Emergent Segmentation of Topological Active Nets by Means of Evolutionary Obtained Artificial Neural Networks

Cristina V. Sierra, Jorge Novo, José Santos, Manuel G. Penedo

2013

Abstract

We developed a novel segmentation method using deformable models. As deformable model we used Topological Active Nets, model which integrates features of region-based and boundary-based segmentation techniques. The deformation through time is defined by an Artificial Neural Network (ANN) that 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 obtained by simulated evolution, using differential evolution to automatically obtain the ANN that provides the emergent segmentation. The new proposal was tested in different artificial and real images, showing the capabilities of the methodology.

Download


Paper Citation


in Harvard Style

V. Sierra C., Novo J., Santos J. and G. Penedo M. (2013). Emergent Segmentation of Topological Active Nets by Means of Evolutionary Obtained Artificial Neural Networks . In Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-8565-39-6, pages 44-50. DOI: 10.5220/0004195700440050

in Bibtex Style

@conference{icaart13,
author={Cristina V. Sierra and Jorge Novo and José Santos and Manuel G. Penedo},
title={Emergent Segmentation of Topological Active Nets by Means of Evolutionary Obtained Artificial Neural Networks},
booktitle={Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2013},
pages={44-50},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004195700440050},
isbn={978-989-8565-39-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Emergent Segmentation of Topological Active Nets by Means of Evolutionary Obtained Artificial Neural Networks
SN - 978-989-8565-39-6
AU - V. Sierra C.
AU - Novo J.
AU - Santos J.
AU - G. Penedo M.
PY - 2013
SP - 44
EP - 50
DO - 10.5220/0004195700440050