Abstract
The binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature. We propose an approach that can augment their performance by searching in the top K near neighbor matches instead of just the single nearest neighbor one. To pick the correct match out of the K near neighbors, we exploit statistics of descriptor variations collected for each keypoint in an off-line training phase. This is a similar approach to those that learn a patch specific keypoint representation. Unlike these approaches, we only use a keypoint specific score to rank the list of K near neighbors. Since this list can be efficiently computed with approximate nearest neighbor algorithms, our approach scales well to large descriptor sets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Note that for each descriptor type, we use different keypoint detector and descriptor settings (either the OpenCV defaults or the setup used by the authors). So, the figures in this paper should not be used for performance comparison between different descriptors.
References
Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: Fast retina keypoint. In: Conference on Computer Vision and Pattern Recognition, pp. 510–517 (2012)
Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. Commun. ACM 51(1), 117–122 (2008)
Balntas, V., Tang, L., Mikolajczyk, K.: Bold-binary online learned descriptor for efficient image matching. In: Conference on Computer Vision and Pattern Recognition (2015)
Bishop, C.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Calonder, M., Lepetit, V., Ozuysal, M., Trzcinski, T., Strecha, C., Fua, P.: BRIEF: computing a local binary descriptor very fast. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1281–1298 (2012)
Chum, O., Matas, J.: Matching with prosac—progressive sample consensus. In: Conference on Computer Vision and Pattern Recognition, pp. 220–226. San Diego, CA (2005)
Chum, O., Mikulik, A., Perdoch, M., Matas, J.: Total recall ii: Query expansion revisited. In: Conference on Computer Vision and Pattern Recognition, pp. 889–896 (2011)
Gupta, R., Mittal, A.: Smd: a locally stable monotonic change invariant feature descriptor. In: European Conference on Computer Vision, pp. 265–277 (2008)
Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1465–1479 (2006)
Leutenegger, S., Chli, M., Siegwart, R.Y.: Brisk: binary robust invariant scalable keypoints. In: International Conference on Computer Vision, pp. 2548–2555 (2011)
Levi, G., Hassner, T.: LATCH: learned arrangements of three patch codes. CoRR abs/1501.03719 (2015). http://www.openu.ac.il/home/hassner/projects/LATCH
Li, X., Larson, M., Hanjalic, A.: Pairwise geometric matching for large-scale object retrieval. In: Conference on Computer Vision and Pattern Recognition (2015)
Manning, C., Raghavan, P., Schütze, M.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2004)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. Int. J. Comput. Vision 65(1/2), 43–72 (2005)
Morel, J.M., Yu, G.: Asift: a new framework for fully affine invariant image comparison. SIAM J. Imaging Sci. 2(2), 438–469 (2009)
Muja, M., Lowe, D.G.: Scalable nearest neighbor algorithms for high dimensional data. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2227–2240 (2014)
Oszust, M.: An optimisation approach to the design of a fast, compact and distinctive binary descriptor. Signal Image Video Process. (2016). doi:10.1007/s11760-016-0907-4
Ozuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast keypoint recognition using random ferns. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 448–461 (2010)
Proença, H.: Performance evaluation of keypoint detection and matching techniques on grayscale data. SIViP 9(5), 1009–1019 (2015)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: an efficient alternative to sift or surf. In: International Conference on Computer Vision, pp. 2564–2571 (2011)
Trzcinski, T., Christoudias, M., Lepetit, V.: Learning image descriptors with boosting. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 597–610 (2015)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the TÜBİTAK project 113E496.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Uzyıldırım, F.E., Özuysal, M. Instance detection by keypoint matching beyond the nearest neighbor. SIViP 10, 1527–1534 (2016). https://doi.org/10.1007/s11760-016-0966-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-016-0966-6