English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/30163
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:


Shared random Ferns for efficient detection of multiple categories

AuthorsVillamizar, Michael ; Moreno-Noguer, Francesc ; Andrade-Cetto, Juan ; Sanfeliu, Alberto
KeywordsComputer vision
Object detection
Random ferns
Pattern recognition
Pattern recognition systems
Issue Date2010
Citation20th International Conference on Pattern Recognition: 388-391 (2010)
AbstractWe propose a new algorithm for detecting multiple object categories that exploits the fact that different categories may share common features but with different geometric distributions. This yields an efficient detector which, in contrast to existing approaches, considerably reduces the computation cost at runtime, where the feature computation step is traditionally the most expensive. More specifically, at the learning stage we compute common features by applying the same Random Ferns over the Histograms of Oriented Gradients on the training images. We then apply a boosting step to build discriminative weak classifiers, and learn the specific geometric distribution of the Random Ferns for each class. At runtime, only a few Random Ferns have to be densely computed over each input image, and their geometric distribution allows performing the detection. The proposed method has been validated in public datasets achieving competitive detection results, which are comparable with state-of-the-art methods that use specific features per class.
DescriptionTrabajo presentado al 20th ICPR celebrado en Estambul (Turquía) del 23 al 26 de agosto de 2010.
Publisher version (URL)http://dx.doi.org/10.1109/ICPR.2010.103
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
Shared random Ferns.pdf1,2 MBAdobe PDFThumbnail
Show full item record
Review this work

WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.