Detecting Scale-Invariant Regions Using Evolved Image Operators

  • Leonardo Trujillo
  • Gustavo Olague
Part of the Studies in Computational Intelligence book series (SCI, volume 213)

Abstract

This chapter describes scale-invariant region detectors that are based on image operators synthesized through Genetic Programming (GP). Interesting or salient regions on an image are of considerable usefulness within a broad range of vision problems, including, but not limited to, stereo vision, object detection and recognition, image registration and content-based image retrieval. A GP-based framework is described where candidate image operators are synthesized by employing a fitness measure that promotes the detection of stable and dispersed image features, both of which are highly desirable properties. After a significant number of experimental runs, a plateau of maxima was identified within the search space that contained operators that are similar, in structure and/or functionality, to basic LoG or DoG filters. Two such operators with the simplest structure were selected and embedded within a linear scale space, thereby making scale-invariant feature detection a straightforward task. The proposed scale-invariant detectors exhibit a high performance on standard tests when compared with state-of-the-art techniques. The experimental results exhibit the ability of GP to construct highly reusable code for a well known and hard task when an appropriate optimization problem is framed.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. Henry Holt and Co., Inc., New York (1982)Google Scholar
  2. 2.
    Kumar, M.P., Torr, P.H.S., Zisserman, A.: Obj cut. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 20-26, vol. 1, pp. 18–25. IEEE Computer Society, San Diego (2005)CrossRefGoogle Scholar
  3. 3.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision 37(2), 151–172 (2000)MATHCrossRefGoogle Scholar
  4. 4.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision 42(3), 145–175 (2001)MATHCrossRefGoogle Scholar
  5. 5.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 17-22, vol. 2, pp. 2169–2178. IEEE Computer Society, New York (2006)Google Scholar
  6. 6.
    Olague, G., Romero, E., Trujillo, L., Bhanu, B.: Multiclass object recognition based on texture linear genetic programming. In: Giacobini, M. (ed.) EvoWorkshops 2007. LNCS, vol. 4448, pp. 291–300. Springer, Heidelberg (2007)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  8. 8.
    Willamowski, J., Arregui, D., Csurka, G., Dance, C., Fan, L.: Categorizing nine visual classes using local appearance descriptors. In: Proceedings of the 17th International Conference on Pattern Recognition, Workshop Learning for Adaptable Visual Systems, August 23-26. IEEE Computer Society, Cambridge (2004)Google Scholar
  9. 9.
    Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their localization in images. In: Proceedings of the 10th IEEE International Conference on Computer Vision (ICCV), Beijing, China, October 17-20, vol. 1, pp. 370–377. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  10. 10.
    Trujillo, L., Olague, G., de Vega, F.F., Lutton, E.: Evolutionary feature selection for probabilistic object recognition, novel object detection and object saliency estimation using gmms. In: Proceedings from the 18th British Machine Vision Conference, Warwick, UK, September 10-13, British Machine Vision Association (2007)Google Scholar
  11. 11.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proceedings from the Fourth Alvey Vision Conference, vol. 15, pp. 147–151 (1988)Google Scholar
  12. 12.
    Trujillo, L., Olague, G.: Synthesis of interest point detectors through genetic programming. In: Cattolico, M. (ed.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), Seattle, Washington, July 8-12, vol. 1, pp. 887–894. ACM, New York (2006)CrossRefGoogle Scholar
  13. 13.
    Trujillo, L., Olague, G.: Using evolution to learn how to perform interest point detection. In: Proceedings of the 18th International Conference on Pattern Recognition (ICPR), Hong Kong, China, August 20-24, vol. 1, pp. 211–214. IEEE Computer Society, Los Alamitos (2006)Google Scholar
  14. 14.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the International Conference on Computer Vision (ICCV), Kerkyra, Corfu, Greece, September 20-25, vol. 2, pp. 1150–1157. IEEE Computer Society, Los Alamitos (1999)CrossRefGoogle Scholar
  15. 15.
    Trujillo, L., Olague, G., Legrand, P., Lutton, E.: Regularity based descriptor computed from local image oscillations. Optics Express 15, 6140–6145 (2007)CrossRefGoogle Scholar
  16. 16.
