Near-Duplicate Retrieval: A Benchmark Study of Modified SIFT Descriptors

  • Afra’a Ahmad AlyosefEmail author
  • Andreas Nürnberger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10163)


Local feature detectors and descriptors are widely used for image near-duplicate retrieval tasks. However, most studies and evaluations published so far focused on increasing retrieval accuracy by improving descriptor properties and similarity measures. There has been almost no comparisons considering the modification of the descriptors and the impact on accuracy and performance, which is especially of interest for interactive retrieval systems that require fast system responses. Therefore, we evaluate in this paper accuracy and performance of variations of SIFT descriptors (reduced SIFT versions, RC-SIFT\(-64 D\), the original SIFT\(-128 D\)) and SURF\(-64D\) in two cases: Firstly, using benchmarks of various sizes. Secondly, using one particular benchmark but extracting varying amounts of descriptors. Another aspect that has been almost neglected in previous benchmarks is the combination of different affine transformations in near-duplicate images. A problem that many real-world systems have to face. Therefore, we provide in addition results of a comparative performance analysis using benchmarks generated by combining several image affine transformations.


Query Image Affine Transformation Scale Invariant Feature Transform Illumination Change Retrieval Task 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. J. Comput. Vis. 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Nistèr, D., Stewènius, H.: Scalable recognition with a vocabulary tree. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2161–2168 (2006)Google Scholar
  3. 3.
    Jiang, M., Zhang, S., Li, H., Metaxas, D.N.: Computer-aided diagnosis of mammographic masses using scalable image retrieval. IEEE Trans. Biomed. Eng. 62, 783–792 (2015)CrossRefGoogle Scholar
  4. 4.
    Jianchao, Y., Kai, Y., Yihong, G., Thomas, H.: Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (2009)Google Scholar
  5. 5.
    Zhang, C., Wang, S., Huang, Q., Liu, J., Liang, C., Tian, Q.: Image classification using spatial pyramid robust sparse coding. Pattern Recogn. Lett. 34, 1046–1052 (2013)CrossRefGoogle Scholar
  6. 6.
    Zhang, D.Q., Chang, S.F.: Detecting image near-duplicate by stochastic attribute relational graph matching with learning. In: Proceedings of the 12th Annual ACM International Conference on Multimedia (2004)Google Scholar
  7. 7.
    Chum, O., Philbin, J., Isard, M., Zisserman, A.: Scalable near identical image and shot detection. In: Proceedings of the 6th ACM International Conference on Image and Video Retrieval (CIVR), pp. 549–556 (2007)Google Scholar
  8. 8.
    Chum, O., Philbin, J., Zisserman, A.: Near duplicate image detection: min-Hash and tf-idf weighting. In: British Machine Vision Conference, pp. 50.1–50.10 (2008)Google Scholar
  9. 9.
    Auclair, A., Vincent, N., Cohen, L.D.: Hash functions for near duplicate image retrieval. In: Applications of Computer Vision (WACV), pp. 1–6 (2009)Google Scholar
  10. 10.
    Xu, D., Cham, T., Yan, S., Duan, L., Chang, S.: Near duplicate identification with spatially aligned pyramid matching. IEEE Trans. Circ. Syst. Video Technol. 20, 1068–1079 (2010)CrossRefGoogle Scholar
  11. 11.
    Chu, L., Jiang, S., Wang, S., Zhang, Y., Huang, Q.: Robust spatial consistency graph model for partial duplicate image retrieval. IEEE Trans. Multimedia 15, 1982–1996 (2010)CrossRefGoogle Scholar
  12. 12.
    Steinbach, M., Ertoz, L., Kumar, V.: The challenges of clustering high dimensional data. In: Wille, L.T. (ed.) New Vistas in Statistical Physics-Applications in Econophysics, Bioinformatics, and Pattern Recognition, pp. 273–309. Springer, Heidelberg (2004)Google Scholar
  13. 13.
    Khan, N.Y., McCane, B., Wyvill, G.: SIFT and SURF performance evaluation against various image deformations on benchmark dataset. In: Digital Image Computing Techniques and Applications (DICTA), pp. 501–506 (2011)Google Scholar
  14. 14.
    Grauman, K., Darrell, T.: The pyramid match kernel: efficient learning with sets of features. J. Mach. Learn. Res. 8, 725–760 (2007)zbMATHGoogle Scholar
  15. 15.
    Grauman, K., Darrell, T.: Pyramid match kernels: discriminative classification with sets of image features. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 1458–1465 (2005)Google Scholar
  16. 16.
    Yang, Y., Newsam, S.: Comparing SIFT descriptors and Gabor texture features for classification of remote sensed imagery. In: Proceedings of the 15th IEEE on Image Processing, pp. 1852–1855 (2008)Google Scholar
  17. 17.
    Li, J., Qian, X., Li, Q., Zhao, Y., Wang, L., Tang, Y.Y.: Mining near duplicate image groups. Multimedia Tools Appl. 74, 655–669 (2014). Springer Science and Business Media, New YorkCrossRefGoogle Scholar
  18. 18.
    Steffen, J., Christian, H., Ahmad Alyosef, A., Tönnies, K., Nürnberger, A.: Rotational invariance at fixation points - experiments using human gaze data. In: Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods, pp. 451–456 (2012)Google Scholar
  19. 19.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). doi: 10.1007/11744023_32 CrossRefGoogle Scholar
  20. 20.
    Jègou, H., Douze, M., Schmid, C., Pèrez, P.: Aggregating local descriptors into a compact image representation. In: Proceedings of IEEE Computer Vision and Pattern Recognition, pp. 3304–3311 (2010)Google Scholar
  21. 21.
    Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: Computer Vision and Pattern Recognition, no. 2, pp. 506–513 (2004)Google Scholar
  22. 22.
    Ahmad Alyosef, A., Nürnberger, A.: Adapted SIFT descriptor for improved near duplicate retrieval. In: Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods, pp. 55–64 (2016)Google Scholar
  23. 23.
    Manning, C.D., Raghavan, P., Schütze, H.: Chapter 8: evaluation in information retrieval. Part of Introduction to Information Retrieval, pp. 151–175 (2009)Google Scholar
  24. 24.
    Aly, M., Welinder, P., Munich, M., Perona, P.: Towards automated large scale discovery of image families. In: Computer Vision and Pattern Recognition Second IEEE Workshop (CVPR), pp. 9–16 (2009)Google Scholar
  25. 25.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1615–1630 (2005)CrossRefGoogle Scholar
  26. 26.
    Foo, J.J., Sinha, R.: Pruning SIFT for scalable near-duplicate image matching. In: Proceedings of the Eighteenth Conference on Australasian Database, pp. 63–71 (2007)Google Scholar
  27. 27.
    Jègou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: European Conference on Computer Vision, pp. 301–317 (2008)Google Scholar
  28. 28.
    Nistèr, D., Stewènius, H.: Recognition Benchmark Images.
  29. 29.
    Aly, M., Welinder, P., Munich, M., Perona, P.: Caltech-Buildings Benchmark.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Technical and Business Information Systems, Faculty of Computer ScienceOtto von Geruicke University MagdeburgMagdeburgGermany

Personalised recommendations