An Active Contour Algorithm for Continuous-Time Cellular Neural Networks

Authors:
T. Kozek;D. L. Vilariño
Affiliations:
Electronics Research Laboratory, Department of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CA 94720, USA;Electronics Research Laboratory, Department of Electrical Engineering and Computer Science, University of California at Berkeley, Berkeley, CA 94720, USA
Venue:
Journal of VLSI Signal Processing Systems - Special issue on spatiotemporal signal processing with analog CNN visual microprocessors
Year:
1999

Citing 2
Cited 0

Discrete-time CNN for image segmentation by active contours

Pattern Recognition Letters
Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A CNN-based algorithm for image segmentation by activecontours is proposed here. The algorithm is based on an iterativeprocess of expansion of the contour and its subsequent thinningguided by external and internal energy. The proposed strategy allowsfor a high level of control over contour evolution making theirtopologic transformations easier. Therefore processing of multiplecontours for segmenting several objects can be carried outsimultaneously.