Advertisement

An Oscillatory Neural Network for Image Segmentation

  • Dênis Fernandes
  • Philippe Olivier Alexandre Navaux
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)

Abstract

Oscillatory neural networks are a recent approach for applications in image segmentation. Two positive aspects of such networks are its massively parallel topology and the capacity to separate the segments in time. On the other hand, limitations that restrict the practical application are found in the proposed oscillatory networks, such as the use of differential equations, implying high complexity for implementation in digital hardware, and limited capacity of segmentation. In the present paper, an oscillatory neural network suitable for image segmentation in digital vision chips is presented. This network offers several advantages, including unlimited capacity of segmentation. Preliminary results confirm the successful operation of the proposal in image segmentation and its good potential for real time video segmentation.

Keywords

Image Segmentation Input Image Inhibitory Connection Oscillator Network Neighboring Neuron 
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.

References

  1. 1.
    ALTERA, MAX+PLUS II Software Overview (June 20, 2002), http://www.altera.com/products/sofware/maxplus2/mp2-index.html
  2. 2.
    Ando, H., Miyake, M., Morie, T., Nagata, M., Iwata, A.: A Nonlinear Oscillator Network Circuit for Image Segmentation with Double-threshold Phase Detection. In: ICANN 1999, pp. 655–660. IEE, Edinburgh (1999)Google Scholar
  3. 3.
    Barbaro, M., Burgi, P., Mortara, A., Nussbaum, P., Heitger, F.: A 100x100 Pixel Silicon Retina for Gradient Extraction With Steering Filter Capabilities and Temporal Output Coding. IEEE Journal of Solid-State Circuits 37(2), 160–172 (2002)CrossRefGoogle Scholar
  4. 4.
    Buhmann, J., von der Malsburg, C.: Sensory Segmentation by Neural Oscillators. In: IJCNN 1991, pp. II603–II607. IEEE, Seattle (1991)Google Scholar
  5. 5.
    Chen, K., Wang, D.: Image Segmentation Based on a Dynamically Coupled Neural Oscillator Network. In: IJCNN 1999, IEEE, Washington (1999)Google Scholar
  6. 6.
    Cosp, J., Madrenas, J.: A Neural Network for Scene Segmentation Based on Compact Astable Oscillators. In: ICANN 1999, pp. 690–695. IEE, Edinburgh (1999)Google Scholar
  7. 7.
    Fernandes, D., Navaux, P.O.A., Fichtner, P.F.P.: Segmentation of TEM Images Using Oscillatory Neural Networks. In: SIBGRAPI 2001, pp. 289–296. IEEE, Florianópolis (2001)Google Scholar
  8. 8.
    Fernandes, D., Siqueira, M.L., Navaux, P.O.A.: Segmentation of Fetal Echocardiographic Images Using Self-Organizing Maps and Oscillatory Neural Networks. In: SIARP 2001, IARP, Florianópolis, Brazil, pp. 55–60 (2001)Google Scholar
  9. 9.
    Fernandes, D., Stedile, J.P., Navaux, P.O.A.: Architecture of Oscillatory Neural Network for Image Segmentation. In: SBAC-PAD 2002, IEEE, Vitória (2002)Google Scholar
  10. 10.
    Komuro, T., Ishii, I., Ishikawa, M.: Digital Vision Chips and High-Speed Vision Systems. In: Symposium on VLSI Circuits Digest of Technical Papers, pp. 1–4. IEEE, Kyoto (2001)Google Scholar
  11. 11.
    Kurokawa, H., Mori, S.: A Local Connected Neural Oscillator Network for Sequential Character Segmentation. In: ICNN 1997, pp. 838–843. IEEE, Texas (1997)Google Scholar
  12. 12.
    Liu, X., Chen, K., Wang, D.L.: Extraction of hydrographic regions from remote sensing images using an oscillator network with weight adaptation. Transactions on GeoScience and Remote Sensing, IEEE 39(1), 207–211 (2001)CrossRefGoogle Scholar
  13. 13.
    Shareef, N., Wang, D.L., Yagel, R.: Segmentation of Medical Images Using LEGION. Transactions on Medical Imaging 18(1). IEEE (1999)Google Scholar
  14. 14.
    Terman, D., Wang, D.L.: Global competition and local cooperation in a network of neural oscillators. Physica D. 81(1-2), 148–176 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Wang, D., Terman, D.: Image Segmentation Based on Oscillatory Correlation. Neural Computation, MIT 9, 805–836 (1997)CrossRefGoogle Scholar
  16. 16.
    Wang, D.: Relaxation Oscillators and Networks. Wiley Encyclopedia of Electrical and Electronics Engineering 18, 396–405 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Dênis Fernandes
    • 1
  • Philippe Olivier Alexandre Navaux
    • 2
  1. 1.PUCRS – Faculdade de EngenhariaPontifícia Universidade Católica do Rio Grande do SulPorto AlegreBrazil
  2. 2.UFRGS – Instituto de InformáticaUniversidade Federal do Rio Grande do SulPorto AlegreBrazil

Personalised recommendations