Modelling the Human Visual Process by Evolving Images from Noise

  • Sameer Singh
  • Andrew Payne
  • Roman Kingsland
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4153)


The modelling of human visual process is considerably important for developing future autonomous agents such as mobile robots with vision capability. The future efforts will be directed at using this knowledge to develop powerful new algorithms that mimic the human vision capability. In this paper we focus on the process of how the human eye forms an image. We use genetic algorithms to synthetically model this process and interpret the results on different types of objects. In particular, we investigate which of the image properties stabilise early and which ones later, i.e. as the image forms iteratively, does the shape appear before the texture?


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bounsaythip, C., Alander, J.: Genetic Algorithms in Image Processing - A Review. In: Proc. of the 3rd Nordic Workshop on Genetic Algorithms and their Applications, Metsatalo, Univ. of Helsinki, Helsinki, Finland, pp. 173–192 (1997)Google Scholar
  2. 2.
    Marshall, S., Harvey, N.R., Greenhalgh, D.: Design of Morphological Filters Using Genetic Algorithms. In: Mathematical Morphology and Its Applications to Image Processing (1994)Google Scholar
  3. 3.
    Zhang, Y.J.: A Survey on Evaluating Methods for Image Segmentation. Pattern Recognition 29(8), 1246–1335 (1996)CrossRefGoogle Scholar
  4. 4.
    Ramos, V., Muge, F.: Image Colour Segmentation by Genetic Algorithms. In: RecPad 2000 Portugese conferernce on Pattern Recognition, pp. 125–129 (2000)Google Scholar
  5. 5.
    Munteanu, C., Rosa, A.: Evolutionary Image Enhancement with User Behaviour Modelling. In: Proceedings of the 2001 ACM Symposium on Applied Computing, pp. 316–320 (2001)Google Scholar
  6. 6.
    Munteanu, C., Rosa, A.: Towards Automatic Image Enhancement Using Genetic Algorithms. In: Proceedings of the IEEE conference on Evolutionary Computation, vol. 4, pp. 1535–1542 (2000)Google Scholar
  7. 7.
    Otobe, K., Tanaka, K., Hirafuji, M.: Knowledge Acquisition on Image Processing Based On Genetic Algorithms. In: Proceedings of the IASTED International Conference on Signal and Image Processing, pp. 28–31 (1998)Google Scholar
  8. 8.
    Brumby, S.P., Harvey, N.R., Perkins, S., Porter, R.B., Szymanski, J.J., Theiler, J., Bloch, J.J.: A Genetic Algorithm for Combining New and Existing Image Processing Tools for Multispectral Imagery. In: Proceedings of SPIE (2000)Google Scholar
  9. 9.
    Poli, R.: Genetic Programming for Image Analysis. In: Proceedings of Genetic Programming, pp. 363–368 (1996)Google Scholar
  10. 10.
    Coello, C.A.: An Updated Survey of GA-Based Multiobjective Optimisation Techniques. ACM Computing Surveys 32(2) (June 2000)Google Scholar
  11. 11.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Transactions on System, Man, Cybernetics SMC-3, 610–621 (1973)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sameer Singh
    • 1
  • Andrew Payne
    • 1
  • Roman Kingsland
    • 1
  1. 1.Research School of InfomaticsLoughboroughUK

Personalised recommendations