Advertisement

A study on fast SIFT image mosaic algorithm based on compressed sensing and wavelet transform

  • Xin XieEmail author
  • Yin Xu
  • Qing Liu
  • Fengping Hu
  • Tijian Cai
  • Nan Jiang
  • Huandong Xiong
Original Research

Abstract

Considering the disadvantages of massive calculation and slow speed of traditional Scale Invariant Feature Transform (SIFT) algorithm, we propose an improved image mosaic method which combines Wavelet Transform (WT) and Compressed Sensing (CS) algorithm. The method works as follows. Firstly, images are transformed with wavelet and compressed using compressed sensing technology. Then, image feature points are extracted in combination with SIFT algorithm. Finally, Sequential Similarity Detection Algorithm (SSDA) with adaptive threshold is used to fast search of image matching to find out an optimal stitching line, and a panoramic image is obtained. Experimental results demonstrate that the method realizes fast image matching, efficiently overcomes the shortcomings of heavy computation and low efficiency in the process of extracting image features, and guarantees matching accuracy and stitching efficiency, which meets the real-time requestments in machine vision system. This algorithm can be applied to image matching and stitching in the field of digital image security.

Keywords

Scale invariant feature transform Compressed sensing  Wavelet transform Sequential similarity detection algorithm Image mosaic Digital image security 

Notes

Acknowledgments

Project supported by the National Natural Science Foundation (61272197, 41402290, 61462028), Cultivation Plan of Leadership for Excellence Jiangxi Province and Poyang Lake 555 Engineering (S2013-57), Science and Technology Support Program of Jiangxi Province (20151BBE50055), Natural Science Foundation of Jiangxi Province (20132BAB201027, 20142BAB207007), and Landing Plan of Scientific and Technological Project of Jiangxi Provincial Colleges and Universities (KJLD2013037).

