Structured learning approach to image descriptor combination

Structured learning approach to image descriptor combination

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

In this study, the authors address the problem of combining descriptors for purposes of object categorisation and classification. The authors cast the problem in a structured learning setting by viewing the classifier bank and the codewords used in the categorisation and classification tasks as random fields. In this manner, the authors can abstract the problem into a graphical model setting, in which the fusion operation is a transformation over the field of descriptors and classifiers. Thus, the problem reduces itself to that of recovering the optimal transformation using a cost function which is convex and can be converted into either a quadratic or linear programme. This cost function is related to the target function used in discrete Markov random field approaches. The authors demonstrate the utility of our algorithm for purposes of image classification and learning class categories on two datasets.


    1. 1)
      • Nister, D., Stewenius, H.: `Scalable recognition with a vocabulary tree', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2006, p. 2161–2168.
    2. 2)
      • Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: `Discovering objects and their location in images', Proc. IEEE Int. Conf. on Computer Vision, 2005, p. 370–377.
    3. 3)
      • Chum, O., Philbin, J., Sivic, J., Isard, M., Zisserman, A.: `Total recall: automatic query expansion with a generative feature model for object retrieval', Proc. IEEE Int. Conf. on Computer Vision, 2007, p. 1–8.
    4. 4)
      • Fei-Fei, L., Perona, P.: `A bayesian hierarchical model for learning natural scene categories', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2005, p. 524–531.
    5. 5)
      • Quelhas, P., Monay, F., Odobez, J., Gatica-Perez, D., Tuytelaars, T., Van Gool, L.: `Modelling scenes with local descriptors and latent aspects', Proc. IEEE Int. Conf. on Computer Vision, 2005, I, p. 883–890.
    6. 6)
      • Nilsback, M.E., Zisserman, A.: `A visual vocabulary for flower classification', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2006, p. 1447–1454.
    7. 7)
      • Varma, M., Ray, D.: `Learning the discriminative powerinvariance trade-off', Proc. IEEE Int. Conf. on Computer Vision, 2007, p. 1–8.
    8. 8)
    9. 9)
      • Sengupta, K., Boyer, K.L.: `Using geometric hashing with information theoretic clustering for fast recognition from a large cad modelbase', Proc. IEEE Int. Symp. on Computer Vision, 1995, p. 151–156.
    10. 10)
      • Shokoufandeh, A., Dickinson, S.J., Siddiqi, K., Zucker, S.W.: `Indexing using a spectral encoding of topological structure', Proc. Computer Vision and Pattern Recognition, 1998, p. 491–497.
    11. 11)
      • Winder, S., Brown, M.: `Learning local image descriptors', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2007.
    12. 12)
      • Bosch, A., Zisserman, A., Munoz, X.: `Representing shape with a spatial pyramid kernel', Proc. ACM Int. Conf. on Image and Video Retrieval, 2007, p. 401–408.
    13. 13)
    14. 14)
    15. 15)
    16. 16)
      • N. Cristianini , J. Shawe-Taylor . (2000) An introduction to support vector machines.
    17. 17)
      • R. Baeza-Yates , B. Ribeiro-Neto . (1999) Modern information retrieval.
    18. 18)
    19. 19)
      • LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: `Gradient-based learning applied to document recognition', Proc. IEEE, 1998, 86, p. 2278–2324.
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
    26. 26)
      • Cristianini, N., Shawe-Taylor, J., Kandola, J., Elisseeff, A.: `On kernel-target alignment', Proc. Advances in Neural Information Processing Systems, 2002, p. 367–373.
    27. 27)
      • G. Lanckriet , N. Cristianini , P. Bartlett , L. El Ghaoui , M.I. Jordan . Learning the kernel matrix with semidefinite programming. J. Mach. Learn. Res. , 27 - 72
    28. 28)
    29. 29)
      • Keuchel, J.: `Multiclass image labeling with semidefinite programming', Proc. European Conf. on Computer Vision, 2006, p. 454–467.
    30. 30)
      • Torr, P.H.S.: `Solving markov random fields using semi definite programming', Proc. Int. Workshop on Artificial Intelligence and Statistics, 2003.
    31. 31)
      • Kumar, M.P., Torr, P.H.S., Zisserman, A.: `Solving markov random fields using second order cone programming relaxations', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2006, p. 1045–1052.
    32. 32)
      • Cour, T., Shi, J.: `Solving markov random fields with spectral relaxation', Proc. Int. Conf. on Artificial Intelligence and Statistics, 2007.
    33. 33)
      • Boykov, Y., Jolly, M.-P.: `Interactive graph cuts for optimal boundary and region segmentation of objects in n–d images', Proc. Int. Conf. on Computer Vision, 2001, p. 105–112.
    34. 34)
      • Zhou, D., Bousquet, O., Lal, T., Weston, J., Schölkopf, B.: `Learning with local and global consistency', Proc. Neural Information Processing Systems, 2003.
    35. 35)
      • Zhu, X., Ghahramani, Z., Lafferty, J.: `Semi-supervised learning using Gaussian fields and harmonic functions', Proc. 20th Int. Conf. on Machine Learning, 2003.
    36. 36)
    37. 37)
      • T. Davis . (2006) Direct methods for sparse linear systems.
    38. 38)
      • R.K. Ahuja , T.L. Magnanti , J.B. Orlin . (1993) Network flows: theory, algorithms, and applications.
    39. 39)
      • Sinop, A.K., Grady, L.: `A seeded image segmentation framework unifying graph cuts and ramdom walker which yields a new algorithm', Proc. ICCV, 2007.
    40. 40)
      • P.J. Huber . (1981) Robust statistics.
    41. 41)
      • T. Hastie , R. Tibshirani , J. Friedman . (2009) The elements of statistical learning: data mining, inference and prediction.
    42. 42)
      • Platt, J.: `Probabilistic outputs for support vector machines and comparison to regularized likelihood methods', Proc. Advances in Large Margin Classifiers, 2000, p. 61–74.
    43. 43)
      • Leibe, B., Schiele, B.: `Analyzing appearance and contour based methods for object categorization', Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2003, p. 409–415.
    44. 44)
    45. 45)
      • R.O. Duda , P.E. Hart , D.G. Stork . Pattern classification.
    46. 46)
      • C.C. Chang , C.J. Lin . LIBSVM: a library for support vector machines.
    47. 47)
    48. 48)
    49. 49)
      • Bach, F.R., Thibaux, R., Jordan, M.I.: `Computing regularization paths for learning multiple kernels', Proc. Conf. on Neural Information Processing Systems (NIPS), 2004.
    50. 50)
      • Nilsback, M.E., Zisserman, A.: `Automated flower classification over a large number of classes', Proc. 2008 Sixth Indian Conf. on Computer Vision, Graphics and Image Processing, 2008, p. 722–729.

Related content

This is a required field
Please enter a valid email address