Jet-Based Local Image Descriptors

Anders Boesen Lindbo Larsen¹, Sune Darkner¹, Anders Lindbjerg Dahl², and Kim Steenstrup Pedersen¹

¹Department of Computer Science, University of Copenhagen, Denmark
abll@diku.dk
darkner@diku.dk
kimstp@diku.dk

²Department of Informatics and Mathematical Modelling, Technical University of Denmark, Denmark
abd@imm.dtu.dk

Abstract. 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.

LNCS 7574, p. 638 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012