TY  - CONF
AU  - Rahat Khan
AU  - Joost Van de Weijer
AU  - Fahad Shahbaz Khan
AU  - Damien Muselet
AU  - christophe Ducottet
AU  - Cecile Barat
A2  - CVPR
PY  - 2013//
TI  - Discriminative Color Descriptors
BT  - IEEE Conference on Computer Vision and Pattern Recognition
SP  - 2866
EP  - 2873
N2  - Color description is a challenging task because of large variations in RGB values which occur due to scene accidental events, such as shadows, shading, specularities, illuminant color changes, and changes in viewing geometry. Traditionally, this challenge has been addressed by capturing the variations in physics-based models, and deriving invariants for the undesired variations. The drawback of this approach is that sets of distinguishable colors in the original color space are mapped to the same value in the photometric invariant space. This results in a drop of discriminative power of the color description. In this paper we take an information theoretic approach to color description. We cluster color values together based on their discriminative power in a classification problem. The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data sets than the one at hand, can obtain competing performance. Experiments show that the proposed descriptor outperforms existing photometric invariants. Furthermore, we show that combined with shape description these color descriptors obtain excellent results on four challenging datasets, namely, PASCAL VOC 2007, Flowers-102, Stanford dogs-120 and Birds-200.
SN  - 1063-6919
L1  - http://refbase.cvc.uab.es/files/KWK2013a.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2013.369
N1  - CIC; 600.048
ID  - Rahat Khan2013
ER  -