Automatic Learning and Extraction of Multi-Local Features
2009 (English)In: Proceedings of the IEEE International Conference on Computer Vision, 2009, 917-924 p.Conference paper (Refereed)
In this paper we introduce a new kind of feature - the multi-local feature, so named as each one is a collection of local features, such as oriented edgels, in a very specific spatial arrangement. A multi-local feature has the ability to capture underlying constant shape properties of exemplars from an object class. Thus it is particularly suited to representing and detecting visual classes that lack distinctive local structures and are mainly defined by their global shape. We present algorithms to automatically learn an ensemble of these features to represent an object class from weakly labelled training images of that class, as well as procedures to detect these features efficiently in novel images. The power of multi-local features is demonstrated by using the ensemble in a simple voting scheme to perform object category detection on a standard database. Despite its simplicity, this scheme yields detection rates matching state-of-the-art object detection systems.
Place, publisher, year, edition, pages
2009. 917-924 p.
, IEEE International Conference on Computer Vision, ISSN 1550-5499
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-38598DOI: 10.1109/ICCV.2009.5459338ISI: 000294955300118ScopusID: 2-s2.0-77953207220ISBN: 978-142444420-5ISBN: 978-1-4244-4419-9OAI: oai:DiVA.org:kth-38598DiVA: diva2:437461
12th International Conference on Computer Vision, ICCV 2009; Kyoto; 29 September 2009 through 2 October 2009
QC 201209172011-08-292011-08-292012-09-17Bibliographically approved