References

  1. Bai TZ, Hou XB (2013) An improved image matching algorithm based on sift. Trans Beijing Inst Technol 33(6):622–628Google Scholar
  2. Bay H, Ess A, Tuytelaars T (2006) Surf: speeded up robust features. Comput Vis Image Underst 110(3):346–359CrossRefGoogle Scholar
  3. Castiglione A, Pizzolante R, Santis AD, Carpentieri B, Castiglione A, Palmieri F (2015) Cloud-based adaptive compression and secure management services for 3D healthcare data. Future Gener Comput Syst 43–44:120–134CrossRefGoogle Scholar
  4. Cen YG, Chen XF, Cen LH (2010) Compressed sensing based on the single layer wavelet transform for image processing. J Commun 31(8A):51–55Google Scholar
  5. Chen TH, Horng G, Lee WB (2005) A publicly verifiable copyright-proving scheme resistant to malicious attacks. IEEE Trans Ind Electron 52(1):327–334CrossRefGoogle Scholar
  6. Cheng YH, Xue DY, Han XW (2008) Fast image mosaic based on wavelet transform for remote sensing. J Northeast Univ (Nat Sci) 29(10):1385–1388Google Scholar
  7. Dooho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289–1306CrossRefGoogle Scholar
  8. Fang XY, Pan ZG, Xu D (2003) An improved algorithm for image matching. J Comput-Aided Des Comput Graph 15(11):1362–1365Google Scholar
  9. Fan XN, Zhu JY (2009) Fast image matching algorithm based on wavelet transform and it’s implementation. Comput Eng Des 30(20):4674–4676Google Scholar
  10. He Y, Wang L (2010) Image stitching algorithm based on feature block and wavelet transform. Comput Eng Des 31(9):1958–1960Google Scholar
  11. Jane Y, Prabir BA (2000) Wavelet-based coarse-to-fine image matching scheme in a parallel virmal machine environment. IEEE Trans Image Process 9(9):1547–1559CrossRefGoogle Scholar
  12. Jiang MQ, Hong JX, Liao QW (2010) Seamless image mosaic based on feature invariant description. In: 3rd international conference on advanced computer theory and engineering (ICACTE). IEEE, pp 423–427Google Scholar
  13. Jiang N (2014) Wdem: weighted dynamics and evolution models for energy-constrained wireless sensor networks. Phys A: Stat Mech Appl 404:323–331CrossRefGoogle Scholar
  14. Jiang N, You H, Jiang F, He YS (2014) Dcsh: distributed compressed sensing algorithm for hierarchical wireless sensor networks. Int J Comput Commun Control 9(4):425–433CrossRefGoogle Scholar
  15. Jiang N, Xiao X, Liu L (2015) Localization scheme for wireless sensor networks based on “shortcut” constraint. Ad Hoc Sens Wirel Netw 26(1–4):1–19Google Scholar
  16. Li SC, Xu LD, Wang XH (2013) A continuous biomedical signal acquisition system based on compressed sensing in body sensor networks. IEEE Trans Ind Inform 9(3):1764–1771MathSciNetCrossRefGoogle Scholar
  17. Li SC, Xu LD, Wang XH (2013) Compressed sensing signal and data acquisition in wireless sensor networks and internet of things. IEEE Trans Ind Inform 9(4):2177–2186CrossRefGoogle Scholar
  18. Lowe DG (2004) Distinctive image features from scale invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  19. Pizzolante R, Carpentieri B, Castiglione A (2013) A secure low complexity approach for compression and transmission of 3-D medical images. In: 2013 Eighth international conference on broadband and wireless computing, communication and applications (BWCCA), Compiegne, France, 28–30 Oct 2013, pp 387–392Google Scholar
  20. Prete DD, Pardi S, Russo G (2011) Evaluating new cluster setup on 10Gbit/s network to support the superB computing model. In: Proceeding of CCP2011–2011 Palinuro (SA) Italy. IEEE, pp 21–24Google Scholar
  21. Qiu WT, Zhao J, Liu J, Wang JZ (2012) Image matching combine sift with regional ssda. In: International conference on control engineering and communication technology (ICCECT). IEEE, pp 177–179Google Scholar
  22. Shi GM, Liu DH, Gao DH (2009) Advances in theory and application of compressed sensing. Acta Electron Sin 37(5):1070–1081Google Scholar
  23. Wang LD, Hua SG, Liu J (2006) An algorithm for images matching based on sequential similarity detection with adaptive threshold. Electro-opt Technol Appl 21(3):54–58Google Scholar
  24. Wang JY, Chen WD, Li LF (2011) Seamless image mosaic based on feature invariant description. J Appl Opt 32(1):59–64Google Scholar
  25. Wang Y, Wang YT (2009) Image stitch algorithm based on sift and wavelet transform. Trans Beijing Inst Technol 29(5):423–426Google Scholar
  26. Wang SL, Xiang XG (2014) Real-time tracking using multi-feature weighting based on compressive sensing. Comput Appl Res 3(3):929–932Google Scholar
  27. Xi HF, Tian C (2013) Wide baseline image matching using support vector regression. J Chongqing Univ Posts Telecommun (Nat Sci Ed) 25(2):197–202Google Scholar
  28. Zeng H, Shi Y, Hou YT, Zhu RB, Lou W (2014) A novel mimo dof model for multi-hop networks. IEEE Netw 28(5):81–85CrossRefGoogle Scholar
  29. Zeng H, Shi Y, Hou YT, Lou W, Kompella S, Midkiff SF (2015a) An anlytical model for interference alignment in multi-hop mimo networks. In: IEEE transactions on mobile computingGoogle Scholar
  30. Zeng H, Shi Y, Hou YT, Lou W, Zhu R, Midkiff SF (2015b) A scheduling algorithm for mimo dof allocation in multi-hop networks. In: IEEE transactions on mobile computingGoogle Scholar
  31. Zeng H, Tian F, Hou YT, Lou W, Midkiff SF (2015c) Interference alignment for multi-hop wireless networks: challenges and research directions. In: IEEE networkGoogle Scholar
  32. Zhang XB, Wang JF, Yang YY (2011) Image matching algorithm based on wavelet transform. Comput Simul 28(10):219–223MathSciNetGoogle Scholar
  33. Zhang KH, Zhang L, Yang MH (2012) Real-time compressive tracking. In: European conference on computer vision. IEEE, pp 89–99Google Scholar
  34. Zhao XY, Du LM (2004) An automatic and robust image mosaic algorithm. J Image Graph 9(4):417–422Google Scholar
  35. Zuo Y, Chen Y, You H (2014) A fast sift image mosaic algorithm based on wavelet transform. J Chongqing Normal Univ (Nat Sci) 31(3):77–81Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Xin Xie
    • 1
    Email author
  • Yin Xu
    • 1
  • Qing Liu
    • 2
  • Fengping Hu
    • 3
  • Tijian Cai
    • 1
  • Nan Jiang
    • 1
  • Huandong Xiong
    • 1
  1. 1.School of Information EngineeringEast China Jiaotong UniversityNanchangPeople’s Republic of China
  2. 2.School of Foreign LanguagesShanghai Normal UniversityShanghaiPeople’s Republic of China
  3. 3.School of Civil EngineeringEast China Jiaotong UniversityNanchangPeople’s Republic of China

Personalised recommendations