We present a general novel image descriptor based on higherorder differential geometry and investigate the effect of common descriptor choices. Our investigation is twofold in that we develop a jet-based descriptor and perform a comparative evaluation with current state-of-the-art descriptors on the recently released DTU Robot dataset. We demonstrate how the use of higher-order image structures enables us to reduce the descriptor dimensionality while still achieving very good performance. The descriptors are tested in a variety of scenarios including large changes in scale, viewing angle and lighting. We show that the proposed jet-based descriptor is superior to state-of-the-art for DoG interest points and show competitive performance for the other tested interest points.
|Title of host publication||Computer Vision – ECCV 2012 : Workshops and Demonstrations, Part III|
|Publication status||Published - 2012|
|Event||12th European Conference on Computer Vision (ECCV 2012) - Florence, Italy|
Duration: 7 Oct 2012 → 13 Oct 2012
|Conference||12th European Conference on Computer Vision (ECCV 2012)|
|Period||07/10/2012 → 13/10/2012|
|Series||Lecture Notes in Computer Science|