    Beaudet, P.R.: Rotational invariant image operators. In: Proceedings of the 4th International Joint Conference on Pattern Recognition (ICPR), Tokyo, Japan, pp. 579–583 (1978)Google Scholar
  17. 17.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)CrossRefGoogle Scholar
  18. 18.
    Trujillo, L., Olague, G.: Scale invariance for evolved interest operators. In: Giacobini, M. (ed.) EvoWorkshops 2007. LNCS, vol. 4448, pp. 423–430. Springer, Heidelberg (2007)Google Scholar
  19. 19.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. International Journal of Computer Vision 65(1-2), 43–72 (2005)CrossRefGoogle Scholar
  20. 20.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)MATHGoogle Scholar
  21. 21.
    Poli, R., Langdon, W.B., McPhee, N.F.: A field guide to genetic programming (2008) (with contributions by J. R. Koza), http://lulu.com, http://www.gp-field-guide.org.uk
  22. 22.
    Ebner, M.: On the evolution of interest operators using genetic programming. In: Poli, R., et al. (eds.) Late Breaking Papers at EuroGP 1998, pp. 6–10. The University of Birmingham, UK (1998)Google Scholar
  23. 23.
    Ebner, M., Zell, A.: Evolving task specific image operator. In: Poli, R., Voigt, H.-M., Cagnoni, S., Corne, D.W., Smith, G.D., Fogarty, T.C. (eds.) EvoIASP 1999 and EuroEcTel 1999. LNCS, vol. 1596, pp. 74–89. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  24. 24.
    Lindeberg, T.: Discrete scale-space theory and the scale-space primal sketch. PhD thesis, Computational Vision and Active Perception Laboratory (CVAP), Royal Institute of Technology, Stockholm, Sweden (1991)Google Scholar
  25. 25.
    Asada, H., Brady, M.: The curvature primal sketch. IEEE Trans. Pattern Anal. Mach. Intell. 8(1), 2–14 (1986)CrossRefGoogle Scholar
  26. 26.
    Mokhtarian, F., Suomela, R.: Robust image corner detection through curvature scale space. IEEE Trans. Pattern Anal. Mach. Intell. 20(12), 1376–1381 (1998)CrossRefGoogle Scholar
  27. 27.
    Rohr, K.: Recognizing corners by fitting parametric models. Int. J. Comput. Vision 9(3), 213–230 (1992)CrossRefGoogle Scholar
  28. 28.
    Olague, G., Hernández, B.: A new accurate and flexible model based multi-corner detector for measurement and recognition. Pattern Recognition Letters 26(1), 27–41 (2005)CrossRefGoogle Scholar
  29. 29.
    Moravec, H.P.: Towards automatic visual obstacle avoidance. In: IJCAI, p. 584 (1977)Google Scholar
  30. 30.
    Kitchen, L., Rosenfeld, A.: Gray-level corner detection. Pattern Recognition Letters 1, 95–102 (1982)CrossRefGoogle Scholar
  31. 31.
    Wang, H., Brady, J.: Corner detection for 3d vision using array processors. In: Proceedings from BARNAIMAGE 1991, Barcelona, Spain, Secaucus, NJ. Springer, Heidelberg (1991)Google Scholar
  32. 32.
    Förstner, W.: A framework for low level feature extraction. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 383–394. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  33. 33.
    Shi, J., Tomasi, C.: Good features to track. In: Proceedings of the 1994 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, pp. 593–600. IEEE Computer Society, Los Alamitos (1994)Google Scholar
  34. 34.
    Smith, S.M., Brady, J.M.: Susan-a new approach to low level image processing. Int. J. Comput. Vision 23(1), 45–78 (1997)CrossRefGoogle Scholar
  35. 35.
    Tissainayagam, P., Suter, D.: Assessing the performance of corner detectors for point feature tracking applications. Image Vision Comput. 22(8), 663–679 (2004)CrossRefGoogle Scholar
  36. 36.
    Trujillo, L., Olague, G.: Automated design of image operators that detect interest points. Evolutionary Computation (to appear) (2008)Google Scholar
  37. 37.
    Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: Sridharan, S. (ed.) Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 762–767. Morgan Kaufman, San Francisco (1989)Google Scholar
  38. 38.
  39. 39.
    Young, R.A.: Simulation of human retinal function with the gaussian derivative model. In: Proceedings of the 1986 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 564–569. IEEE, Los Alamitos (1986)Google Scholar
  40. 40.
    Lindeberg, T.: Feature detection with automatic scale selection. International Journal of Computer Vision 30(2), 79–116 (1998)CrossRefGoogle Scholar
  41. 41.
    Kadir, T., Brady, M.: Saliency, scale and image description. International Journal of Computer Vision 45(2), 83–105 (2001)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Leonardo Trujillo
    • 1
  • Gustavo Olague
    • 1
  1. 1.Centro de Investigación Científica y de Educación Superior de EnsenadaEnsenadaMéxico

Personalised recommendations