Encoding Classes of Unaligned Objects Using Structural Similarity Cross-Covariance Tensors

  • Marco San Biagio
  • Samuele Martelli
  • Marco Crocco
  • Marco Cristani
  • Vittorio Murino
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)

Abstract

Encoding an object essence in terms of self-similarities between its parts is becoming a popular strategy in Computer Vision. In this paper, a new similarity-based descriptor, dubbed Structural Similarity Cross-Covariance Tensor is proposed, aimed to encode relations among different regions of an image in terms of cross-covariance matrices. The latter are calculated between low-level feature vectors extracted from pairs of regions. The new descriptor retains the advantages of the widely used covariance matrix descriptors [1], extending their expressiveness from local similarities inside a region to structural similarities across multiple regions. The new descriptor, applied on top of HOG, is tested on object and scene classification tasks with three datasets. The proposed method always outclasses baseline HOG and yields significant improvement over a recently proposed self-similarity descriptor in the two most challenging datasets.

Keywords

object recognition scene classification covariance 

References

  1. 1.
    Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. IEEE Trans. PAMI, 1713–1727 (2008)Google Scholar
  2. 2.
    Tosato, D., Spera, M., Cristani, M., Murino, V.: Block Characterizing humans on riemannian manifolds. IEEE Trans. PAMI, 2–15 (2013)Google Scholar
  3. 3.
    San Biagio, M., Crocco, M., Cristani, M., Martelli, S., Murino, V.: Heterogeneous Auto-Similarities of Characteristics (HASC): Exploiting relational information for classification. In: Proc. ICCV (2013)Google Scholar
  4. 4.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. ICCV, vol. 2, pp. 1150–1157 (1999)Google Scholar
  5. 5.
    Wang, X., Han, T.X., Yan, S.: An hog-lbp human detector with partial occlusion handling. In: Proc. ICCV, pp. 32–39 (2009)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  7. 7.
    Martelli, S., Cristani, M., Bazzani, L., Tosato, D., Murino, V.: Joining feature-based and similarity-based pattern description paradigms for object detection. In: Proc. ICPR (2012)Google Scholar
  8. 8.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. CVIU 106(1), 59–70 (2007)Google Scholar
  9. 9.
    Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Tech. Rep. 7694, California Institute of Technology (2007)Google Scholar
  10. 10.
    Perina, A., Jojic, N.: Spring lattice counting grids: Scene recognition using deformable positional constraints. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 837–851. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Chang, C.-C., Lin, C.-J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27 (2011), http://www.csie.ntu.edu.tw/cjlin/libsvm CrossRefGoogle Scholar
  12. 12.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: Proc. ICCV, pp. 606–613 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Marco San Biagio
    • 1
  • Samuele Martelli
    • 1
  • Marco Crocco
    • 1
  • Marco Cristani
    • 1
    • 2
  • Vittorio Murino
    • 1
    • 2
  1. 1.Pattern Analysis & Computer VisionIstituto Italiano di TecnologiaGenovaItaly
  2. 2.Dipartimento di InformaticaUniversità degli Studi di VeronaVeronaItaly

Personalised recommendations