Skip to main content
SpringerLink
Log in

An Active Contour Algorithm for Continuous-Time Cellular Neural Networks

  • Published:
Journal of VLSI signal processing systems for signal, image and video technology Aims and scope Submit manuscript

Abstract

A CNN-based algorithm for image segmentation by active contours is proposed here. The algorithm is based on an iterative process of expansion of the contour and its subsequent thinning guided by external and internal energy. The proposed strategy allows for a high level of control over contour evolution making their topologic transformations easier. Therefore processing of multiple contours for segmenting several objects can be carried out simultaneously.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contours models,” Int. J. Computer Vision, Vol. 1, pp. 321–331, 1998.

    Article  Google Scholar 

  2. L.D. Cohen and I. Cohen, “Finite element methods for active contour models and ballons for 2d and 3d images,” IEEE Trans. Patt. Anal. Machine Intell., Vol. 15, pp. 1131–1147, 1993.

    Article  Google Scholar 

  3. P. Radeva and J. Serrat, “Rubber snake: Implementation on signed distance potential,” in Vision Conference SWISS'93, pp. 187–194, 1993.

  4. T. Roska and L.O. Chua, “CNN universal machine: An analogic array computer,” IEEE Trans. Circuits Syst.,Vol. 3, pp. 163–173, 1993.

    Article  Google Scholar 

  5. Cs. Rekeczky, T. Roska, and L.O. Chua, Computing with front propagation: Active contour and skeleton models in continuoustime CNN. Technical report DNS-9-1998, MTA-SZTAKI, 1998.

  6. Cs. Rekeczky, “Dynamic spatio-temporal nonlinear filtering and detection on CNN architecture: Theory, modeling, and applications,” Ph.D. Dissertation, MTA-SZTAKI, 1998.

  7. Cs. Rekeczky, A. Tahy, Z. Vigh, and T. Roska, “Spatiotemporal nonlinear filtering and endocardial boundary detection in echocardiography,” International Journal of Circuit Theory and Applications, Vol. 27, pp. 171–207, 1999.

    Article  Google Scholar 

  8. D.L. Vilariño, D. Cabello, V.M. Brea, and J.M. Pardo, “Discretetime CNN for image segmentation by active contours,” Pattern Recognition Letters, Vol. 19, No. 8, pp. 721–734, 1998.

    Article  MATH  Google Scholar 

  9. D.L. Vilariño, D. Cabello, M. Balsi, and V.M. Brea, “Image segmentation based on active contours using discrete-time cellular neural networks,” in Fifth IEEE InternationalWorkshop on Cellular Neural Networks and Their Applications, V. Tavsanoglu (Ed.), pp. 331–336, 1998.

  10. H. Harrer, “Multilayer discrete-time cellular neural networks using time-variable templates,” IEEE Trans. Circuits Syst., Vol. 40, No. 3, pp. 191–199, 1993.

    Article  MATH  Google Scholar 

  11. H. Harrer and J.A. Nossek, “Discrete-time cellular neural networks,” Int. Journal Circ. Th. Appl., Vol. 20, pp. 453–467, 1992.

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electronics Research Laboratory, Department of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CA, 94720, USA

    T. Kozek & D. L. Vilariño

Authors
  1. T. Kozek
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. L. Vilariño
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kozek, T., Vilariño, D.L. An Active Contour Algorithm for Continuous-Time Cellular Neural Networks. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 23, 403–414 (1999). https://doi.org/10.1023/A:1008105404510

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1008105404510

Keywords

Search

Navigation