Generic Object Class Detection using Boosted Configurations of Oriented Edges
2010 (English)In: Computer Vision – ACCV 2010 / [ed] Kimmel, R; Klette, R; Sugimoto, A, Springer Berlin/Heidelberg, 2010, 1-14 p.Conference paper (Refereed)
In this paper we introduce a new representation for shape-based object class detection. This representation is based on very sparse and slightly flexible configurations of oriented edges. An ensemble of such configurations is learnt in a boosting framework. Each edge configuration can capture some local or global shape property of the target class and the representation is thus not limited to representing and detecting visual classes that have distinctive local structures. The representation is also able to handle significant intra-class variation. The representation allows for very efficient detection and can be learnt automatically from weakly labelled training images of the target class. The main drawback of the method is that, since its inductive bias is rather weak, it needs a comparatively large training set. We evaluate on a standard database  and when using a slightly extended training set, our method outperforms state of the art  on four out of five classes.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2010. 1-14 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 6493
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-38597DOI: 10.1007/978-3-642-19309-5_1ISI: 000295546500001ScopusID: 2-s2.0-79952494364ISBN: 978-364219308-8OAI: oai:DiVA.org:kth-38597DiVA: diva2:437459
10th Asian Conference on Computer Vision, ACCV 2010; Queenstown; 8 November 2010 through 12 November 2010
FunderICT - The Next Generation