Efficient Discriminative Projections for Compact Binary Descriptors

  • Tomasz Trzcinski
  • Vincent Lepetit
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)


Binary descriptors of image patches are increasingly popular given that they require less storage and enable faster processing. This, however, comes at a price of lower recognition performances. To boost these performances, we project the image patches to a more discriminative subspace, and threshold their coordinates to build our binary descriptor. However, applying complex projections to the patches is slow, which negates some of the advantages of binary descriptors. Hence, our key idea is to learn the discriminative projections so that they can be decomposed into a small number of simple filters for which the responses can be computed fast. We show that with as few as 32 bits per descriptor we outperform the state-of-the-art binary descriptors in terms of both accuracy and efficiency.


Image Patch Stepwise Approach Integral Image Random Projection Stochastic Gradient Descent 
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. IJCV 20, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    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)CrossRefGoogle Scholar
  3. 3.
    Calonder, M., Lepetit, V., Ozuysal, M., Trzcinski, T., Strecha, C., Fua, P.: BRIEF: Computing a Local Binary Descriptor Very Fast. PAMI (2011)Google Scholar
  4. 4.
    Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: ICCV (2011)Google Scholar
  5. 5.
    Leutenegger, S., Chli, M., Siegwart, R.: BRISK: Binary Robust Invariant Scalable Keypoints. In: ICCV (2011)Google Scholar
  6. 6.
    Brown, M., Hua, G., Winder, S.: Discriminative Learning of Local Image Descriptors. PAMI 33, 43–57 (2011)CrossRefGoogle Scholar
  7. 7.
    Strecha, C., Bronstein, A., Bronstein, M., Fua, P.: LDAHash: Improved Matching with Smaller Descriptors. PAMI 1, 66–78 (2012)CrossRefGoogle Scholar
  8. 8.
    Cai, H., Mikolajczyk, K., Matas, J.: Learning Linear Discriminant Projections for Dimensionality Reduction of Image Descriptors. PAMI 33, 338–352 (2011)CrossRefGoogle Scholar
  9. 9.
    Torralba, A., Fergus, R., Weiss, Y.: Small Codes and Large Databases for Recognition. In: CVPR (2008)Google Scholar
  10. 10.
    Chandrasekhar, V., Takacs, G., Chen, D., Tsai, S., Grzeszczuk, R., Girod, B.: CHoG: Compressed histogram of gradients A low bit-rate feature descriptor. In: CVPR (2009)Google Scholar
  11. 11.
    Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. PAMI 33, 117–128 (2011)CrossRefGoogle Scholar
  12. 12.
    Gionis, A., Indik, P., Motwani, R.: Similarity Search in High Dimensions via Hashing. In: International Conference on Very Large Databases (1999)Google Scholar
  13. 13.
    Weiss, Y., Torralba, A., Fergus, R.: Spectral Hashing. In: NIPS (2009)Google Scholar
  14. 14.
    Andoni, A., Indyk, P.: Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions. Communications of the ACM (2008)Google Scholar
  15. 15.
    Gong, Y., Lazebnik, S.: Iterative Quantization: A Procrustean Approach to Learning Binary Codes. In: CVPR (2011)Google Scholar
  16. 16.
    Shakhnarovich, G.: Learning Task-Specific Similarity. PhD thesis (2005)Google Scholar
  17. 17.
    Wang, J., Kumar, S.: S.-F.Chang: Semi-Supervised Hashing for Scalable Image Retrieval. In: CVPR (2010)Google Scholar
  18. 18.
    Bergamo, A., Torresani, L., Fitzgibbon, A.: Picodes: Learning a compact code for novel-category recognition. In: NIPS (2011)Google Scholar
  19. 19.
    Bach, F., Jenatton, R., Mairal, J., Obozienski, G.: Optimization with Sparsity-Inducing Penalties. Foundations and Trends in Machine Learning 4, 1–106 (2012)CrossRefGoogle Scholar
  20. 20.
    Tibshirani, R.: Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society (1996)Google Scholar
  21. 21.
    Rosten, E., Porter, R., Drummond, T.: Faster and Better: A Machine Learning Approach to Corner Detection. PAMI 32, 105–119 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Tomasz Trzcinski
    • 1
  • Vincent Lepetit
    • 1
  1. 1.CVLabEPFLLausanneSwitzerland

Personalised recommendations