Integrating representative and discriminant models for object category detection
2005 (English)In: Tenth IEEE International Conference on (Volume:2 ) Computer Vision, 2005. ICCV 2005, IEEE Computer Society, 2005, 1363-1370 p.Conference paper (Refereed)
Category detection is a lively area of research. While categorization algorithms tend to agree in using local descriptors, they differ in the choice of the classifier, with some using generative models and others discriminative approaches. This paper presents a method for object category detection which integrates a generative model with a discriminative classifier. For each object category, we generate an appearance codebook, which becomes a common vocabulary for the generative and discriminative methods. Given a query image, the generative part of the algorithm finds a set of hypotheses and estimates their support in location and scale. Then, the discriminative part verifies each hypothesis on the same codebook activations. The new algorithm exploits the strengths of both original methods, minimizing their weaknesses. Experiments on several databases show that our new approach performs better than its building blocks taken separately. Moreover, experiments on two challenging multi-scale databases show that our new algorithm outperforms previously reported results.
Place, publisher, year, edition, pages
IEEE Computer Society, 2005. 1363-1370 p.
, IEEE International Conference on Computer Vision. Proceedings, ISSN 1550-5499 ; II
Algorithms, Classification (of information), Codes (symbols), Database systems, Vocabulary control, Voice/data communication systems, Categorization algorithms, Codebook activations, Discriminative classifiers, Generative models, Object recognition
Other Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-156548DOI: 10.1109/ICCV.2005.124ISI: 000233155100179ScopusID: 2-s2.0-33745911319ISBN: 076952334XISBN: 978-076952334-7OAI: oai:DiVA.org:kth-156548DiVA: diva2:767599
Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, 17 October 2005 through 20 October 2005, Beijing, China
QC 201412022014-12-022014-12-012014-12-02Bibliographically approved