Region Covariance: A Fast Descriptor for Detection and Classification

  • Oncel Tuzel
  • Fatih Porikli
  • Peter Meer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)

Abstract

We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rosenfeld, A., Vanderburg, G.: Coarse-fine template matching. IEEE Trans. Syst. Man. Cyb. 7, 104–107 (1977)CrossRefGoogle Scholar
  2. 2.
    Brunelli, R., Poggio, T.: Face recognition: Features versus templates. IEEE Trans. Pattern Anal. Machine Intell. 15, 1042–1052 (1993)CrossRefGoogle Scholar
  3. 3.
    Marée, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, San Diego, CA, vol. 1, pp. 34–40 (2005)Google Scholar
  4. 4.
    Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Maui, HI, pp. 586–591 (1991)Google Scholar
  5. 5.
    Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. Intl. J. of Comp. Vision 26, 63–84 (1998)CrossRefGoogle Scholar
  6. 6.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head, SC, vol. 1, pp. 142–149 (2000)Google Scholar
  7. 7.
    Porikli, F.: Integral histogram: A fast way to extract histograms in cartesian spaces. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, San Diego, CA, vol. 1, pp. 829–836 (2005)Google Scholar
  8. 8.
    Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Intl. J. of Comp. Vision 43, 29–44 (2001)CrossRefMATHGoogle Scholar
  9. 9.
    Varma, M., Zisserman, A.: Statistical approaches to material classification. In: Proc. European Conf. on Computer Vision, Copehagen, Denmark (2002)Google Scholar
  10. 10.
    Georgescu, B., Meer, P.: Point matching under large image deformations and illumination changes. IEEE Trans. Pattern Anal. Machine Intell. 26, 674–688 (2004)CrossRefGoogle Scholar
  11. 11.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, HI, vol. 1, pp. 511–518 (2001)Google Scholar
  12. 12.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Intl. J. of Comp. Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  13. 13.
    Förstner, W., Moonen, B.: A metric for covariance matrices. Technical report, Dept. of Geodesy and Geoinformatics, Stuttgart University (1999)Google Scholar
  14. 14.
    Schmid, C.: Constructing models for content-based image retreival. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, HI, pp. 39–45 (2001)Google Scholar
  15. 15.
    Georgescu, B., Shimshoni, I., Meer, P.: Mean shift based clustering in high dimensions: A texture classification example. In: Proc. 9th Intl. Conf. on Computer Vision, Nice, France, pp. 456–463 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Oncel Tuzel
    • 1
    • 3
  • Fatih Porikli
    • 3
  • Peter Meer
    • 1
    • 2
  1. 1.Computer Science DepartmentUSA
  2. 2.Electrical and Computer Engineering DepartmentRutgers UniversityPiscatawayUSA
  3. 3.Mitsubishi Electric Research LaboratoriesCambridgeUSA

Personalised recommendations