TOP-SIFT: the selected SIFT descriptor based on dictionary learning

  • Yujie Liu
  • Deng Yu
  • Xiaoming Chen
  • Zongmin Li
  • Jianping Fan
Original Article

Abstract

The large amount of SIFT descriptors in an image and the high dimensionality of SIFT descriptor have made problems for the large-scale image database in terms of speed and scalability. In this paper, we present a descriptor selection algorithm based on dictionary learning to remove the redundant features and reserve only a small set of features, which we refer to as TOP-SIFTs. During the experiment, we discovered the inner relativity between the problem of descriptor selection and dictionary learning in sparse representation, and then turned our problem into dictionary learning. We designed a new dictionary learning method to adapt our problem and employed the simulated annealing algorithm to obtain the optimal solution. During the process of learning, we added the sparsity constraint and spatial distribution characteristic of SIFT points. And lastly selected the small representative feature set with good spatial distribution. Compared with the earlier methods, our method is neither relying on the database nor losing important information, and the experiments have shown that our algorithm can save memory space a lot and increase time efficiency while maintaining the accuracy as well.

Keywords

SIFT descriptor selection Dictionary learning Sparse coding Feature compression 

Notes

Acknowledgements

This work is partly supported by National Natural Science Foundation of China (Grant Nos. 61379106, 61379082, 61227802) and the Shandong Provincial Natural Science Foundation (Grant Nos. ZR2013FM036, ZR2015FM011, ZR2015FM022).

References

  1. 1.
    Aharon, M., Elad, M., Bruckstein, A.: The K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)CrossRefMATHGoogle Scholar
  2. 2.
    Alcantarilla, P.F., Beall, C., Dellaert, F.: Large-Scale Dense 3D Reconstruction From Stereo Imagery. Georgia Institute of Technology, Atlanta (2013)Google Scholar
  3. 3.
    Bao, S.Y., Chandraker, M., Lin, Y., Savarese, S.: Dense object reconstruction with semantic priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1264–1271 (2013)Google Scholar
  4. 4.
    Brown, M., Szeliski, R., Winder, S.: Multi-image matching using multi-scale oriented patches. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 510–517. IEEE (2005)Google Scholar
  5. 5.
    Dash, M., Choi, K., Scheuermann, P., Liu, H.: Feature selection for clustering-a filter solution. In: Proceedings of 2002 IEEE International Conference on Data Mining, ICDM 2003, pp. 115–122. IEEE (2002)Google Scholar
  6. 6.
    Dean, T., Ruzon, M.A., Segal, M., Shlens, J., Vijayanarasimhan, S., Yagnik, J.: Fast, accurate detection of 100,000 object classes on a single machine. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1814–1821 (2013)Google Scholar
  7. 7.
    Donoho, D.L., Elad, M.: Optimally sparse representation in general (nonorthogonal) dictionaries via l1 minimization. Proc. Nat. Acad. Sci. 100(5), 2197–2202 (2003)CrossRefMATHGoogle Scholar
  8. 8.
    Engan, K., Aase, S.O., Husoy, J.H.: Frame based signal compression using method of optimal directions (mod). In: Proceedings of the 1999 IEEE International Symposium on Circuits and Systems, ISCAS’99, vol 4, pp. 1–4. IEEE (1999)Google Scholar
  9. 9.
    Foo, J.J., Sinha, R.: Pruning sift for scalable near-duplicate image matching. In: Proceedings of the Eighteenth Conference on Australasian Database, vol. 63, pp. 63–71. Australian Computer Society, Inc. (2007)Google Scholar
  10. 10.
    Gionis, A., Indyk, P., Motwani, R., et al.: Similarity search in high dimensions via hashing. VLDB 99, 518–529 (1999)Google Scholar
  11. 11.
    Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometry consistency for large scale image search–extended version (2008)Google Scholar
  12. 12.
    Johnson, M., Cipolla, R.: Stable interest points for improved image retrieval and matching. Technical report (2006)Google Scholar
  13. 13.
    Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P., et al.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    Knopp, J., Sivic, J., Pajdla, T.: Avoiding confusing features in place recognition. In: European Conference on Computer Vision, pp. 748–761. Springer (2010)Google Scholar
  15. 15.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2169–2178. IEEE (2006)Google Scholar
  16. 16.
    Lee, Y.J., Grauman, K.: Vision Foreground focus: unsupervised learning from partially matching images. Int. J. Comput. 85(2), 143–166 (2009)Google Scholar
  17. 17.
    Li, Y., Peng, Z., Liang, D., Chang, H., Cai, Z.: Facial age estimation by using stacked feature composition and selection. Vis. Comput. 32(12), 1525–1536 (2016)CrossRefGoogle Scholar
  18. 18.
    Liu, Y., Chen, X., Zhao, Q., Li, Z., Fan, J.: Top-sift: a new method for sift descriptor selection. In: 2015 IEEE International Conference on Multimedia Big Data (BigMM), pp. 236–239. IEEE (2015)Google Scholar
  19. 19.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157. IEEE (1999)Google Scholar
  20. 20.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  21. 21.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 2, pp. 2161–2168. IEEE (2006)Google Scholar
  22. 22.
    Nowak, E., Jurie, F., Triggs, B.: Sampling strategies for bag-of-features image classification. In: European Conference on Computer Vision, pp. 490–503. Springer (2006)Google Scholar
  23. 23.
    Sadeghi, M.A., Hejrati, S.M.M., Gheissari, N.: Poisson local color correction for image stitching. In: VISAPP (1), pp. 275–282 (2008)Google Scholar
  24. 24.
    Turcot, P., Lowe, D.G.: Better matching with fewer features: the selection of useful features in large database recognition problems. In: 2009 IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 2109–2116. IEEE (2009)Google Scholar
  25. 25.
    Xu, W., Mulligan, J.: Performance evaluation of color correction approaches for automatic multi-view image and video stitching. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 263–270. IEEE (2010)Google Scholar
  26. 26.
    Yang, C., Shen, J., Peng, J., Fan, J.: Image collection summarization via dictionary learning for sparse representation. Pattern Recogn. 46(3), 948–961 (2013)CrossRefGoogle Scholar
  27. 27.
    Yasseen, Z., Verroust-Blondet, A., Nasri, A.: View selection for sketch-based 3D model retrieval using visual part shape description. Vis. Comput. 33(5), 565–583 (2017)CrossRefGoogle Scholar
  28. 28.
    Zhan, J., Zhuo, S., Hefeng, W., Luo, X.: Robust tracking via discriminative sparse feature selection. Vis. Comput. 31(5), 575–588 (2015)CrossRefGoogle Scholar
  29. 29.
    Zhou, N., Fan, J.: Jointly learning visually correlated dictionaries for large-scale visual recognition applications. IEEE Trans. Pattern Anal. Mach. Intell. 36(4), 715–730 (2014)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Yujie Liu
    • 1
  • Deng Yu
    • 1
  • Xiaoming Chen
    • 1
  • Zongmin Li
    • 1
  • Jianping Fan
    • 2
  1. 1.College of Computer and Communication EngineeringChina University of PetroleumQingdaoChina
  2. 2.Department of Computer ScienceUniversity of North Carolina at CharlotteCharlotteUSA

Personalised recommendations