The Log-polar Image Representation in Pattern Recognition Tasks

  • V. Javier Traver
  • Filiberto Pla
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2652)


This paper is a review of works about the use of the log-polar image model for pattern recognition purposes. Particular attention is paid to the rotation- and scale-invariant pattern recognition problem, which is simplified by the log-polar mapping. In spite of this advantage, ordinary translations become a complicated image transform in the log-polar domain. Two approaches addressing the estimation of translation, rotation and scaling are compared. One of them, developed by the authors, takes advantage of the principles of the active vision paradigm.


Active Vision Object Recognition Task Pattern Recognition Task Handwritten Numeral Cartesian 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.
    Aloimonos, J.Y., Weiss, I., Bandyopadhyay, A.: Active vision. Intl. Journal of Computer Vision, 333–356 (1988)Google Scholar
  2. 2.
    Ballard, D.H.: Animate vision. Artificial Intelligence 48, 57–86 (1991)CrossRefGoogle Scholar
  3. 3.
    Bartlett, S.L., Hampapur, A., Huber, M.J., Kortenkamp, D., Moezzi, S.: Vision for mobile robots. In: Sanz, J.L.C. (ed.) Image Technology: Advances in Image Processing, Multimedia and Machine Vision, pp. 1–37. Springer, Heidelberg (1996)Google Scholar
  4. 4.
    Bernardino, A., Santos-Victor, J.: Sensor geometry for dynamic vergence: Characterization and performance analysis. In: Workshop on Performance Characteristics of Vision Algorithms, ECCV (1996) (Also as TR 01/96 at VisLab, Lisbon, Portugal)Google Scholar
  5. 5.
    Bolduc, M., Levine, M.D.: A review of biologically motivated space-variant data reduction models for robotic vision. Computer Vision and Image Understanding (CVIU) 69(2), 170–184 (1998)CrossRefGoogle Scholar
  6. 6.
    Bonmassar, G., Schwartz, E.L.: Space-variant Fourier analysis: The exponential chirp transform. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) 19(10), 1080–1089 (1997)CrossRefGoogle Scholar
  7. 7.
    Capodiferro, L., Cusani, R., Jacovitti, G., Vascotto, M.: A correlation based technique for shift, scale and rotation independent object identification. In: Intl. Conf. on Acoustics, Speech, and Signal Processing, vol. 1, pp. 221–224 (1987)Google Scholar
  8. 8.
    Capurro, C., Panerai, F., Sandini, G.: Vergence and tracking fusing log-polar images. In: Intl. Conf. on Pattern Recognition (ICPR), pp. 740–744. IEEE, Los Alamitos (1996)CrossRefGoogle Scholar
  9. 9.
    Debevec, P.: A neural network for facial feature location. C283 Course report, Berkeley University (Fall 1992),
  10. 10.
    Hotta, K., Kurita, T., Mishima, T.: Scale invariant face recogniton method using spectral features in log-polar image. In: Applications of Digital Image Processing XXII (SPIE Proc.), pp. 33–43 (1999)Google Scholar
  11. 11.
    Jurie, F.: A new log-polar mapping for space variant imaging. Application to face detection and tracking. Pattern Recognition 32, 865–875 (1999)CrossRefGoogle Scholar
  12. 12.
    Kehtarnavaz, N., Ahmad, A.: Traffic sign recognition in noisy outdoor scenes. In: IEEE Intl. Conf. on Intelligent Vehicles, pp. 460–565 (1995)Google Scholar
  13. 13.
    Koh, L.H., Ranganath, S., Lee, M.W., Venkatesth, Y.V.: An integrated face detection and recognition system. In: Intl. Conf. on Image Analysis and Processing (ICIAP), Venice, Italy (September 1999)Google Scholar
  14. 14.
    Lee, S., Horprasert, T.: Recognition of handwritten connected numerals based on dual cooperative neural network. In: Intl. Conf. on Neural Networks, Perth, Australia (December 1995)Google Scholar
  15. 15.
    Lim, F.L., West, G.A.W., Venkatesh, S.: Use of log polar space for foveation and feature recognition. IEE Proc. Vis. Image Signal Process. 144(6), 323–331 (1997)CrossRefGoogle Scholar
  16. 16.
    Massone, L., Sandini, G., Tagliasco, V.: ‘Form-Invariant’ topological mapping strategy for 2D shape recognition. Computer Vision, Graphics, and Image Processing 30, 169–188 (1985)CrossRefGoogle Scholar
  17. 17.
    Mikrut, Z., Augustyn, G.: Influence of the object representation on the results of characters recognition in the car’s licence plates. In: 5th Conf. on Neural Networks and Soft Computing, Zakopane, Poland (June 2000)Google Scholar
  18. 18.
    Mikrut, Z., Czwartkowski, B.: Log-Hough space as input for a neural network. In: 4th Conf. on Neural Networks and their Applications, Zakopane, Poland (May 1999)Google Scholar
  19. 19.
    Schwartz, E.L.: Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception. Biological Cybernetics 25, 181–194 (1977)CrossRefGoogle Scholar
  20. 20.
    Thornton, A.L.: Color Object Recognition Using a Complex Colour Representation and the Frequency Domain. PhD thesis, Department of Engineering, The University of Reading (May 1998)Google Scholar
  21. 21.
    Tistarelli, M.: Active/space-variant object recognition. Image and Vision Computing (IVC) 13(3), 215–226 (1995)CrossRefGoogle Scholar
  22. 22.
    Tistarelli, M., Grosso, E.: Active vision-based face authentication. Image and Vision Computing (IVC) 18, 299–314 (2000)CrossRefGoogle Scholar
  23. 23.
    Tistarelli, M., Sandini, G.: Estimation of depth from motion using an anthropomorphic visual sensor. Image and Vision Computing (IVC) 8(4), 271–278 (1990)CrossRefGoogle Scholar
  24. 24.
    Tistarelli, M., Sandini, G.: On the advantages of polar and log-polar mapping for direct estimation of time-to-impact from optical flow. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) 15, 401–410 (1993)CrossRefGoogle Scholar
  25. 25.
    Traver, V.J.: Motion Estimation Algorithms in Log-polar Images and Application to Monocular Active Tracking. PhD thesis, Dep. Llenguatges i Sistemes Informàtics, Universitat Jaume I, Castellón (Spain) (September 2002)Google Scholar
  26. 26.
    Traver, V.J., Pla, F.: Dealing with 2D translation estimation in log-polar imagery. Image and Vision Computing (IVC) 21(3), 145–160 (2003)CrossRefGoogle Scholar
  27. 27.
    Weiman, C.F.R.: Polar exponential sensor arrays unify iconic and Hough space representation. In: SPIE Conf. on Intelligent Robots and Computer Vision VIII: Algorithms and Techniques, Philadelphia, November 1989, vol. 1192 (1989)Google Scholar
  28. 28.
    Wilson, J.C., Hodgson, R.M.: Log-polar mapping applied to pattern representation and recognition. Computer Vision and Image Processing, 245–277 (1992)Google Scholar
  29. 29.
    Wodnicki, R., Roberts, G.W., Levine, M.D.: A foveated image sensor in standard CMOS technology. In: Custom Integrated Circuits Conf., Santa Clara (May 1995)Google Scholar
  30. 30.
    Young, D.: Straight lines and circles in the log-polar image. In: British Machine Vision Conference, Bristol, UK (September 2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • V. Javier Traver
    • 1
  • Filiberto Pla
    • 1
  1. 1.Dep. de Llenguatges i Sistemes InformàticsUniversitat Jaume ICastellóSpain

Personalised recommendations