Conference paper
Jet-Based Local Image Descriptors
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.
Language: | English |
---|---|
Publisher: | Springer |
Year: | 2012 |
Pages: | 638-650 |
Proceedings: | 12th European Conference on Computer Vision (ECCV 2012)European Conference on Computer Vision |
Series: | Lecture Notes in Computer Science |
Journal subtitle: | Workshops and Demonstrations, Part Iii |
ISBN: | 3642337112 , 3642337120 , 9783642337116 and 9783642337123 |
ISSN: | 03029743 |
Types: | Conference paper |
DOI: | 10.1007/978-3-642-33712-3_46 |
ORCIDs: | 0000-0001-6114-7100 , 0000-0003-3713-0960 and Dahl, Anders Lindbjerg |