Wavelets for Object Representation and Recognition in Computer Vision

  • Luis Pastor
  • Angel Rodríguez
  • David Ríos Insua
Part of the Lecture Notes in Statistics book series (LNS, volume 141)


Finding efficient and powerful techniques for representing 2D and 3D entities is central in many areas, such as computer vision, graphics, CAD or data visualization. The large amount of data often involved and the small processing time required place strong demands on modeling techniques. This chapter gives an overview of the possibilities wavelets offer for object modeling, specially from the point of view of object recognition in computer vision environments. For the 2D case, techniques based on segmented contours or raw grey level information are described. For 3D data, both the cases of dense, regularly sampled volumetric information and sparse, irregularly sampled geometric surface information are considered. Ideas on how Bayesian methods may enhance wavelet based techniques for object representation and recognition are outlined.


Object Recognition Object Representation Gabor Filter Resolution Level Subdivision Scheme 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    D. Marr and E. Hildreth: Theory of Edge Detection, Proceedings of the Royal Society, (London), ser. B, vol. 207, pp. 187–217, 1980.CrossRefGoogle Scholar
  2. [2]
    A. Rosenfeld, Ed.: Multiresolution Image Processing and Analysis, Springer Verlag, 1984.Google Scholar
  3. [3]
    E. L. Grimson: Introduction of the Special Issue on Interpretation of 3D Scenes. IEEE Trans, on PAMI, 14,2, (1992), 97–98.Google Scholar
  4. [4]
    S. J. Dickinson, R. Bergevin, I. Biederman, J. Eklundh, R. Munck-Fairwood and A. Pentland: The Use of Geons for Generic 3D Object Recognition. Proc. 13th Int. Conf. on Artificial Intelligence, Chambery, France,(1993) pp. 1693-1699.Google Scholar
  5. [5]
    J. Wood: Invariant Pattern Recognition: A Review. Pattern Recognition, vol. 29(1), pp. 1–17, 1996.CrossRefGoogle Scholar
  6. [6]
    A. Laine, S. Schuler y V. Girish: Orthonormal wavelet representations for recognizing complex annotations, Machine Vision and Applications, vol. 6, pp. 110–123, 1993.CrossRefGoogle Scholar
  7. [7]
    P. Wunsch and A. F. Laine: Wavelet Descriptors for Multiresolution Recognition of Handprinted Characters. Pattern Recognition, vol. 28(8), pp. 1237–1249, 1995.CrossRefGoogle Scholar
  8. [8]
    Gene C.H. Chuang y C.C. Jay Kuo: Wavelet Descriptor of Planar Curves: Theory and Applications. IEEE Trans, on Image Processing, vol. 5(1), pp. 56–70, Jan. 1996.CrossRefGoogle Scholar
  9. [9]
    W. Wang, Z. Bao, Q. Meng, G.M: Flachs y J.B. Jordan: Hand Recognition by Wavelet Transform and Neural Network. Proc. of the SPIE, vol. 2484, pp. 346–353, 1995.Google Scholar
  10. [10]
    S.G. Mallat: Zero-crossing of a Wavelet Transform. IEEE Trans, on Information Theory, vol. 37(14), pp. 1019–1033, 1991.MathSciNetCrossRefGoogle Scholar
  11. [11]
    Z. Berman y J. S. Baras: Properties of the Multiscale Maxima and Zerocrossings Representations. IEEE Trans. Signal Processing, vol. 41(12), pp. 3216–3230, 1993.CrossRefGoogle Scholar
  12. [12]
    R. Hummel and R. Moniot: Reconstruction from zero-crossings in scale-space, IEEE Trans, on Acoustic Speech Signal Processing, vol. 37(12), Dec. 1989.Google Scholar
  13. [13]
    W. W. Boles: A Security System Based on Human Iris Identification Using Wavelet Transform. First International Conference on Knowledge-Based Intelligent Electronic Systems, Ed. L.C. Jain, pp. 533-541, 21-23 May., 1997.Google Scholar
  14. [14]
    E.P. Simoncelli, W.T. Freeman, E.H. Adelson y D.J. Heeger: Shiftable Multiscale Transforms. IEEE Trans on Information Theory, vol. 38(2), pp. 587–607, Mar. 1992.CrossRefGoogle Scholar
