Feed Forward Genetic Image Network: Toward Efficient Automatic Construction of Image Processing Algorithm

  • Shinichi Shirakawa
  • Tomoharu Nagao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4842)

Abstract

A new method for automatic construction of image transformation, Feed Forward Genetic Image Network (FFGIN), is proposed in this paper. FFGIN evolves feed forward network structured image transformation automatically. Therefore, it is possible to straightforward execution of network structured image transformation. The genotype in FFGIN is a fixed length representation and consists of string which encode the image processing filter ID and connections of each node in the network. In order to verify the effectiveness of FFGIN, we apply FFGIN to the problem of automatic construction of image transformation which is “pasta segmentation” and compare with several method. From the experimental results, it is verified that FFGIN automatically constructs image transformation. Additionally, obtained structure by FFGIN is unique, and reuses the transformed images.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aoki, S., Nagao, T.: Automatic construction of tree-structural image transformation using genetic programming. In: Proceedings of the 1999 International Conference on Image Processing (ICIP 1999), Kobe, Japan, vol. 1, pp. 529–533. IEEE, Los Alamitos (1999)CrossRefGoogle Scholar
  2. 2.
    Nakano, Y., Nagao, T.: 3D medical image processing using 3D-ACTIT; automatic construction of tree-structural image transformation. In: Proceedings of the International Workshop on Advanced Image Technology (IWAIT-2004), Singapore, pp. 529–533 (2004)Google Scholar
  3. 3.
    Nakano, Y., Nagao, T.: Automatic construction of abnormal signal extraction processing from 3D diffusion weighted image. In: Proceedings of the International Workshop on Advanced Image Technology (IWAIT-2007), Bangkok, Thailand (2007)Google Scholar
  4. 4.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)MATHGoogle Scholar
  5. 5.
    Koza, J.R.: Genetic Programming II: Automatic Discovery of Reusable Programs. MIT Press, Cambridge (1994)MATHGoogle Scholar
  6. 6.
    Shirakawa, S., Nagao, T.: Genetic image network (GIN): Automatically construction of image processing algorithm. In: Proceedings of the International Workshop on Advanced Image Technology (IWAIT-2007), Bangkok, Thailand (2007)Google Scholar
  7. 7.
    Teller, A., Veloso, M.: Algorithm evolution for face recognition: What makes a picture difficult. In: International Conference on Evolutionary Computation, Perth, Australia, pp. 608–613. IEEE Press, Los Alamitos (1995)CrossRefGoogle Scholar
  8. 8.
    Teller, A., Veloso, M.: PADO: A new learning architecture for object recognition. In: Ikeuchi, K., Veloso, M. (eds.) Symbolic Visual Learning, pp. 81–116. Oxford University Press, Oxford (1996)Google Scholar
  9. 9.
    Poli, R.: Evolution of graph-like programs with parallel distributed genetic programming. In: Proceedings of the Seventh International Conference on Genetic Algorithms, East Lansing, MI, USA, pp. 346–353. Morgan Kaufmann, San Francisco (1997)Google Scholar
  10. 10.
    Miller, J.F., Smith, S.L.: Redundancy and computational efficiency in cartesian genetic programming. IEEE Transactions on Evolutionary Computation 10, 167–174 (2006)CrossRefGoogle Scholar
  11. 11.
    Miller, J.F., Thomson, P.: Cartesian genetic programming. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds.) EuroGP 2000. LNCS, vol. 1802, pp. 121–132. Springer, Heidelberg (2000)Google Scholar
  12. 12.
    Hirasawa, K., Okubo, M., Hu, J., Murata, J.: Comparison between genetic network programming (GNP) and genetic programming (GP). In: Proceedings of the 2001 Congress on Evolutionary Computation (CEC 2001), Seoul, Korea, pp. 1276–1282. IEEE Computer Society Press, Los Alamitos (2001)CrossRefGoogle Scholar
  13. 13.
    Eguchi, T., Hirasawa, K., Hu, J., Ota, N.: A study of evolutionary multiagent models based on symbiosis. IEEE Transactions on Systems, Man and Cybernetics Part B 36, 179–193 (2006)CrossRefGoogle Scholar
  14. 14.
    Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87, 1423–1447 (1999)CrossRefGoogle Scholar
  15. 15.
    Stanley, K.O.: Efficient evolution of neural networks through complexification. Technical Report AI-TR-04-314, Ph.D. Thesis; Department of Computer Sciences, The University of Texas at Austin (2004)Google Scholar
  16. 16.
    Satoh, H., Yamamura, M., Kobayashi, S.: Minimal generation gap model for considering both exploration and exploitations. In: Proceedings of the IIZUKA 1996, pp. 494–497 (1996)Google Scholar
  17. 17.
    Kita, H., Ono, I., Kobayashi, S.: Multi-parental extension of the unimodal normal distribution crossover for real-coded genetic algorithms. In: Proceedings of the 1999 Congress on Evolutionary Computation (CEC 1999), vol. 2, pp. 1581–1587 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Shinichi Shirakawa
    • 1
  • Tomoharu Nagao
    • 1
  1. 1.Graduate School of Environment and Information Sciences, Yokohama National University, 79-7, Tokiwadai, Hodogaya-ku, Yokohama, Kanagawa, 240-8501Japan

Personalised recommendations