Binary Coherent Edge Descriptors

  • C. Lawrence Zitnick
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)


Patch descriptors are used for a variety of tasks ranging from finding corresponding points across images, to describing object category parts. In this paper, we propose an image patch descriptor based on edge position, orientation and local linear length. Unlike previous works using histograms of gradients, our descriptor does not encode relative gradient magnitudes. Our approach locally normalizes the patch gradients to remove relative gradient information, followed by orientation dependent binning. Finally, the edge histogram is binarized to encode edge locations, orientations and lengths. Two additional extensions are proposed for fast PCA dimensionality reduction, and a min-hash approach for fast patch retrieval. Our algorithm produces state-of-the-art results on previously published object instance patch data sets, as well as a new patch data set modeling intra-category appearance variations.


Principal Component Analysis Image Patch Equal Error Rate Gradient Magnitude Jaccard Similarity 
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.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: CVPR, pp. 2161–2168 (2006)Google Scholar
  3. 3.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. IJCV 66 (2006)Google Scholar
  4. 4.
    Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: Exploring photo collections in 3d. ACM Transactions on Graphics 25, 835–846 (2006)Google Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)Google Scholar
  6. 6.
    Crandall, D., Huttenlocher, D.: Weakly supervised learning of part-based spatial models for visual object recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 16–29. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Felzenszwalb, P., Mcallester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
  8. 8.
    Berg, A.C., Malik, J.: Geometric blur for template matching. In: CVPR, pp. 607–614 (2001)Google Scholar
  9. 9.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE PAMI 27, 1615–1630 (2005)Google Scholar
  10. 10.
    Winder, S.A.J., Brown, M.: Learning local image descriptors. In: CVPR (2007)Google Scholar
  11. 11.
    Winder, S., Hua, G., Brown, M.: Picking the best daisy. In: CVPR, pp. 178–185 (2009)Google Scholar
  12. 12.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  13. 13.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE PAMI 27, 1615–1630 (2005)Google Scholar
  14. 14.
    Ke, Y., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image descriptors. In: CVPR, pp. 506–513 (2004)Google Scholar
  15. 15.
    Tola, E., Lepetit, V., Fua, P.: A fast local descriptor for dense matching. In: CVPR (2008)Google Scholar
  16. 16.
    Bay, H., Tuytelaars, T., Gool, L.V.: 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
  17. 17.
    Osindero, S., Hinton, G.E.: Modeling image patches with a directed hierarchy of markov random fields. In: NIPS 20 (2008)Google Scholar
  18. 18.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE PAMI 28, 1465–1479 (2006)Google Scholar
  19. 19.
    Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: CVPR (2008)Google Scholar
  20. 20.
    Babenko, B., Dollar, P., Belongie, S.: Task specific local region matching. In: ICCV (2007)Google Scholar
  21. 21.
    Cormen, T.H.: Introduction to Algorithms. MIT Press, Cambridge (2001)zbMATHGoogle Scholar
  22. 22.
    Torralba, A., Fergus, R., Weiss, Y.: Small codes and large databases for object recognition. In: CVPR (2008)Google Scholar
  23. 23.
    Salakhutdinov, R., Hinton, G.: Semantic hashing. Int. J. of Approximate Reasoning (2009)Google Scholar
  24. 24.
    Raginsky, M., Lazebnik, S.: Locality-sensitive binary codes from shift-invariant kernels. In: NIPS (2009)Google Scholar
  25. 25.
    Broder, A.Z.: On the resemblance and containment of documents. In: Compression and Complexity of Sequences (SEQUENCES 1997), pp. 21–29. IEEE Computer Society, Los Alamitos (1997)Google Scholar
  26. 26.
    Chum, O., Philbin, J., Zisserman, A.: Near duplicate image detection: min-hash and tf-idf weighting. In: British Machine Vision Conference (2008)Google Scholar
  27. 27.
    Chum, O., Perdoch, M., Matas, J.: Geometric min-hashing: Finding a (thick) needle in a haystack. In: CVPR, pp. 17–24 (2009)Google Scholar
  28. 28.
    Kulis, B., Grauman, K.: Kernelized locality-sensitive hashing for scalable image search. In: ICCV (2009)Google Scholar
  29. 29.
    Silpa-Anan, C., Hartley, R.: Optimised KD-trees for fast image descriptor matching. In: CVPR, pp. 1–8 (2008)Google Scholar
  30. 30.
    Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology (2007)Google Scholar
  31. 31.
    Mikolajczyk, K., Zisserman, A., Schmid, C.: Shape recognition with edge-based features. In: British Machine Vision Conference (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • C. Lawrence Zitnick
    • 1
  1. 1.Microsoft ResearchRedmond

Personalised recommendations