Object categorization with SVM: kernels for local features

In this paper, we propose to combine an efficient image representation based on local descriptors with a Support Vector Machine classifier in order to perform object categorization. For this purpose, we apply kernels defined on sets of vectors. After testing different combinations of kernel / local descriptors, we have been able to identify a very performant one.

[1]  A. Bhattacharyya.  On a measure of divergence between two statistical populations defined by their probability distributions , 1943 .

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Katya Scheinberg,et al.  Efficient SVM Training Using Low-Rank Kernel Representations , 2002, J. Mach. Learn. Res..

[5]  Tony Jebara,et al.  A Kernel Between Sets of Vectors , 2003, ICML.

[6]  Bernt Schiele,et al.  Analyzing contour and appearance based methods for object categorization , 2003, CVPR 2003.

[7]  Lior Wolf,et al.  Learning over Sets using Kernel Principal Angles , 2003, J. Mach. Learn. Res..

[8]  Barbara Caputo,et al.  Recognition with local features: the kernel recipe , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[10]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.