Object recognition and performance bounds

  • J. K. Aggarwal
  • Shishir Shah
Keynote Address
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


Object recognition is the classification of objects into one of many a priori known object classes. In addition, it may involve the estimation of the pose of the object and/or the track of the object in a sequence of images. Bayesian statistical pattern recognition, neural networks and rule based systems have been used to address the object recognition problem. In the case of statistical pattern recognition it is assumed that the a priori probability density functions are known or that they can be estimated from the given samples. For neural networks the samples may be used to train a network and the coefficients for the network function may be estimated. Whereas, in the case of the rule based system, rules may be given by an expert or they may be estimated from the samples. However, Bayesian framework provides a methodology for the estimation of error bounds on the performance of the recognition system. The paper discusses the Bayesian paradigm and contrasts its ability to provide performance bounds as compared to neural networks and rule based systems. Future direction of results on object recognition and performance bounds will also be discussed.


  1. [AA93a]
    F. Arman and J. K. Aggarwal. CAD-based vision: Object recognition in cluttered range images using recognition strategies. Computer Vision, Graphics, and Image Procesing, 58(1):33–47, 1993.Google Scholar
  2. [AA93b]
    F. Arman and J. K. Aggarwal. Model-based object recognition in dense depth images — a review. ACM Computing Surveys, 25(1):5–43, 1993.Google Scholar
  3. [AGNT96]
    J. K. Aggarwal, J. Ghosh, D. Nair, and 1. Taha. A comparative study of three paradigms for object recognition: Bayesian, neural network and expert systems. In K. Bowyer and N. Ahuja, editors, Advances in Image Understanding: A Festschrift to Azriel Rosenfeld, chapter 15, pages 300–324. Springer-Verlag, 1996.Google Scholar
  4. [BA90]
    J Ben-Arie. The probabilistic peaking effect of viewed angles and distances with application to 3D object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(8):760–774, 1990.Google Scholar
  5. [Bie85]
    I. Biederman. Human image understanding: Recent research and a theory. Computer Vision, Graphics and Image Processing, 32:29–73, 1985.Google Scholar
  6. [Bis95]
    C. M. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, New York, 1995.Google Scholar
  7. [BJ85]
    P.J. Besl and R.C. Jain. Three-dimensional object recognition. ACM Computing Surveys, 17(1):75–145, March 1985.Google Scholar
  8. [BR92]
    J. B. Burns and E. M. Riseman. Matching complex images to multiple 3D objects using view description networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages 328–334, 1992.Google Scholar
  9. [CA84]
    C. H. Chien and J. K. Aggarwal. A volume/surface octree representation. In 7th International Conference on Pattern Recognition, pages 817–820, 1984.Google Scholar
  10. [CA95]
    C.C. Chu and J.K. Aggarwal. The interpretation of a laser rader images by a knowledge-based system. Machine Vision and Applications, 4:145–163, 1995.Google Scholar
  11. [CD86]
    R.T. Chin and C.R. Dyer. Model-based recognition in robot vision. ACM Computing Surveys, 18(1):67–108, March 1986.Google Scholar
  12. [CH91]
    Z. Chen and S. Ho. Computer vision for robust 3D aircraft recognition with fast library search. Pattern Recognition, 24(5):375–390, 1991.Google Scholar
  13. [CJ93]
    S. Chen and A. K. Jain. Strategies of multi-view multi-matching for 3d object recognition. Computer Vision and Image Processing, 57(1):121–130, 1993.Google Scholar
  14. [CJR93]
    T. Caelli, M. Johnston, and T. Robinson. 3d object recognition: Inspiration and lessons from biological vision. In A. K. Jain and P. J. Flynn, editors, Three-Dimensional Object Recognition Systems, pages 1–16. Elsevier Science Publishers, 1993.Google Scholar
  15. [DBM77]
    S.A. Dudani, K.J. Breeding, and R.B. McGhee. Aircraft identification by moment invariants. IEEE Transactions on Computers, C-26:39–46, 1977.Google Scholar
  16. [DH73]
    R. O. Duda and P. E. Hart. Pattern Classification and Scene Analysis. A Wiley-Interscience Publication, 1973.Google Scholar
  17. [DMPA93]
    M. De Mathelin, C. Perneel, and M. Acheroy. IRES: an expert system for automatic target recognition from short-distance infrared images. In L.E. Garn and L.L. Graceffo, editors, SPIE, Architecture, Hardware, and Forward-Looking Infrared Issues in Automatic Object Recognition, volume 1957, pages 68–84, 1993.Google Scholar
  18. [GG92]
    D. Gavrila and F. Greon. 3D object recognition from 2D image using geometric hashing. Pattern Recognition Letters, 13(4):263–278, 1992.Google Scholar
  19. [Gho94]
    J. Ghosh. Vision based inspection. In C. H. Dagli, editor, Artificial Neural Networks for Intelligent Manufacturing, pages 265–297. Chapman and Hall, London, 1994.Google Scholar
  20. [GT94]
