Abstract
We propose a multiple-kernel local-patch descriptor based on efficient match kernels of patch gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch miss-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Even though handcrafted, the proposed method consistently outperforms the state-of-the-art methods on two local patch benchmarks.
Cite
CITATION STYLE
Mukundan, A., Tolias, G., & Chum, O. (2017). Multiple-kernel local-patch descriptor. In British Machine Vision Conference 2017, BMVC 2017. BMVA Press. https://doi.org/10.5244/c.31.184
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.