Active Contour with Neural Networks-Based Information Fusion Kernel

  • Xiongcai Cai
  • Arcot Sowmya
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


This paper proposes a novel active contour model for image object recognition using neural networks as a dynamic information fusion kernel. It first learns feature fusion strategies from training data by searching for an optimal fusion model at each marching step of the active contour model. A recurrent neural network is then employed to learn the fusion strategy knowledge. The learned knowledge is then applied to guide another linear neural network to fuse the features, which determine the marching procedures of an active contour model for object recognition. We test our model on both artificial and real image data sets and compare the results to those of a standard active model, with promising outcomes.


Active Contour Recurrent Neural Network Information Fusion Active Contour Model Object Extraction 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision, 321–331 (1988)Google Scholar
  2. 2.
    Cohen, L.: On active contour models and balloons. CVGIP Image Understanding 53 (1991)Google Scholar
  3. 3.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. In: ICCV 1995, Cambridge, USA, pp. 694–699 (1995)Google Scholar
  4. 4.
    Cohen, L.D., Kimmel, R.: Global minimum for active contour models: A minimal path approach. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 666–673 (1996)Google Scholar
  5. 5.
    Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape modeling with front propagation: a level set approach. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(2) (1995)Google Scholar
  6. 6.
    Geman, D., Jedynak, B.: An active testing model for tracking roads in satellite images. IEEE Trans. Pattern Anal. Machine Intell. 18(1) (1996)Google Scholar
  7. 7.
    Cai, X., Sowmya, A., Trinder, J.: Learning Parameter Tuning for Object Extraction. In: Narayanan, P.J., Nayar, S.K., Shum, H.-Y. (eds.) ACCV 2006. LNCS, vol. 3851, pp. 868–877. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Cai, X., Sowmya, A., Trinder, J.: Learning to recognise roads from high resolution remotely sensed images. In: The 2nd International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Melbourne, pp. 307–312. IEEE, Los Alamitos (2005)Google Scholar
  9. 9.
    Chan, T., Vese, L.: Active contours without edges. IEEE Transactions on Image Processin 10(2), 266–277 (2001)MATHCrossRefGoogle Scholar
  10. 10.
    Chan, T., Sandberg, B., Vese, L.: Active contours without edges for vector valued images. Journal of Visual Communication and Image Representation 11, 130–141 (2000)CrossRefGoogle Scholar
  11. 11.
    Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)MATHGoogle Scholar
  12. 12.
    Elman, J.: Finding structure in time. Congitive Science 14, 179–210 (1990)CrossRefGoogle Scholar
  13. 13.
    Rudrapatna, M., Sowmya, A., Zrimec, T., Wilson, P., Kossoff, G., Lucas, P., Wong, J., Misra, A., Busayarat, S.: Lmik learning medical image knowledge: An internet-based medical image knowledge acquisition framework. In: Internet Imaging, San Jose, CA, USA, vol. 5305, pp. 307–318 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xiongcai Cai
    • 1
    • 3
  • Arcot Sowmya
    • 1
    • 2
    • 3
  1. 1.School of Computer Science and EngineeringThe University of New South WalesSydneyAustralia
  2. 2.Division of Engineering, Science and TechnologyUNSW AsiaSingapore
  3. 3.National ICT AustraliaAustralia

Personalised recommendations