Abstract | ||
---|---|---|
In our work we aim to explore a general framework that addresses the fundamental problem of universal unsupervised extraction of semantically meaningful visual regions. To this end this paper describes a novel region analysis technique using a self-organising map, the growing neural gas, which is adapted so as to improve modelling speed as well as to ensure a double-linkage chain around all region contours to simplify shape analysis. While the growing neural gas has been extensively applied to shape modelling, it has never explicitly been used for curvature analysis, contour description and region similarity. Once a contour network has been obtained, a transformation is applied that converts the closed contour to an open one, facilitating the use of certain angular descriptors. Discriminative descriptors derived from the properties of regions, their contours and their transformed contours are established and define a feature vector used for the representation of regions based on the appearance and contour information. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/IJCNN.2012.6252764 | IJCNN |
Keywords | Field | DocType |
double-linkage chain,feature vector,close contour transformation,self-organising map,region similarity,shape analysis,computational geometry,curvature analysis,region analysis,angular descriptor,feature extraction,contour information,universal unsupervised extraction,discriminative descriptor,self-organising feature maps,growing neural gas,vectors,contour description,shape,visualization | Computer science,Computational geometry,Artificial intelligence,Discriminative model,Computer vision,Feature vector,Pattern recognition,Feature extraction,Curvature analysis,Region analysis,Machine learning,Neural gas,Shape analysis (digital geometry) | Conference |
ISSN | ISBN | Citations |
2161-4393 E-ISBN : 978-1-4673-1489-3 | 978-1-4673-1489-3 | 3 |
PageRank | References | Authors |
0.39 | 11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gaurav Gupta | 1 | 14 | 7.06 |
Alexandra Psarrou | 2 | 199 | 27.14 |
Anastassia Angelopoulou | 3 | 102 | 21.29 |
José García Rodríguez | 4 | 192 | 29.10 |