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. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-87656-4_56 | HAIS |
Keywords | Field | DocType |
multilevel multispectral threshold segmentation,input space,neural network,induced delaunay triangulation,neural gas,competitive learning,multiple specialized map,adaptive process,hybrid gng architecture learns,new hybrid architecture,different cluster,delaunay triangulation,data clustering | Competitive learning,Architecture,Pattern recognition,Computer science,Segmentation,Multispectral image,Artificial intelligence,Artificial neural network,Cluster analysis,Machine learning,Neural gas,Delaunay triangulation | Conference |
Volume | ISSN | Citations |
5271 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
José García Rodríguez | 1 | 192 | 29.10 |
Francisco Flórez-revuelta | 2 | 481 | 34.95 |
Juan Manuel García-Chamizo | 3 | 72 | 8.98 |