Incremental computation of feature hierarchies
2010 (English)In: Pattern Recognition: 32nd DAGM Symposium, Darmstadt, Germany, September 22-24, 2010. Proceedings / [ed] Michael Goesele, Stefan Roth, Arjan Kuijper, Bernt Schiele and Konrad Schindler, Springer Berlin/Heidelberg, 2010, 523-532 p.Conference paper (Refereed)
Feature hierarchies are essential to many visual object recognition systems and are well motivated by observations in biological systems. The present paper proposes an algorithm to incrementally compute feature hierarchies. The features are represented as estimated densities, using a variant of local soft histograms. The kernel functions used for this estimation in conjunction with their unitary extension establish a tight frame and results from framelet theory apply. Traversing the feature hierarchy requires resampling of the spatial and the feature bins. For the resampling, we derive a multi-resolution scheme for quadratic spline kernels and we derive an optimization algorithm for the upsampling. We complement the theoretic results by some illustrative experiments, consideration of convergence rate and computational efficiency.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2010. 523-532 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 6376
IdentifiersURN: urn:nbn:se:liu:diva-60596DOI: 10.1007/978-3-642-15986-2_53ISI: 000288936400053ISBN: 978-3-642-15985-5 (Print)ISBN: 978-3-642-15986-2 (Online)OAI: oai:DiVA.org:liu-60596DiVA: diva2:358047
32nd DAGM Symposium, Darmstadt, Germany, September 22-24, 2010