A Local Neighborhood Constraint Method for SIFT Features Matching

Conference paper
Part of the Springer Proceedings in Business and Economics book series (SPBE)

Abstract

For improving the accuracy of the SIFT matching algorithm with low time cost, this paper proposes a novel matching algorithm which is based on local neighborhood constraints, that is, SIFT matching feature is optimized by the local neighborhood constraint method in the SIFT algorithm. We optimize the matching results by using the information of SIFT feature descriptor and the relative position information of SIFT feature, then the final matching result obtained by RANSANC algorithm to filter the false matched pairs. The experimental results show that our method can improve the accuracy of the matching feature pairs without affecting the time cost.

Keywords

Image matching SIFT algorithm Local neighborhood constraints 

Notes

Acknowledgements

This work was supported by the Science & Technology Development Program of Jilin Province, China (Nos. 20140101182JC, 20150101060JC, 20150307030GX, 2015Y059 and 20160204048GX), and by the International Science and Technology Cooperation Program of China (Nos. 20140101182JC, 20150101060JC, 20150307030GX and 20160204048GX).

References

  1. 1.
    Vourvoulakis, J., Kalomiros, J., & Lygouras, J. (2016). FPGA accelerator for real-time SIFT matching with RANSAC support. Microprocessors and Microsystems, 49, 105–116.CrossRefGoogle Scholar
  2. 2.
    Chen, Y., & Shang, L. (2016). Improved SIFT image registration algorithm on characteristic statistical distributions and consistency constraint. Optik - International Journal for Light and Electron Optics, 127(2), 900–911.CrossRefGoogle Scholar
  3. 3.
    Jin, R., & Kim, J. (2015). Tracking feature extraction techniques with improved SIFT for video identification. Multimedia Tools & Applications, 76, 1–10.Google Scholar
  4. 4.
    Wei, W., Hong, J., & Tang, Y. (2008). Image matching for geomorphic measurement based on SIFT and RANSAC methods. International Conference on Computer Science and Software Engineering. IEEE Computer Society (pp.317–320).Google Scholar
  5. 5.
    Qian, S., & Zhu, J. (2007). Improved SIFT-based bidirectional image matching algorithm. Mechanical Science & Technology for Aerospace Engineering, 26(9), 1179–1182.Google Scholar
  6. 6.
    Huo, C. L., Zhou, Z. X., Liu, Q. S., et al. (2007). Remote sensing image registration based on SIFT and the distance between generalized tight pair-wise prototypes. Remote Sensing Technology & Application, 22(4), 524–530.Google Scholar
  7. 7.
    Zhang, R. (2008). Study on Color Image Registration Technique based on CSIFT. Acta Optica Sinica, 28(11), 2097–2103.CrossRefGoogle Scholar
  8. 8.
    Jiang, Y., & Wang, J. (2010). Research on multi-source remote sensing image registration base on SIFT algorithm of window segmentation. International Conference on Wireless Communications Networking and Mobile Computing. IEEE (pp. 1–4).Google Scholar
  9. 9.
    Yi, Z., Zhiguo, C., & Yang, X. (2008). Multi-spectral remote image registration based on SIFT. Electronics Letters, 44(2), 107–108.CrossRefGoogle Scholar
  10. 10.
    Lowe, D. G. (2004). Distinctive image features form scale-invariant key-points. International Journal of Computer Vision, 60(2), 91–110.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Qingliang Li
    • 1
  • Lili Xu
    • 1
  • Pengliang Zheng
    • 1
  • Fei He
    • 1
  1. 1.Changchun University of Science and Technology, School of Computer Science and TechnologyChangchunChina

Personalised recommendations