NF-Features – No-Feature-Features for Representing Non-textured Regions
In order to achieve a complete image description, we introduce no-feature-features (NF-features) representing object regions where regular interest point detectors do not detect features. As these regions are usually non-textured, stable re-localization in different images with conventional methods is not possible. Therefore, a technique is presented which re-localizes once-detected NF-features using correspondences of regular features. Furthermore, a distinctive NF descriptor for non-textured regions is derived which has invariance towards affine transformations and changes in illumination. For the matching of NF descriptors, an approach is introduced that is based on local image statistics.
NF-features can be used complementary to all kinds of regular feature detection and description approaches that focus on textured regions, i.e. points, blobs or contours. Using SIFT, MSER, Hessian-Affine or SURF as regular detectors, we demonstrate that our approach is not only suitable for the description of non-textured areas but that precision and recall of the NF-features is significantly superior to those of regular features. In experiments with high variation of the perspective or image perturbation, at unchanged precision we achieve NF recall rates which are better by more than a factor of two compared to recall rates of regular features.
KeywordsImage Noise Interest Point Regular Feature Interest Point Detector Maximally Stable Extremal Region
Unable to display preview. Download preview PDF.
- 1.NF Project Website, http://www.tnt.uni-hannover.de/project/nf
- 2.Harris, C., Stephen, M.: A combined corner and edge detector. In: Fourth Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
- 4.Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable external regions. Image and Vision Computing (2004)Google Scholar
- 5.Mikolajcyk, K., Schmid, C.: An affine invariant interest point detector. In: ICCV (2002)Google Scholar
- 8.Förstner, W., Dickscheid, T., Schindler, F.: Detecting interpretable and accurate scale-invariant keypoints. In: ICCV, pp. 2256–2263 (2009)Google Scholar
- 10.Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. TPAMI 30(1), 36–51 (2008)Google Scholar
- 11.Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. TPAMI 27(10), 1615–1630 (2005)Google Scholar
- 15.Eldar, Y., Lindenbaum, M., Porat, M., Zeevi, Y.Y.: The farthest point strategy for progressive image sampling. TIP 6(9), 1305–1315 (1997)Google Scholar
- 16.Hartley, R.I.: In defense of the eight-point algorithm. TPAMI 19, 580–593 (1997)Google Scholar
- 17.Debevec, P.E., Malik, J.: Recovering high dynamic range radiance maps from photographs. In: SIGGRAPH, pp. 369–378 (1997)Google Scholar