Abstract
We present a general novel image descriptor based on higher- order differential geometry and investigate the effect of common descrip- tor 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 includ- ing 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.