Sciweavers

Share
PRL
2007

Boosted Landmarks of Contextual Descriptors and Forest-ECOC: A novel framework to detect and classify objects in cluttered scene

8 years 8 months ago
Boosted Landmarks of Contextual Descriptors and Forest-ECOC: A novel framework to detect and classify objects in cluttered scene
In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-class object recognition. To detect a sample of the object class, Boosted Landmarks identify landmark candidates in the image and define a constellation of contextual descriptors able to capture the spatial relationship among them. To classify the object, we consider the problem of multi-class classification with a battery of classifiers trained to share their knowledge among classes. For this purpose, we extend the Error Correcting Output Codes technique proposing a methodology based on embedding a forest of optimal tree structures. We validated our approach using public data-sets from the UCI and Caltech databases. Furthermore, we show results of the technique applied to a real computer vision problem: detection and categorization of traffic signs. Ó 2007 Elsevier B.V. All rights reserved.
Sergio Escalera, Oriol Pujol, Petia Radeva
Added 27 Dec 2010
Updated 27 Dec 2010
Type Journal
Year 2007
Where PRL
Authors Sergio Escalera, Oriol Pujol, Petia Radeva
Comments (0)
books