    J. Ghosh and K. Turner. Structural adaptation and generalization in supervised feedforward networks. Journal of Artificial Neural Networks, 1(4):431–458, 1994.Google Scholar
  21. [Hu62]
    M. Hu. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, February: 179–187, 1962.Google Scholar
  22. [HU90]
    D. P. Huttenlocher and S. Ullman. Recognizing solid objects by alignment with the image. International Journal on Computer Vision, 5(2):195–212, 1990.Google Scholar
  23. [JMM96]
    A. Jain, J. Mao, and K. M. Mohiuddin. Artificial neural networks: A tutorial. In Computer, pages 31–44, March 1996.Google Scholar
  24. [KA86]
    Y. C. Kim and J. K. Aggarwal. Rectangular parallepiped coding: A volumetric representation of three-dimensional objects. IEEE Transactions on Robotics and Automation, 2(3):127–134, 1986.Google Scholar
  25. [KH90]
    A. Khotanzad and Y.H. Hong. Invariant image recognition by Zernike moments. IEEE Transactions on Pattern Analysis and Machine Intelligence. 12:489–497. 1990.Google Scholar
  26. [KvD79]
    I. Koenderink and A. van Doorn. The internal representation of solid shape with respect to vision. Biological Cybernetics, 32:211–216, 1979.Google Scholar
  27. [LA92]
    H. Q. Lu and J. K. Aggarwal. Applying perceptual organization to the detection of man-made objects in non-urban scenes. Pattern Recognition, 25(8):835–853, 1992.Google Scholar
  28. [MA77]
    J. W. McKee and J. K. Aggarwal. Computer recognition of partial views of curved objects. IEEE Transactions on Computers, C-26(8):790–800, 1977.Google Scholar
  29. [Mar82]
    D. Marr. Vision. W. H. Freeman, 1982.Google Scholar
  30. [MN89]
    R. Mohan and R. Nevatia. Using perceptual organization to extract 3-d structures. PAMI, 11(11):1121–1139, November 1989.Google Scholar
  31. [NL91]
    K. Ng and R.P. Lippmann. Practical characteristics of neural network and conventional pattern classifiers. In J.E. Moody R.P. Lippmann and D.S. Touretzky, editors, Neural Information Processing Systems, pages 970–976, 1991.Google Scholar
  32. [PC93]
    A. Pathak and O. I. Camps. Bayesian view class determination. IEEE Conference on Computer Vision and Pattern Recognition, pages 407–412, 1993.Google Scholar
  33. [Pea88]
    J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers, Inc. San Mateo, California, 1988.Google Scholar
  34. [Pop94]
    A. Pope. Model-based object recognition—a survey of recent research. Technical Report, TR-94-04, 1994.Google Scholar
  35. [PPK92]
    S. Petitjean, S. Ponce, and D. J. Kriegman. Computing exact aspect graphs of curved objects: Algebraic surfaces. International Journal on Computer Vision, 9(3):231–255, 1992.Google Scholar
  36. [RH92]
    E.M. Riseman and A.R. Hanson. A methodology for the development of general knowledge-based vision system. In C. Torras, editor, Computer Vision: Theory and Industrial Applications, pages 293–336. Springer Verlag, 1992.Google Scholar
  37. [Ros84]
    A. Rosenfeld. Image analysis: Problems, progress and prospects. Pattern Recognition, 17(1):3–12, January 1984.Google Scholar
  38. [SFH92]
    P. Suetens, P. Fua, and A.J. Hanson. Some computational strategies for object recognition. ACM Computing Surveys, 24(1):5–62, March 1992.Google Scholar
  39. [SP90]
    G. Shafer and J. Pearl, editors. Readings in Uncertain Reasoning. Morgan Kauffman, Inc., 1990.Google Scholar
  40. [SSY92]
    W.J. Shomar, G. Seetharaman, and T.Y. Young. An expert system for recovering 3D shape and orientation from a single view. In L. Shapiro and A. Rosenfield, editors, Computer Vision and Image Processing, pages 459–516. Academic Press, 1992.Google Scholar
  41. [Tou87]
    J. T. Ton. Knowledge-based systems for robotic application. In A. Wong and A. Pugh, editors, Machine Intelligence and Knowledge Engineering for Robotics Applications, Proc. NATO/ASI Workshop, pages 145–189. Springer Verlag, 1987.Google Scholar
  42. [VMA86]
    B. Vemuri, A. Mitiche, and J. K. Aggarwal. Curvature-based representation of objects from range data. Image and Vision Computing, 4(2):107–114, 1986.Google Scholar
  43. [Wel93]
    W. M. Wells. Statistical Object Recognition. PhD thesis, Cambridge, MIT, November 1993.Google Scholar
  44. [WMA84]
    Y. F. Wang, M. J. Magee, and J. K. Aggarwal. Matching three-dimensional objects using silhouettes. IEEE Transactions on Pattern Analysis and, Machine Intelligence, 6(4):513–518, 1984.Google Scholar
  45. [Won87]
    A. Wong. Knowledge representation for robot vision and path planning using attributed graphs and hypergraphs. In A. Wong and A. Pugh, editors, Machine Intelligence and Knowledge Engineering for Robotics Applications, Proc. NATO/ASI Workshop, pages 113–143. Springer Verlag, 1987.Google Scholar
  46. [ZSB93]
    S. Zhang, G. Sullivan, and K. Baker. The automatic construction of a view-independent relational model for 3D object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(6):778–786, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • J. K. Aggarwal
    • 1
  • Shishir Shah
    • 1
  1. 1.Computer and Vision Research Center Department of Electrical and Computer Engineering, ENS 522The University of Texas at AustinAustinUSA

Personalised recommendations