Research on Wrong Match Pairs Elimination of SIFT Algorithm

Abstract:

The image matching is key technology of image processing applied to many fields. Image matching based on invariant features was the hot spot in image matching research recently. SIFT is one of the most effective scale, rotation and illumination invariant features. However there are a lot of wrong match pairs produced by original SIFT algorithm. Two specific types of wrong matches are analyzed and corresponding eliminating methods are given. Aiming at general wrong matches eliminating, a method based on similar triangles is proposed. Experiments are carried out, and the results confirm that: compared with the art of state, the proposed method is faster; it can eliminate wrong matches cleanly and preserve correct matches as well.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 963-968
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.963
• Online since: July 2013
• Authors: Dong Xing Zhang, Ming Bo Zhu, Xiang Ping Li
• Keywords: Elimination, Similar Triangles, Wrong Match Pairs

References

[1] Tang Yong-he, Research on image matching based on feature points [D], library of national university of defense technology, 2007, 2-3.

[2] J.P. Lewis, Fast Template Matching, Vision Interface, P. 1995, 120—123.

[3] M.P. Dubuisson and A.K. Jain．A modified Hausdorff distance for object matching，in Proc．12th Int．Conf．Pattern Recognition, Jerusalem, Israel，Oct. 1994, PP．566-568.

[4] Lowe D G. Object recognition from local scale-invariant features [J]. International Conference on Computer Vision, 1999: 1150-1157.

DOI: 10.1109/iccv.1999.790410

[5] D. G. Lowe, Distinctive Image Features from Scale-Invariant Key points. International Journal of Computer Vision, vol. 60(2), p.91–110. January (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

[6] A. Kuffner and A. Robles-Kelly. Image Feature Evaluation for Contents-based Image Retrieval. HCSNet Workshop on the Use of Vision in HCI(VisHCI), Canberra, Australia, (2006).

[7] C. Liu, C. Huang, W. Chu, J. Wu. ITEMS, intelligent travel experience management system. Proceeding of the international workshop on Workshop on multimedia information retrieval. Pages: 291-298, (2007).

DOI: 10.1145/1290082.1290122

[8] L. Kennedy,M. Naaman. Generating diverse and representative image search results for landmarks. Proceeding of the 17th international conference on World Wide Web, pages: 296-306, (2008).

DOI: 10.1145/1367497.1367539

[9] Y. Gao,J. Fan. Automatic function selection for large scale salient object detection. Proceedings of the 14th annual ACM international conference on Multimedia. Pages: 97-100, (2006).

DOI: 10.1145/1180639.1180669

[10] G. Zhao, L. Chen, J. Song, G. Chen. Large had movement tracking using SIFT-based registration. Proceedings of the 15th international conference on Multimedia. Pages: 807-810, (2007).

DOI: 10.1145/1291233.1291416

[11] M. Fischler, R. Bolles, Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Graphics and Image Processing, vol. 24(6), p.381–395, June, (1981).

DOI: 10.1145/358669.358692

[12] Z. Wei and J. Kosecka, Generalized RANSAC Framework for Relaxed Correspondence Problems, " in 3D Data Processing, Visualization, and Transmission, Third International Symposium on, Chapel Hill, NC, 2006, pp.854-860.M. Young, The Technical Writer, s Handbook. Mill Valley, CA: University Science, (1989).

DOI: 10.1109/3dpvt.2006.67

[13] Zhang Jieyu, et al, A Method of Correcting SIFT Mismatching Based on Spatital Distribution Descriptor, Journal of Image and Graphics, vol 14(7), p.1369–1377 July (2009).

[14] Wang Yigang et al, Study on medical micro-image mosaic with SIFT features, International Conference on Nanotechnology and Computer Engineering, July, (2010).

[15] Ren Jiayuan, Wang Yigang, Deng Yun. Study on Eliminating Wrong Match Pairs of SIFT[J]. IEEE Trans．on Image Processing，2010，11(11)：992～995.

DOI: 10.1109/icosp.2010.5655847

[16] Qian Sen, Zhu Jianying. Improved SIFT-based Bidirectional Image Matching Algorithm[J]. Mechanical Science and Technology for Aerospace Engineering, 2007, 26(9): 1179-1182.