patt. Recog.(Ann Arbor, MI), June 5-9, 1988, pp. 291-297.
[37] S. A. Sharer,Shadows and Silhouettes in Computer Vision. Boston: Kluwer, 1985.
[38] K. Rao and G. Medioni, "Useful geometrical properties of the generalized cone," inProc. IEEE Comput. Soc. Conf. Comput. Vision Patt. Recogn.(Ann Arbor, MI), June 5-9, 1988, pp. 276-281.
[39] J. Ponce, "Straight homogeneous generalized cylinders: Differential geometry and uniqueness results," inProc. IEEE Comput. Soc. Conf. Comput. Vision Patt. Recogn.(Ann Arbor, MI), June 5-9, 1988, pp. 327-334.
[40] R. Bergevin and M. D. Levine, "Extraction of line drawing features for object recognition,"Patt. Recogn., vol. 25, pp. 319-334, 1992.
[41] R. Bergevin and M. D. Levine, "Part decomposition of objects from single view line drawings,"Comput. Vision Graphics, Image Processing: Image Understanding, vol. 55, pp. 73-83, 1992.
[42] M. Brady, "Criteria for representations of shape," inHuman and Machine Vision. (J. Beck, B. Hope, and A. Rosenfeld, Eds.). New York: Academic, 1983, pp. 39-84.
[43] W. H. Jackson,Elementary Solid Geometry. London: Edward Arnold, 1907.
[44] D. Hoffman and W. Richards, "Parts of recognition,"Cognition, vol. 18, pp. 65-96, 1984.
[45] R. Bergevin, "Primal access recognition of visual objects," Ph.D. thesis, Dep. Elect. Eng., McGill Univ. Montréal, Canada, Mar. 1990.
[46] L. G. Shapiro, J. D. Moriarty, R. M. Haralick, and P. G. Mulgaonkar, "Matching three-dimensional objects using a relational paradigm,"Patt. Recogn., vol. 17, no. 4, pp. 385-405, 1984.
[47] R. Bergevin and M. D. Levine, "Matching coarse object and model descriptions for generic recognition," inProc. Vision Interface '90(Halifax, Canada), May 14-18, 1990.

Index Terms:
recognition by components; generic object recognition; image recognition; primal access recognition of visual objects; PARVO; computer vision; human image understanding; 2D line drawings; spatial orientations; artificial intelligence; computer vision; image recognition
R. Bergevin, M.D. Levine, "Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 19-36, Jan. 1993, doi:10.1109/34.184772
Usage of this product signifies your acceptance of the Terms of Use.