Abstract
We developed a novel method for image segmentation using deformable models. The deformable model adjustment is controlled by an Artificial Neural Network (ANN), which defines the deformations of the segmentation model through time. As deformable model we used Topological Active Nets, model which integrates features of region-based and boundary-based segmentation techniques. The evolved Artificial Neural Network learns to move each node of the segmentation model based on its energy surrounding. The ANN is applied to each of the nodes and in different temporal steps until the final segmentation is obtained. The ANN training is automatically obtained by simulated evolution, using differential evolution. This way, segmentation is an emergent process, result of the small deformations in the active model elements and through time. The new proposal was tested in different artificial and real images, showing the capabilities of the methodology.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tsumiyama, K., Yamamoto, K.: Active net: active net model for region extraction. IPSJ SIG Notes 89(96), 1–8 (1989)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(2), 321–323 (1988)
Ansia, F., Penedo, M., Mariño, C., Mosquera, A.: A new approach to active nets. Pattern Recog. Image Anal. 2, 76–77 (1999)
Williams, D.J., Shah, M.: A fast algorithm for active contours and curvature estimation. CVGIP: Image Underst. 55(1), 14–26 (1992)
Ibáñez, O., Barreira, N., Santos, J., Penedo, M.: Genetic approaches for topological active nets optimization. Pattern Recogn. 42, 907–917 (2009)
Buján, J.N., Santos, J., Penedo, M.G.: Optimization of topological active nets with differential evolution. In: Dobnikar, A., Lotrič, U., Šter, B. (eds.) ICANNGA 2011, Part I. LNCS, vol. 6593, pp. 350–360. Springer, Heidelberg (2011)
McInerney, T., Hamarneh, G., Shenton, M., Terzopoulos, D.: Deformable organisms for automatic medical image analysis. Med. Image Anal. 6, 251–266 (2002)
Price, K., Storn, R.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J. Glob. Optim. 11(4), 341–359 (1997)
Price, K., Storn, R., Lampinen, J.: Differential Evolution: A Practical Approach to Global Optimization. Natural Computing Series. Springer, Heidelberg (2005)
Feoktistov, V.: Differential Evolution: In Search of Solutions. Springer, New York (2006)
Novo, J., Penedo, M.G., Santos, J.: Localisation of the optic disc by means of GA-optimised topological active nets. Image Vis. Comput. 27, 1572–1584 (2009)
Acknowledgments
This paper has been partly funded by the Ministry of Science and Innovation through grant contracts TIN2011-25476 and TIN2011-27294 and by the Consellería de Industria, Xunta de Galicia through grant contract 10/CSA918054PR.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Novo, J., Sierra, C.V., Santos, J., Penedo, M.G. (2014). Emergent Image Segmentation by Means of Evolved Connectionist Models and Using a Topological Active Net Model. In: Filipe, J., Fred, A. (eds) Agents and Artificial Intelligence. ICAART 2013. Communications in Computer and Information Science, vol 449. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-44440-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-662-44440-5_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44439-9
Online ISBN: 978-3-662-44440-5
eBook Packages: Computer ScienceComputer Science (R0)