Tasting families of features for image classification

Authors:
Charles Dubout;Francois Fleuret
Affiliations:
Idiap Research Institute, Switzerland;Idiap Research Institute, Switzerland
Venue:
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Year:
2011

Citing 0
Cited 1

Per-patch descriptor selection using surface and scene properties

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using multiple families of image features is a very efficient strategy to improve performance in object detection or recognition. However, such a strategy induces multiple challenges for machine learning methods, both from a computational and a statistical perspective.