Hybrid GNG Architecture Learns Features in Images

Authors:
José García-Rodríguez;Francisco Flórez-Revuelta;Juan Manuel García-Chamizo
Affiliations:
Department of Computer Technology, University of Alicante, Alicante, Spain 03080;Department of Computer Technology, University of Alicante, Alicante, Spain 03080;Department of Computer Technology, University of Alicante, Alicante, Spain 03080
Venue:
HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Year:
2008

Citing 6
Cited 0

Topology conserving mappings for learning motor tasks

AIP Conference Proceedings 151 on Neural Networks for Computing
Topology representing networks

Neural Networks
Self-Organizing Maps

Self-Organizing Maps
Hand Gesture Recognition Following the Dynamics of a Topology-Preserving Network

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Measuring GNG topology preservation in computer vision applications

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Theoretical analysis of multispectral image segmentation criteria

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Self-organising neural networks try to preserve the topology of an input space by using their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In this work we use a kind of self-organising network, the Growing Neural Gas, to represent objects as a result of an adaptive process by a topology-preserving graph that constitutes an induced Delaunay triangulation of their shapes. In this paper we present a new hybrid architecture that creates multiple specialized maps to represent different clusters obtained from the multilevel multispectral threshold segmentation.