TY  - CONF
AU  - Ekaterina Zaytseva
AU  - Santiago Segui
AU  - Jordi Vitria
A2  - CIARP
PY  - 2012//
TI  - Sketchable Histograms of Oriented Gradients for Object Detection
BT  - 17th Iberomerican Conference on Pattern Recognition
SP  - 374
EP  - 381
VL  - 7441
PB  - Springer Berlin Heidelberg
N2  - In this paper we investigate a new representation approach for visual object recognition. The new representation, called sketchable-HoG, extends the classical histogram of oriented gradients (HoG) feature by adding two different aspects: the stability of the majority orientation and the continuity of gradient orientations. In this way, the sketchable-HoG locally characterizes the complexity of an object model and introduces global structure information while still keeping simplicity, compactness and robustness. We evaluated the proposed image descriptor on publicly Catltech 101 dataset. The obtained results outperforms classical HoG descriptor as well as other reported descriptors in the literature.
SN  - 0302-9743
SN  - 978-3-642-33274-6
L1  - http://refbase.cvc.uab.es/files/ZSV2012.pdf
UR  - http://dx.doi.org/10.1007/978-3-642-33275-3_46
N1  - OR; MILAB;MV
ID  - Ekaterina Zaytseva2012
ER  -