Affine Subspace Representation for Feature Description

  • Zhenhua Wang
  • Bin Fan
  • Fuchao Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8695)


This paper proposes a novel Affine Subspace Representation (ASR) descriptor to deal with affine distortions induced by viewpoint changes. Unlike the traditional local descriptors such as SIFT, ASR inherently encodes local information of multi-view patches, making it robust to affine distortions while maintaining a high discriminative ability. To this end, PCA is used to represent affine-warped patches as PCA-patch vectors for its compactness and efficiency. Then according to the subspace assumption, which implies that the PCA-patch vectors of various affine-warped patches of the same keypoint can be represented by a low-dimensional linear subspace, the ASR descriptor is obtained by using a simple subspace-to-point mapping. Such a linear subspace representation could accurately capture the underlying information of a keypoint (local structure) under multiple views without sacrificing its distinctiveness. To accelerate the computation of ASR descriptor, a fast approximate algorithm is proposed by moving the most computational part (i.e., warp patch under various affine transformations) to an offline training stage. Experimental results show that ASR is not only better than the state-of-the-art descriptors under various image transformations, but also performs well without a dedicated affine invariant detector when dealing with viewpoint changes.


Feature Description Multiple View Local Patch Warping Function Sift Descriptor 
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.

Supplementary material

978-3-319-10584-0_7_MOESM1_ESM.pdf (152 kb)
Electronic Supplementary Material (PDF 153 KB)


  1. 1.
  2. 2.
    Basri, R., Hassner, T., Zelnik-Manor, L.: Approximate nearest subspace search. PAMI 33(2), 266–278 (2011)CrossRefGoogle Scholar
  3. 3.
    Baumberg, A.: Reliable feature matching across widely separated views. In: Proc. of CVPR, vol. 1, pp. 774–781. IEEE (2000)Google Scholar
  4. 4.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Edelman, A., Arias, T.A., Smith, S.T.: The geometry of algorithms with orthogonality constraints. SIAM Journal on Matrix Analysis and Applications 20(2), 303–353 (1998)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    Fan, B., Wu, F., Hu, Z.: Aggregating gradient distributions into intensity orders: A novel local image descriptor. In: Proc. of CVPR, pp. 2377–2384 (2011)Google Scholar
  7. 7.
    Fan, B., Wu, F., Hu, Z.: Rotationally invariant descriptors using intensity order pooling. PAMI 34(10), 2031–2045 (2012)CrossRefGoogle Scholar
  8. 8.
    Hassner, T., Mayzels, V., Zelnik-Manor, L.: On sifts and their scales. In: Proc. of CVPR (2012)Google Scholar
  9. 9.
    Hinterstoisser, S., Lepetit, V., Benhimane, S., Fua, P., Navab, N.: Learning real-time perspective patch rectification. IJCV, 1–24 (2011)Google Scholar
  10. 10.
    Leutenegger, S., Chli, M., Siegwart, R.Y.: Brisk: Binary robust invariant scalable keypoints. In: Proc. of ICCV, pp. 2548–2555 (2011)Google Scholar
  11. 11.
    Lindeberg, T.: Feature detection with automatic scale selection. IJCV 30(2), 79–116 (1998)CrossRefGoogle Scholar
  12. 12.
    Lindeberg, T., Gårding, J.: Shape-adapted smoothing in estimation of 3-d shape cues from affine deformations of local 2-d brightness structure. Image and Vision Computing 15(6), 415–434 (1997)CrossRefGoogle Scholar
  13. 13.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  14. 14.
    Matas, J., Chum, O., Urban, M., Stereo, T.P.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. of BMVC, pp. 414–431 (2002)Google Scholar
  15. 15.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.: A comparison of affine region detectors. IJCV 65(1), 43–72 (2005)CrossRefGoogle Scholar
  16. 16.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  17. 17.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  18. 18.
    Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3d objects. International Journal of Computer Vision 73(3), 263–284 (2007)CrossRefGoogle Scholar
  19. 19.
    Morel, J.-M., Yu, G.: Asift: A new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 438–469 (2009)Google Scholar
  20. 20.
    Ozuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast keypoint recognition using random ferns. PAMI 32(3), 448–461 (2010)CrossRefGoogle Scholar
  21. 21.
    Tuytelaars, T., Van Gool, L.: Matching widely separated views based on affine invariant regions. IJCV 59, 61–85 (2004)CrossRefGoogle Scholar
  22. 22.
    Wang, Z., Fan, B., Wu, F.: Local intensity order pattern for feature description. In: Proc. of ICCV, pp. 603–610 (2011)Google Scholar
  23. 23.
    Winder, S., Hua, G., Brown, M.: Picking the best daisy. In: Proc. of CVPR, pp. 178–185 (2009)Google Scholar
  24. 24.
    Yan, K., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: Proc. of CVPR, pp. 506–513 (2004)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Zhenhua Wang
    • 1
  • Bin Fan
    • 1
  • Fuchao Wu
    • 1
  1. 1.National Laboratory of Pattern RecognitionInstitute of Automation, Chinese Academy of SciencesBeijingChina

Personalised recommendations