Many-to-many feature matching using spherical coding of directed graphs
2004 (English)In: COMPUTER VISION - ECCV 2004, PT 1 / [ed] Pajdla, T; Matas, J, 2004, Vol. 3021, 322-335 p.Conference paper (Refereed)
In recent work, we presented a framework for many-to-many matching of multi-scale feature hierarchies, in which features and their relations were captured in a vertex-labeled, edge-weighted directed graph. The algorithm was based on a metric-tree representation of labeled graphs and their metric embedding into normed vector spaces, using the embedding algorithm of Matousek . However, the method was limited by the fact that two graphs to be matched were typically embedded into vector spaces with different dimensionality. Before the embeddings could be matched, a dimensionality reduction technique (PCA) was required, which was both costly and prone to error. In this paper, we introduce a more efficient embedding procedure based on a spherical coding of directed graphs. The advantage of this novel embedding technique is that it prescribes a single vector space into which both graphs are embedded. This reduces the problem of directed graph matching to the problem of geometric point matching, for which efficient many-to-many matching algorithms exist, such as the Earth Mover's Distance. We apply the approach to the problem of multi-scale, view-based object recognition, in which an image is decomposed into a set of blobs and ridges with automatic scale selection.
Place, publisher, year, edition, pages
2004. Vol. 3021, 322-335 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 3021
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-44672ISI: 000221568400025ScopusID: 2-s2.0-84944053990ISBN: 3-540-21984-6OAI: oai:DiVA.org:kth-44672DiVA: diva2:452103
8th European Conference on Computer Vision Location: Prague, CZECH REPUBLIC Date: MAY 11-14, 2004
QC 201110282011-10-282011-10-252011-10-28Bibliographically approved