Advances in Pattern Recognition — ICAPR 2001
Volume 2013 of the series Lecture Notes in Computer Science pp 111
Towards Bridging the Gap between Statistical and Structural Pattern Recognition: Two New Concepts in Graph Matching
 H. BunkeAffiliated withDept. of Computer Science, Univ. of Bern
 , S. GünterAffiliated withDept. of Computer Science, Univ. of Bern
 , X. JiangAffiliated withDept. of Computer Science, Univ. of Bern
Abstract
Two novel concepts in structural pattern recognition are discussed in this paper. The first, median of a set of graphs, can be used to characterize a set of graphs by just a single prototype. Such a characterization is needed in various tasks, for example, in clustering. The second novel concept is weighted mean of a pair of graphs. It can be used to synthesize a graph that has a specified degree of similarity, or distance, to each of a pair of given graphs. Such an operation is needed in many machine learning tasks. It is argued that with these new concepts various wellestablished techniques from statistical pattern recognition become applicable in the structural domain, particularly to graph representations. Concrete examples include kmeans clustering, vector quantization, and Kohonen maps.
Keywords
Graph matching errortolerant matching edit distance median graph weighted mean Title
 Towards Bridging the Gap between Statistical and Structural Pattern Recognition: Two New Concepts in Graph Matching
 Book Title
 Advances in Pattern Recognition — ICAPR 2001
 Book Subtitle
 Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings
 Pages
 pp 111
 Copyright
 2001
 DOI
 10.1007/3540447326_1
 Print ISBN
 9783540417675
 Online ISBN
 9783540447320
 Series Title
 Lecture Notes in Computer Science
 Series Volume
 2013
 Series ISSN
 03029743
 Publisher
 Springer Berlin Heidelberg
 Copyright Holder
 SpringerVerlag Berlin Heidelberg
 Additional Links
 Topics
 Keywords

 Graph matching
 errortolerant matching
 edit distance
 median graph
 weighted mean
 Industry Sectors
 eBook Packages
 Editors

 Sameer Singh ^{(4)}
 Nabeel Murshed ^{(5)}
 Walter Kropatsch ^{(6)}
 Editor Affiliations

 4. Department of Computer Science, University of Exeter
 5. Computational Intelligence Group, Tuiuti University of Parana
 6. Institute of Computer Aided Automation PRIPGroup 1832, Vienna University of Technology
 Authors
 Author Affiliations

 7. Dept. of Computer Science, Univ. of Bern, Switzerland
Continue reading...
To view the rest of this content please follow the download PDF link above.