Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation

  • Julien Mairal
  • Marius Leordeanu
  • Francis Bach
  • Martial Hebert
  • Jean Ponce
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5304)


Sparse signal models learned from data are widely used in audio, image, and video restoration. They have recently been generalized to discriminative image understanding tasks such as texture segmentation and feature selection. This paper extends this line of research by proposing a multiscale method to minimize least-squares reconstruction errors and discriminative cost functions under ℓ0 or ℓ1 regularization constraints. It is applied to edge detection, category-based edge selection and image classification tasks. Experiments on the Berkeley edge detection benchmark and the PASCAL VOC’05 and VOC’07 datasets demonstrate the computational efficiency of our algorithm and its ability to learn local image descriptions that effectively support demanding computer vision tasks.


Edge Detection Sparse Representation Reconstruction Error Sparse Code Orthogonal Match Pursuit 
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.
    Aharon, M., Elad, M., Bruckstein, A.M.: The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representations. IEEE Trans. SP 54(11) (2006)Google Scholar
  2. 2.
    Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: POCV 2006 (2006)Google Scholar
  3. 3.
    Canny, J.F.: A computational approach to edge detection. IEEE Trans. PAMI 8(6) (1986)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR (2005)Google Scholar
  5. 5.
    Dollar, P., Tu, Z., Belongie, S.: Supervised learning of edges and object boundaries. In: Proc. CVPR (2006)Google Scholar
  6. 6.
    Donoho, D.L.: Compressive sampling. IEEE Trans. IT 52(4) (2006)Google Scholar
  7. 7.
    Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Statist. 32(2) (2004)Google Scholar
  8. 8.
    Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. IP 54(12) (2006)Google Scholar
  9. 9.
    Engan, K., Aase, S.O., Husoy, J.H.: Frame based signal compression using method of optimal directions (MOD). In: Proc. ISCS (1999)Google Scholar
  10. 10.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) Results (2007)Google Scholar
  11. 11.
    Lee, H., Battle, A., Rajat, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Adv. NIPS (2007)Google Scholar
  12. 12.
    Leordeanu, M., Hebert, M., Sukthankar, R.: Beyond local appearance: Category recognition from pairwise interactions of simple features. In: Proc. CVPR (2007)Google Scholar
  13. 13.
    Luenberger, D.G.: Linear and Nonlinear Programming. Addison-Wesley, Reading (1984)zbMATHGoogle Scholar
  14. 14.
    Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Discriminative learned dictionaries for local image analysis. In: Proc. CVPR (2008)Google Scholar
  15. 15.
    Mairal, J., Elad, M., Sapiro, G.: Sparse representation for color image restoration. IEEE Trans. IP 17(1) (2008)Google Scholar
  16. 16.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using Contours to Detect and Localize Junctions in Natural Images. In: Proc. CVPR (2008)Google Scholar
  17. 17.
    Mallat, S., Zhang, Z.: Matching pursuit in a time-frequency dictionary. IEEE Trans. SP 41(12) (1993)Google Scholar
  18. 18.
    Martin, D.R., Fowlkes, C.C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. PAMI 26(1) (2004)Google Scholar
  19. 19.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. ICCV (2001)Google Scholar
  20. 20.
    Moghaddam, B., Weiss, Y., Avidan, S.: Spectral bounds for sparse pca: Exact and greedy algorithms. In: Adv. NIPS (2005)Google Scholar
  21. 21.
    Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: A strategy employed by v1? Vision Research 37 (1997)Google Scholar
  22. 22.
    Peyre, G.: Non-negative sparse modeling of textures. In: Sgallari, F., Murli, A., Paragios, N. (eds.) SSVM 2007. LNCS, vol. 4485. Springer, Heidelberg (2007)Google Scholar
  23. 23.
    Prasad, M., Zisserman, A., Fitzgibbon, A., Kumar, M.P., Torr, P.: Learning class-specifc edges for object detection and segmentation. In: Kalra, P.K., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338. Springer, Heidelberg (2006)Google Scholar
  24. 24.
    Ranzato, M., Huang, F., Boureau, Y., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Proc. CVPR (2007)Google Scholar
  25. 25.
    Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: Proc. CVPR (2005)Google Scholar
  26. 26.
    Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis (2004)Google Scholar
  27. 27.
    Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: Proc. ICCV (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Julien Mairal
    • 1
    • 4
  • Marius Leordeanu
    • 2
  • Francis Bach
    • 1
    • 4
  • Martial Hebert
    • 2
  • Jean Ponce
    • 3
    • 4
  1. 1.INRIA, Paris-RocquencourtFrance
  2. 2.Carnegie Mellon UniversityPittsburgh
  3. 3.Ecole Normale SupérieureParis
  4. 4.WILLOW project-team, ENS/INRIA/CNRS UMR 8548France

Personalised recommendations