Sketchable Histograms of Oriented Gradients for Object Detection

In this paper we investigate a new representation approach for visual object recognition. The new representation, called sketchableHoG, 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 sketchableHoG 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.