Graphics Reference
In-Depth Information
Table 1.
Computing time of SIFT, FREAK and CS_FREAK
SIFT
FREAK
CS-FREAK
Points in first image
6003
6003
6003
Points in second image
7459
7459
7459
Description time [s]
13.029
0.422
0.383
Matching time [s]
5.90881
2.5402
2.7422
3
Conclusions
This paper proposed a novel two-step matching strategy and Center Symmetry
FREAK (CS-FREAK) for feature description and matching. Compared with the pre-
vious proposed FREAK descriptor, CS-FREAK is quite different in the utilization of
the neighborhood intensity information, encoding scheme, comparison rule and
matching strategy. More specifically, it simplifies the 8-layer retina modal and more
fully explores the local intensity relationships by considering the intensity order
among the points in 4 directions around the sample points. Experimental results on
various image transformations have shown that the proposed two-step matching strat-
egy and CS-FREAK outperforms the state-of-the-art methods.
Acknowledgments.
This work is supported by the National Science Foundation of China
(61203189)
and
General
Armament
Department
Pre-research
Foundation
(9140A01060411JB47-01).
References
1.
Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: Fast retina keypoint. In: Computer Vision
and Pattern Recognition (CVPR), pp. 510-517. IEEE Press, New York (2012)
2.
Lin, D., Xiliang, N., Tao, J., Shunshi, H.: Automatic registration of CCD images and IR
images based on invariant feature. In: Infrared and Laser Engineering, vol. 40,
pp. 350-354 (2011)
3.
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. In: International
Journal of Computer Vision, vol. 60, pp. 91-110. Kluwer Academic Publishers (2004)
4.
Xingmiao, L., Shicheng, W., Jing, Z.: Infrared image moving object detection based on
image block reconstruction. In: Infrared and Laser Engineering, vol. 1, pp. 176-180 (2011)
5.
Liu, J., Zhang, T.: Recognition of the blurred image by complex moment invariants. In:
Pattern Recognition Letters, vol. 26, pp. 1128-1138 (2005)
6.
Ke, Y., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image de-
scriptors. In: Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 506-513.
IEEE Press, Washington, DC (2004)
7.
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans-
actions on Pattern Analysis and Machine Intelligence 27, 1615-1630 (2005)
8.
Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: Leonardis, A.,
Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404-417. Springer,
Heidelberg (2006)
Search WWH ::
Custom Search