A Vision System for Recognizing Objects in Complex Real Images

  • Mohammad Reza Daliri
  • Walter Vanzella
  • Vincent Torre
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4842)


A new system for object recognition in complex natural images is here proposed. The proposed system is based on two modules: image segmentation and region categorization. Original images g(x,y) are first regularized by using a self-adaptive implementation of the Mumford-Shah functional so that the two parameters α and γ. controlling the smoothness and fidelity, automatically adapt to the local scale and contrast. From the regularized image u(x,y), a piece-wise constant image s N (x,y) representing a segmentation of the original image g(x,y) is obtained. The obtained segmentation is a collection of different regions or silhouettes which must be categorized. Categorization is based on the detection of perceptual landmarks, which are scale invariant. These landmarks and the parts between them are transformed into a symbolic representation. Shapes are mapped into symbol sequences and a database of shapes in mapped into a set of symbol sequences. Categorization is obtained by using support vector machines. The Kimia silhouettes database is used for training and complex natural images from Martin database and collection of images extracted from the web are used for testing the proposed system. The proposed system is able to recognize correctly birds, mammals and fish in several of these cluttered images.


IEEE Transaction Original Image Feature Space Object Recognition Natural Image 
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.
    Ullman, S.: High-level Vision. MIT Press, Cambridge (1996)zbMATHGoogle Scholar
  2. 2.
    Edelman, S.: Representation and Recognition in Vision. MIT Press, Cambridge (1999)Google Scholar
  3. 3.
    Biederman, I., Ju, G.: Surface Versus Edge-based Determinants of Visual Recognitions. Cognitive Psychology 20, 38–64 (1988)CrossRefGoogle Scholar
  4. 4.
    Blum, H.: A Transformation for Extracting New Descriptors of Shape. In: Wathen-Dunn, W. (ed.) Models for the Perception of Speech and Visual Form, pp. 362–380. MIT Press, Cambridge (1967)Google Scholar
  5. 5.
    Sebastian, T.B., Klien, P., Kimia, B.B.: Recognition of Shapes by Editing Their Shock Graphs. IEEE Transaction on PAMI 26(5), 550–571 (2004)Google Scholar
  6. 6.
    Mokhtarian, F., Mackworth, A.: Scale-based Description and Recognition of Planar Curves and Two-dimensional Shapes. IEEE Transaction on PAMI 8(1), 34–43 (1986)Google Scholar
  7. 7.
    Belongie, S., Malik, J.: Shape Matching and Object Recognition Using Shape Contexts. IEEE Transaction on PAMI 24(24), 509–522 (2002)Google Scholar
  8. 8.
    Arbter, K., Snyder, W.E., Burhardt, H., Hirzinger, G.: Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects. IEEE Transaction on PAMI 12(7), 640–647 (1990)Google Scholar
  9. 9.
    Rivlin, E., Weiss, I.: Local Invariants for Recognition. IEEE Transaction on PAMI 17(3), 226–238 (1995)Google Scholar
  10. 10.
    Murase, H., Nayar, S.K.: Visual Learning and Recognition of 3-D Objects from Appearance. Int. J. Computer Vision 14(1), 5–24 (1995)CrossRefGoogle Scholar
  11. 11.
    Vanzella, W., Pellegrino, F.A., Torre, V.: Self-adaptive Regularization. IEEE Transaction on PAMI 26(6), 804–809 (2004)Google Scholar
  12. 12.
    Vanzella, W., Torre, V.: A Versatile Segmentation Procedure. IEEE Transaction on SMC part B 36(2), 366–378 (2006)CrossRefGoogle Scholar
  13. 13.
    Sharvit, D., Chan, J., Tek, H., Kimia, B.B.: Symmetry-based Indexing of Image Databases. J. of Visual Communication and Image Representation 9(4), 366–380 (1998)CrossRefGoogle Scholar
  14. 14.
    Martin, D.R., Fowlkes, C., Malik, J.: Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues. IEEE Transaction on PAMI 26(5), 530–549 (2004)Google Scholar
  15. 15.
    Dudek, G., Tsotsos, J.: Shape Representation and Recognition from Multi-scale Curvature. Computer Vision and Image Understanding 68(2), 170–189 (1997)CrossRefGoogle Scholar
  16. 16.
    Lindeberg, T.: Edge Detection and Ridge Detection with Automatic Scale Selection. Int. J. Computer Vision 30(2), 117–154 (1998)CrossRefGoogle Scholar
  17. 17.
    Joachims, T.: Text Categorization with Support Vector Machines: Learning with Many Relevant Features. In: Nédellec, C., Rouveirol, C. (eds.) Machine Learning: ECML-1998. LNCS, vol. 1398, pp. 137–142. Springer, Berlin (1998)CrossRefGoogle Scholar
  18. 18.
    Salton, A.W., Yang, C.: A Vector Space Model for Automatic Indexing. Communications of the ACM 18(11), 613–620 (1975)zbMATHCrossRefGoogle Scholar
  19. 19.
    Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text Classification using String Kernels. J. of Machine Learning Research 2, 419–444 (2002)zbMATHCrossRefGoogle Scholar
  20. 20.
    Vapnik, V.: Statistical Learning Theory. Wiley-Interscience, New York (1998)zbMATHGoogle Scholar
  21. 21.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines. Cambridge University Press, Cambridge (2000)Google Scholar
  22. 22.
    Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2(2), 121–167 (1998)CrossRefGoogle Scholar
  23. 23.
    Costa, L.D.F., Junior, R.M.C.: Shape Analysis and Classification: Theory and Practice. CRC Press, Boca Raton, USA (2000)Google Scholar
  24. 24.
    Fan, R.E., Chen, P.H., Lin, C.J.: Working Set Selection using the Second Order Information for Training SVM. Technical report, Department of Computer Science, National Taiwan University (2005)Google Scholar
  25. 25.
    Kearns, M., Ron, D.: Algorithmic Stability and Sanity-check Bounds for Leave-one-out Cross-validation. Neural Computation 11, 1427–1453 (1999)CrossRefGoogle Scholar
  26. 26.
    Martin, D.R., Fowlkes, C., Malik, J.: Learning to Detect Natural Image Boundaries using Local Brightness, Color, and Texture Cues. IEEE Transaction on PAMI 26, 530–549 (2004)Google Scholar
  27. 27.
    Daliri, M.R., Delponte, E., Verri, A., Torre, V.: Shape Categorization using String Kernels. In: Yeung, D.-Y., Kwok, J.T., Fred, A., Roli, F., de Ridder, D. (eds.) Structural, Syntactic, and Statistical Pattern Recognition. LNCS, vol. 4109, pp. 297–305. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Mohammad Reza Daliri
    • 1
    • 2
  • Walter Vanzella
    • 1
  • Vincent Torre
    • 1
  1. 1.SISSA, Via Beirut 2-4, 34014 TriesteItaly
  2. 2.ICTP Programme for Training and Research in Italian Laboratories, International Center for Theoretical Phyiscs, Strada Costiera 11, 34014 TriesteItaly

Personalised recommendations