OSA's Digital Library

Chinese Optics Letters

Chinese Optics Letters

| PUBLISHED MONTHLY BY CHINESE LASER PRESS AND DISTRIBUTED BY OSA

  • Vol. 9, Iss. 8 — Aug. 10, 2011
  • pp: 081002–081002

Novel averaging window filter for SIFT in infrared face recognition

Junfeng Bai, Yong Ma, Jing Li, Fan Fan, and Hongyuan Wang  »View Author Affiliations


Chinese Optics Letters, Vol. 9, Issue 8, pp. 081002-081002 (2011)


View Full Text Article

Acrobat PDF (563 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations
  • Export Citation/Save Click for help

Abstract

The extraction of stable local features directly affects the performance of infrared face recognition algorithms. Recent studies on the application of scale invariant feature transform (SIFT) to infrared face recognition show that star-styled window filter (SWF) can filter out errors incorrectly introduced by SIFT. The current letter proposes an improved filter pattern called Y-styled window filter (YWF) to further eliminate the wrong matches. Compared with SWF, YWF patterns are sparser and do not maintain rotation invariance; thus, they are more suitable to infrared face recognition. Our experimental results demonstrate that a YWF-based averaging window outperforms an SWF-based one in reducing wrong matches, therefore improving the reliability of infrared face recognition systems.

© 2011 Chinese Optics Letters

OCIS Codes
(100.2000) Image processing : Digital image processing
(100.2960) Image processing : Image analysis
(100.3008) Image processing : Image recognition, algorithms and filters

Citation
Junfeng Bai, Yong Ma, Jing Li, Fan Fan, and Hongyuan Wang, "Novel averaging window filter for SIFT in infrared face recognition," Chin. Opt. Lett. 9, 081002-081002 (2011)
http://www.opticsinfobase.org/col/abstract.cfm?URI=col-9-8-081002


Sort:  Author  |  Year  |  Journal  |  Reset

References

  1. S. G. Kong, J. Heo, B. R. Abidi, J. Paik, and M. A. Abidi, Comput. Vis. Image Und. 97, 103 (2005).
  2. D. Socolinsky, L. Wolff, J. Neuheisel, and C. Eveland, in Proceeding of IEEE Workshop Computer Vision and Pattern Recognition 1, I-527 (2001).
  3. A. Selinger, Appearance-Based Facial Recognition Using Visible and Thermal Imagery: a Comparative Study (Equinox Corp, New York, 2006).
  4. F. Prokoski, in Proceeding of IEEE Workshop Computer Vision Beyond Visible Spectrum: Methods and Applications 3, 1688 (2000).
  5. K. Mikolajczyk and C. Schmid, in Proceedings of Computer Vision and Pattern Recognition 2, II-257 (2003).
  6. C. Schmid and R. Mohr, IEEE Trans. Pattern Anal. 19, 530 (1997).
  7. D. G. Lowe, in Proceedings of International Conference on Computer Vision 1150 (1999).
  8. D. G. Lowe, Int. J. Comput. Vision. 60, 91 (2004).
  9. A. Baumberg, in Proceedings of the International Conference on Computer Vision and Pattern Recognition 774 (2000).
  10. T. Tuytelaars and L. Van Gool, in Proceedings of the 11th British Machine Vision Conference 412 (2000).
  11. M. Brown and D. Lowe, in Proceedings of the 13th British Machine Vision Conference 253 (2002).
  12. P. L. Ding, J. F. Mei, L. M. Zhang, J. Infrared Millim. Wav. 20, 5 (2001).
  13. G. Chen and F. H. Qi, J. Infrared and Millim. Wav. 19, 5 (2000).
  14. Q. Zeng, L. Liu, and J. Li, Chin. Opt. Lett. 8, 573 (2010).
  15. M. Brown, R. Szeliski and S. Winder, in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1, 510 (2005).
  16. C. Tan, H. Wang, and D. Pei, Tsinghua Sci. Technol. 15, 357 (2010).
  17. Y. Ke and R. Sukthankar, in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2, 506 (2004).
  18. Andrea Vedaldi, "SIFT for Matlab", http://www.vlfeat. org/vedaldi/code/sift.html (October, 2005).

Cited By

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited