Publication
A recursive embedding approach to median graph computation
Conference Article
Conference
IAPR Workshop on Graph-based Representations in Pattern Recognition (GbRPR)
Edition
7th
Pages
113-123
Doc link
http://dx.doi.org/10.1007/978-3-642-02124-4_12
File
Abstract
The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely complex. Several approaches have been presented up to now based on different strategies. In this paper We present a new approximate recursive algorithm for median graph computation based on graph embedding into vector spaces. Preliminary experiments oil three databases show that this new approach is able to obtain better medians than the previous existing approaches.
Categories
pattern recognition.
Scientific reference
M. Ferrer, D. Karatzas, E. Valveny and H. Bunke. A recursive embedding approach to median graph computation, 7th IAPR Workshop on Graph-based Representations in Pattern Recognition, 2009, Venice, in Graph-Based Representations in Pattern Recognition, Vol 5534 of Lecture Notes in Computer Science, pp. 113-123, 2009, Springer Verlag.
Follow us!