Pattern recognition learning applied to stereovision matching

  • Gonzalo Pajares
  • Jesûs Manuel de la Cruz
  • José A. López
Poster Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


This paper presents an approach to the local stereovision matching problem by developing a statistical pattern recognition learning strategy. We use edge segments as features with several attributes. We have verified that the differences in attributes for the true matches cluster in a cloud around a center. The correspondence is established on the basis of the minimum squared Mahalanobis distance between the difference of the attributes for a current pair of features and the cluster center (similarity constraint). We introduce a learning strategy based on a maximum likelihood estimates method to get the best cluster center. A comparative analysis against a classical approach using the squared Euclidean distance (i.e. without learning) is illustrated.


Cluster Center Mahalanobis Distance Stereo Image Stereo Match Pattern Sample 
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.


  1. Duda, R.O. and P.E. Hart (1973). Pattern Classification and Scene Analysis. Wiley, New York.Google Scholar
  2. Edwards, A.W.F. (1972). Likelihood. Cambridge: University Press.Google Scholar
  3. Huertas, A. and G. Medioni (1986). Detection of Intensity Changes with Subpixel Accuracy Using Laplacian-Gaussian Masks. IEEE Trans. Pattern Analysis Mach. Intell. 8(5),651–664.Google Scholar
  4. Kim, D.H. and J.K. Aggarwal (1987) Positioning Three-Dimensional Objects using Stereo Images,“ IEEE Journal of Robotics and Automation. 3, 361–373.Google Scholar
  5. Kohonen T. (1995). Self-Organizing Maps. Berlin: Springer-Verlag.Google Scholar
  6. Krotkov, E.P. (1989). Active Computer Vision by Cooperative Focus and Stereo, Springer-Verlag, New York.Google Scholar
  7. Leu, J.G. and H.L. Yau (1991). Detecting the Dislocations in Metal Crystals from Microscopic Images, Pattern Recognition, 24(1), 41–56.CrossRefGoogle Scholar
  8. Medioni, G & Nevatia, R. (1985). Segment Based Stereo Matching. Computer Vision, Graphics, and Image Processing, 31, 2–18.Google Scholar
  9. Mousavi, M.S. and R.J. Schalkoff (1994). ANN Implementation of stereo vision using a multi-layer feedback architecture. IEEE Trans. Sys. Man Cybern. 24(8), 1220–1238.CrossRefGoogle Scholar
  10. Nevatia, R. and K.R. Babu (1980). Linear Feature Extraction and Description. Computer Vision Graphics Image Processing 13, 257–269.CrossRefGoogle Scholar
  11. Ozanian, T. (1995). Approaches for Stereo Matching-A Review. Modeling Identification Control 16(2), 65–94.Google Scholar
  12. Pajares, G. (1995). Estrategia de Solucion al Problema de la Correspondencia en Vision Estereoscópica por la Jerarquia Metodológica y la Integración de Criterios, PhD thesis, Dpto. Informática y Automática, Facultad Ciencias UNED: Madrid.Google Scholar
  13. Tanaka, S. and A.C. Kak (1990). A Rule-Based Approach to Binocular stereopsis. In: R.C. Jain and A.K. Jain, Eds., Analysis and interpretation of range images, Springer-Verlag, Berlin, 33–139.Google Scholar
  14. Traven, H.G.C. (1991). A neural Network Approach to Statistical Pattern Classification by Semiparametric Estimation of Probability Density Functions. IEEE Transactions Neural Networks, 2, 366–377.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Gonzalo Pajares
    • 1
  • Jesûs Manuel de la Cruz
    • 1
  • José A. López
    • 1
  1. 1.Dpto. Arquitectura de Computadores y Automática. Facultad de Ciencias FísicasUniversidad ComplutenseMadridSpain

Personalised recommendations