Multiobjective Genetic Algorithm for Image Thresholding

  • Layla Tahri
  • Mohamed Wakrim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7340)

Abstract

In this paper we present a new image thresholding method based on a multiobjective Genetic Algorithm using the Pareto optimality approach. We aim to optimize multiple criteria in order to increase the segmentation quality. Thus, we’ve adapted the well-known Non Domination Sorting Genetic Algorithm [1] for this purpose so that it takes into consideration the contribution of the objective functions in improving the reproduction step and then improving the optimal Pareto front of solutions. Our method was tested against NSGAII algorithm and has shown effectiveness and convergence speed.

Keywords

Evolutionary approach Genetic algorithms Image segmentation Image thresholding Multiobjective optimization Pareto optimization 

References

  1. 1.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6(2), 182–197 (2002)CrossRefGoogle Scholar
  2. 2.
    Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. on Syst., Man and Cyb. 9(1), 62–66 (1979)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Kapur, J.N., Sahoo, P.K., Wong, A.C.K.: A new method for gray-level picture thresholding using the entropy of the histogram. Computer Vision, Graphics and Image Processing 29, 273–285 (1985)CrossRefGoogle Scholar
  4. 4.
    Pal, N.K., Pal, S.K.: Entropy: A new definition and its applications. IEEE Trans. Syst. Man. Cybern. 21, 1260–1270 (1991)CrossRefGoogle Scholar
  5. 5.
    Nakib, A.: Conception de métaheuristiques d’optimisation pour la segmentation d’images. Application à des images biomédicales, pp. 9–10 (2008)Google Scholar
  6. 6.
    Deb, K., Kumar, A.: Real-coded Genetic Algorithms with Simulated Binary Crossover: Studies on Multimodal and Multiobjective Problems. Complex Systems, 431–454 (1995)Google Scholar
  7. 7.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Layla Tahri
    • 1
  • Mohamed Wakrim
    • 1
  1. 1.Faculty of Sciences, EMMSIbnZohr UniversityAgadirMorocco

Personalised recommendations