This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Organizing Large Structural Modelbases
April 1995 (vol. 17 no. 4)
pp. 321-332

Abstract—We present a hierarchically structured approach to organizing large structural modelbases using an information theoretic criterion. Objects (patterns) are modeled in the form of random parametric structural descriptions (RPSDs), an extension of the parametric structural description graph-theoretic formalism [1]. Objects in scenes are modeled as parametric structural descriptions (PSDs). The organization process is driven by pairwise dissimilarity values between RPSDs. We also introduce the node pointer lists, which are computed offline during modelbase organization. During recognition, the only exponential matching process involved is between the scene PSD and the RPSD at the root of the organized tree. Using the organized hierarchy along with the node pointer lists, the remaining work simplifies to a series of inexpensive linear tests at the subsequent levels of the tree search. We develop the theory and present three modelbases: 50 objects built from real image data, 100 CAD models, and 1000 synthetic abstract models.

[1] K.L. Boyer and A.C. Kak,“Structural stereopsis in 3D vision,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, no. 2, pp. 144-166, 1988.
[2] R.T. Chin and C.R. Dyer, "Model-Based Recognition in Robotics Vision," ACM Computing Surveys, vol. 18, pp. 67-108, Mar. 1986.
[3] F. Stein and G. Medioni, “Structural Indexing: Efficient 3-D Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 125–145, 1992.
[4] A.K.C. Wong, S.W. Lu, and M. Roux, "Recognition and Shape Synthesis of 3D Object Based on Attributed Hypergraph," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 3, pp. 279-290, Mar. 1990.
[5] M. Oshima and Y. Shirai,“Object recognition using 3D information,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 5, no. 7, pp. 353-361, 1983.
[6] P.J. Flynn and A.K. Jain,“CAD-based computer vision: From CAD models to relational graphs,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 2, pp. 114-132, Feb. 1991.
[7] C. Chen and A. Kak, "A Robot Vision System for Recognizing 3D Objects in Low-Order Polynomial Time," IEEE Trans. On Systems, Man, and Cybernetics," vol. 19 no. 6, pp. 1,535-1,563, Nov./Dec. 1989.
[8] W. Kim and A.C. Kak, "3-D Object Recognition Using Bi-Partite Graph Matching Embedded in Discrete Relaxation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 224-251, 1991.
[9] E. Grimson and T. Lozano-Perez,“Model-based recognition and localization fromsparse range and tactile data,” Int’l J. of Robotics, vol. 3, pp. 3-35, 1984.
[10] Y. Lamdan, J.T. Schwartz, and H.J. Wolfson, "Affine invariant model-based object recognition," IEEE Trans. Robotics and Automation, vol. 6, pp. 578-589, 1990.
[11] D. Forsyth, J.L. Mundy, A. Zisserman, C. Coelho, A. Heller, and C. Rothwell, "Invariant descriptors for 3-D object recognition and pose," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 971-991, 1991.
[12] A.P. Pentland,“Recognition by parts,” Proc. First Int’l Conf. on Computer Vision, pp. 612-620, 1987.
[13] S.J. Dickinson,A. Pentland,, and A. Rosenfeld,“Qualitative 3D shape reconstruction usingdistributed aspect graph matching,” Int’l Conf. on Computer Vision, pp. 257-262, 1990.
[14] H. Sossa and R. Horaud, Model Indexing: The Graph-Hashing Approach Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 811-815, 1992.
[15] L.G. Shapiro and R.M. Haralick,“Organization of relational models forscene analysis,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 4, no. 11, pp. 595-602, 1982.
[16] L.G. Shapiro and R.M. Haralick,“Structural descriptions and inexact matching,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 3, pp. 504-519, 1981.
[17] A. Wong and M. You,“Entropy and distance of random graphs with applicationto structural pattern recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 7, no. 9, pp. 599-609, 1985.
[18] A.K.C. Wong and D.E. Ghahraman,“Random graphs: Structural-contextual dichotomy,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 2, no. 4, pp. 341-348, 1980.
[19] K. Sengupta,“Organizing large structural modelbases,” Master’s thesis, The Ohio State Univ., 1992.
[20] A.K. Jain and R.C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, N.J.: Prentice Hall, 1988.
[21] J.B. Burns and L.J. Kitchen,“Recognition in 2D images of 3D objects fromlarge model bases using prediction hierarchies,” Int’l Joint Conf. on Artificial Intelligence, pp. 763-766, 1987.
[22] S. Sarkar and K. L. Boyer, "On Optimal Infinite Impulse Response Edge Detection Filters," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 11, pp. 1,154-1,171, 1991.
[23] D.M. Wuescher and K.L. Boyer,“Robust contour decomposition using a constant curvature criterion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 1, pp. 41-51, 1991.
[24] E.M. Arkin, L.P. Chew, D.P. Huttenlocher, K. Kedem, and J.S.B. Mitchell, "An Efficiently Computable Metric for Comparing Polygonal Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 209-216, 1991.
[25] K. Sengupta and K.L. Boyer,“Creating random structural descriptions of CAD modelsand determining object classes,” Proc. of Second CAD-based Vision Workshop, pp. 38-45, 1994.
[26] J. Stewman and K. Bowyer, "Creating the perspective projection aspect graph of polyhedral objects," Int'l Conf. Computer Vision, pp. 494-500, 1988.
[27] P. Gros and R. Mohr,“Automatic object modelization in computer vision,” in IAPR Workshop on Structural and Syntactic Pattern Recognition,Bern, Switzerland, Aug. 1992.
[28] K. Sengupta and K.L. Boyer,“Incremental modelbase updating: Learning new model sites,” Tech. Rep. AAAI FS-93-04, AAAI Fall Symp. Series: Machine Learning in ComputerVision: What, Why, and How?, Oct. 1993.

Index Terms:
Object recognition, model based recognition, organizing modelbases, structural descriptions, large modelbases.
Citation:
Kuntal Sengupta, Kim L. Boyer, "Organizing Large Structural Modelbases," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 4, pp. 321-332, April 1995, doi:10.1109/34.385984
Usage of this product signifies your acceptance of the Terms of Use.