An OpenCL-based feature matcher

Nowadays visual search is one of the most active branches of computer vision. It relies on finding invariant points inside images, describing them into features and then matching these features against a reference database to identify objects in the scene or the entire photo (environment). In this paper, we discuss an approach to feature matching that exploits the capabilities of modern GPUs to speed up the aforementioned and that keeps low the number of false matches.

► We describe an invariant features matcher based on GPU computing.
► The matcher employees a naive brute-force search strategy.
► We compare its performances against modern approximated matching techniques.
► An approximated features matcher on the GPU may lead to lower performances.
► Our matcher outperforms in quality and speed every CPU-based matcher to date.