Real-time pose invariant logo and pattern detection

Oliver Sidla, Michal Kottman, Vanda Benesova

Abstract. In this work we have tested several keypoint/feature descriptor combinations for logo detection in order to estimate the robustness of different algorithms with respect to logo type and image quality. Our tests have shown that the well established SURF/SURF combination seems to perform best, followed by Calonder’s keypoint detector/Random Fern combination. The authors still believe that the LDETECTOR/Fern combination, especially when using the compressed signature framework is used (which has not yet been implemented for this test) bears a large potential. Its speed advantage and ability for fast online learning should make it an interesting alternative to SURF/SURF.