Sciweavers

Share
CVPR
2009
IEEE

Learning Photometric Invariance From Diversified Color Model Ensembles

8 years 3 months ago
Learning Photometric Invariance From Diversified Color Model Ensembles
Color is a powerful visual cue for many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the imaging conditions affecting negatively the performance of the task at hand. Often, a reflection model (\eg, Lambertian or dichromatic reflectance) is used to derive color invariant models. However, those reflection models might be too restricted to model real--world scenes in which different reflectance mechanisms may hold simultaneously. Therefore, in this paper, we aim to derive color invariance by learning from color models to obtain diversified color invariant ensembles. First, a photometrical orthogonal and non--redundant color model set is taken on input composed of both color variants and invariants. Then, the proposed method combines and weights these color models to arrive at a diversified color ensemble yielding a proper balance between invariance (repeatability) and discriminative p...
Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
Related Content
Added 06 Aug 2009
Updated 14 Aug 2010
Type Conference
Year 2009
Where CVPR
Authors Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
Extension of this paper has been accepted in International Journal of Computer Vision in April 2010

Learning Photometric Invariance for Object Detection
Comments (0)
books