  15. [15]
    Q. M. Tieng and W. W. Boles: Complex Daubechies Wavelet Based Affine Invariant Representation for Object Recognition. ICIP—94, pp. 198-202, 1994.Google Scholar
  16. [16]
    J.C. Pesquet, H. Krim and H. Carfantan: Time-Invariant Orthonormal Wavelet Representations. IEEE Trans, on Signal Processing, vol. 44(8), pp. 1964–1970, Aug. 1996.CrossRefGoogle Scholar
  17. [17]
    W. Yu-Ping and S.L. Lee: Scale-space derived from B-splines. IEEE Trans, on PAMI, vol. 20(10), October, 1998Google Scholar
  18. [18]
    W. Yu-Ping: Image Representations Using Multiscale Differential Operators. Submitted to IEEE Trans, on Image Processing in 1998. Avaliable as a preprint in: Scholar
  19. [19]
    L. M. Reissell: Wavelet multiresolution representation of curves and surfaces. Graphical Models and Image Processing, vol. 58(3), pp. 198–217, 1996.CrossRefGoogle Scholar
  20. [20]
    M. Lades, J.C. Vorbriiggen, J. Buhmann, J. Lange, C.v.d. Malsburg, R.P. Würtz y W. Konen: Distortion Invariant Object Recognition in the Dynamic Link Architecture. IEEE Trans, on Computers, vol. 42(3), pp. 300–311, Mar. 1993.CrossRefGoogle Scholar
  21. [21]
    L. Wiskott, J.M. Fellous, N. Krüger y C. von der Malsburg: Face Recognition by Elastic Bunch Graph Matching. IEEE Trans, on PAMI, vol. 19(7), pp. 775–779, Jul. 1997.CrossRefGoogle Scholar
  22. [22]
    R. P. Würtz: Object Recognition Robust Under Translations, Deformations, and Changes in Background. IEEE Trans, on PAMI, vol. 19(7), pp. 769–775, Jul. 1997.CrossRefGoogle Scholar
  23. [23]
    J.G. Daugman: High Confidence Visual Recognition of Persons by a Test of Statistical Independence. IEEE Trans, on PAMI, vol. 15(11), pp. 1148–1161, Nov. 1993.CrossRefGoogle Scholar
  24. [24]
    M. Eck, T. DeRose, T. Duchamp, H. Hoppe, M. Lounsbery and W. Stuetzle: Multiresolution analysis of arbitrary meshes. Computer Graphics Proceedings (SIGGRAPH 95), pp. 173-182, 1995.Google Scholar
  25. [25]
    S. Campagna and H.-P. Seidel: Parametrerizing Meshes with Arbitrary Topology, in H. Niemann, H.-P. Seidel and B. Girod (eds.), Image and Multidimensional Signal Processing’98, pp. 287-290, 1998.Google Scholar
  26. [26]
    L. Pastor, A. Rodriguez: Aproximaciön de superficies utilizando técnicas multirresoluciön. Technical report, Dept. Tecnologia Fotónica, Universidad Politécnica de Madrid, 1997.∼arodri/ Scholar
  27. [27]
    B. C. Vemuri y A. Radisavljevic: Multiresolution Stochastic Hybrid Shape Models with Fractal Priors, ACM Transactions on Graphics, vol. 13(2), pp. 177–207, ACM, 1994.CrossRefGoogle Scholar
  28. [28]
    M.H. Gross y R. Gatti: Efficient Triangular Surface Approximations using Wavelets and Quadtree Data Structures. IEEE Trans, on Visualization and Computer Graphics, vol. 2(2), pp. 1–13, Jun. 1996.Google Scholar
  29. [29]
    M. Lounsbery, T. DeRose y J. Warren: Multiresolution analysis for surfaces of arbitrary topological type. ACM Trans, on Graphics, vol 16(1), pp. 34–73, Jan. 1997.CrossRefGoogle Scholar
  30. [30]
    Ikeuchi K. and Hebert M.: Spherical Representations: From EGI to SAL Proc. Intl, NSI-ARPA Workshop, pp. 327-345, 1995.Google Scholar
  31. [31]
    P. Schröeder and W. Sweldens: Spherical wavelets: Efficiently representing functions on a sphere. Computer Graphics Proceedings (SIG-GRAPH 95), pp. 161-172, 1995.Google Scholar
  32. [32]
    P. Schröeder: Wavelets in Computers Graphics. Proc. of the IEEE, vol. 84(4), Abr., pp. 615–625, 1996.CrossRefGoogle Scholar
  33. [33]
    E. J. Stollnitz, T. D. DeRose and D. H. Salesin: Wavelets for Computer Graphics. Morgan Kauffman Publishers (1996).Google Scholar
  34. [34]
