Advertisement

Particle Swarm Optimization for Object Recognition in Computer Vision

  • Hugo A. Perlin
  • Heitor S. Lopes
  • Tânia Mezzadri Centeno
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5027)

Abstract

Particle Swarm Optimization (PSO) is an evolutionary computation technique frequently used for optimization tasks. This work aims at applying PSO for recognizing specific patterns in complex images. Experiments were done with gray level and color images, with and without noise. PSO was able to find predefined reference images, submitted to translation, rotation, scaling, occlusion, noise and change in the viewpoint in the landscape image. Several experiments were done to evaluate the performance of PSO. Results show that the proposed method is robust and very promising for real-world applications.

Keywords

Particle Swarm Optimization Search Space Color Image Object Recognition Reference 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jain, R., Kasturi, R., Schunck, B.G.: Machine Vision. McGraw-Hill, New York (1995)Google Scholar
  2. 2.
    Felizberto, M.K., Centeno, T.M., Lopes, H.S.: Object detection for computer vision using a robust genetic algorithm. In: Rothlauf, F., Branke, J., Cagnoni, S., Corne, D.W., Drechsler, R., Jin, Y., Machado, P., Marchiori, E., Romero, J., Smith, G.D., Squillero, G. (eds.) EvoWorkshops 2005. LNCS, vol. 3449, pp. 284–293. Springer, Heidelberg (2005)Google Scholar
  3. 3.
    Felizberto, M.K., Lopes, H.S., Centeno, T.M., Arruda, L.V.R.: An object detection and recognition system for weld bead extraction from digital radiographs. Comput. Vis. Image Unders. 102, 238–249 (2006)CrossRefGoogle Scholar
  4. 4.
    Guerra, C., Pascucci, V.: Find line segments with tabu search. IEICE Trans. Inf. Syst. E84-D(12), 1739–1744 (2001)Google Scholar
  5. 5.
    Eberhart, R.C., Kennedy, J.: Swarm Intelligence. Morgan Kaufmann, San Francisco (2001)Google Scholar
  6. 6.
    Hembecker, F., Lopes, H.S., Godoy Jr., W.: Particle swarm optimization for the multidimensional knapsack problem. In: Min, G., Di Martino, B., Yang, L.T., Guo, M., Rünger, G. (eds.) ISPA Workshops 2006. LNCS, vol. 4331, pp. 358–365. Springer, Heidelberg (2006)Google Scholar
  7. 7.
    Lopes, H.S., Coelho, L.S.: Particle swarm optimization with fast local search for the blind traveling salesman problem. In: Proc. 5th Int. Conf. on Hybrid Intelligent Systems, pp. 245–250 (2005)Google Scholar
  8. 8.
    Talbi, H., Batouche, M.: Hybrid particle swam with differential evolution for multimodal image registration. In: Proc. IEEE Int. Conf. on Industrial Technology (ICIT), pp. 1568–1572 (2004)Google Scholar
  9. 9.
    Wachowiak, M.P., Smolíková, R., Zurada, J.M., Elmaghraby, E.: An approach to multimodal biomedical image registration utilizing particle swarm optimization. IEEE Trans. Evolut. Comput. 8(3), 289–301 (2004)CrossRefGoogle Scholar
  10. 10.
    Maruo, M.H., Lopes, H.S., Delgado, M.R.B.S.: Self-Adapting Evolutionary Parameters: Encoding Aspects for Combinatorial Optimization Problems. In: Raidl, G.R., Gottlieb, J. (eds.) EvoCOP 2005. LNCS, vol. 3448, pp. 154–165. Springer, Heidelberg (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Hugo A. Perlin
    • 1
  • Heitor S. Lopes
    • 1
  • Tânia Mezzadri Centeno
    • 1
  1. 1.Bioinformatics LaboratoryFederal University of Technology Paraná (UTFPR)Curitiba (PR)Brazil

Personalised recommendations