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.
KeywordsInterest Point Image Patch View Angle Linear Path Interest Point Detector
- 3.Ke, Y., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image descriptors. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), vol. 2, pp. 506–513 (2004)Google Scholar
- 4.Winder, S., Hua, G., Brown, M.: Picking the best daisy. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp. 178–185 (2009)Google Scholar
- 12.Kaneva, B., Torralba, A., Freeman, W.T.: Evaluating image feaures using a photorealistic virtual world. In: IEEE International Conference on Computer Vision (2011)Google Scholar
- 14.Pedersen, K.S.: Statistics of natural image geometry. PhD thesis, University of Copenhagen, Department of Computer Science, Denmark (2003)Google Scholar
- 16.Dahl, A.L., Aanæs, H., Pedersen, K.S.: Finding the best feature detector-descriptor combination. In: The First Joint Conference of 3D Imaging, Modeling, Processing, Visualization and Transmission (2011)Google Scholar