Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/37813
Title: Structural image classification with graph neural networks
Authors: Quek, A
Wang, Z
Zhang, J
Feng, D
Keywords: Delaunay triangulation
Image classification
Graph neural networks
Minimum spanning tree
Region adjacency graph
Structural representation
Issue Date: 2011
Source: Proceedings of the International Conference on Digital Image Computing Techniques and Applications (DICTA'2011), Noosa, Queensland, Australia, 6-8 Dec. 2011, p. 416-421 How to cite?
Abstract: Many approaches to image classification tend to transform an image into an unstructured set of numeric feature vectors obtained globally and/or locally, and as a result lose important relational information between regions. In order to encode the geometric relationships between image regions, we propose a variety of structural image representations that are not specialised for any particular image category. Besides the traditional grid-partitioning and global segmentation methods, we investigate the use of local scale-invariant region detectors. Regions are connected based not only upon nearest-neighbour heuristics, but also upon minimum spanning trees and Delaunay triangulation. In order to maintain the topological and spatial relationships between regions, and also to effectively process undirected connections represented as graphs, we utilise the recently-proposed graph neural network model. To the best of our knowledge, this is the first utilisation of the model to process graph structures based on local-sampling techniques, for the task of image classification. Our experimental results demonstrate great potential for further work in this domain.
URI: http://hdl.handle.net/10397/37813
ISBN: 978-1-4577-2006-2
DOI: 10.1109/DICTA.2011.77
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

4
Citations as of Feb 26, 2017

Page view(s)

8
Last Week
0
Last month
Checked on Mar 26, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.