    D. Zorin, P. Schröeder and W. Sweldens: Interactive Multiresolution Mesh Editing. Computer Graphics Proceedings (SIGGRAPH 97), pp. 259-269, 1997.Google Scholar
  35. [35]
    I. Biederman: Recognition by Components: A Theory of Human Image Understanding, Psycological Review, vol. 94 (2), pp. 115-147, American Psychological Association, 1987.Google Scholar
  36. [36]
    Aggarwal, J. K., Ghosh, J., Nair, D. y Taha, L: A Comparative Study of Three Paradigms for Object Recognition—Bayesian Statistics, Neural Networks and Expert Systems, Bowyer, K. and N. Ahuja, Ed., Advances in Image Understanding. A Festschrift for Azriel Rosenfeld, pp. 196-208, IEEE Comp. Society, 1996.Google Scholar
  37. [37]
    R. Jain, R. Kasturi y B.G. Schunck: Machine Vision, McGraw-Hill, 1995.Google Scholar
  38. [38]
    S. Ullman: High-level Vision. Object Recognition and Visual Cognition, MIT Press, 1996.Google Scholar
  39. [39]
    S. J. Dickinson, A. P. Pentland and A. Rosenfeld: From Volumes to Views: An Approach to 3D Object Recognition, CVGIP: Image Understanding, vol. 55(2), pp. 130–154, Academic Press, 1992.MATHCrossRefGoogle Scholar
  40. [40]
    T. Chang and C.-C.J. Kuo: Texture analysis and classification with tree-structured wavelet trasform. IEEE Trans. Im. Process., vol 2(4), pp. 429–441, 1993.CrossRefGoogle Scholar
  41. [41]
    A. Laine and J. Fan: Texture classification and segmentation using wavelet frames. IEEE Trans. Pattern Analysis and Machine Intelligence, vol 15(11), pp. 1186–1190, 1993.CrossRefGoogle Scholar
  42. [42]
    G. Van de Wouwer, S. Livens and D. van Dyck: Color Texture Classification by wavelet energy-correlation signatures. In Proc. of the International Conference on Computer Analysis and Image Processing, 1997-Firenze, pp. 327-334, 1997.Google Scholar
  43. [43]
    C. E. Jacobs, A. Finkelstein and D. H. Salesin: Fast Multiresolution Image Querying. Proc. of SIGGRAPH’95, pp. 277–286, ACM, New York, 1995.Google Scholar
  44. [44]
    L. Pastor, A. Rodríguez, O. Robles and J.M. Espadero: Estudio de técnicas de búsqueda de objetos por contenido utilizando wavelets. Technical report, Dpto. Tecnología Fotónica, Universidad Politécnica de Madrid, 1998.∼arodri/ Scholar
  45. [45]
    Q. M. Tieng and W. W. Boles: Recognition of 2D Object Contours Using the Wavelet Transform Zero-Crossing Representation. IEEE Trans, on PAMI, vol. 19(8), pp. 910–916, 1997.CrossRefGoogle Scholar
  46. [46]
    X. Wu and B. Bhanu: Gabor Wavelet Representation for 3-D Object Recognition. IEEE Trans, on Image Processing, vol. 6(1), pp. 47–64, Jan. 1997.CrossRefGoogle Scholar
  47. [47]
    L. Pastor, J. Duran and A. Rodríguez: Qualitative shape modeling of 3D data. Proc of Second International Conference on Mathematics & Design 98, San Sebastián, Spain, pp. 459-466, Jun. 1998.Google Scholar
  48. [48]
    D. Knill and W. Richards: Perception as Bayesian Inference, Cambridge University Press, 1996.Google Scholar
  49. [49]
    B. Vidakovic: Statistical Modeling by Wavelets, Wiley, 1999.Google Scholar
  50. [50]
    M. Lavine, M. West: A Bayesian method for classification and discrimination, Can. Jour. Stats., 20, 451–461, 1992.MathSciNetMATHCrossRefGoogle Scholar
  51. [51]
    P. Muller, D. Rios Insua: Issues in Bayesian analysis of neural network models, Neural Computation, pp. 571–592, 1998.Google Scholar
  52. [52]
    C. Bishop: Neural Networks for Pattern Recognition, Chapman Hall, 1996.Google Scholar
  53. [53]
    D.B. Phillips and A.M.F. Smith: Bayesian faces via hierarchical template modeling, Jour. Amer. Stat. Assoc, 89, pp. 1151–1163, 1994.MATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1999

Authors and Affiliations

  • Luis Pastor
  • Angel Rodríguez
  • David Ríos Insua

There are no affiliations available

Personalised recommendations