Advertisement

Rectifying Non-euclidean Similarity Data through Tangent Space Reprojection

  • Weiping Xu
  • Edwin R. Hancock
  • Richard C. Wilson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6669)

Abstract

This paper concerns the analysis of shapes characterised in terms of dissimilarities rather than vectors of ordinal shape-attributes. Such characterisations are rarely metric, and as a result shape or pattern spaces can not be constructed via embeddings into a Euclidean space. The problem arises when the similarity matrix has negative eigenvalues. One way to characterise the departures from metricty is to use the relative mass of negative eigenvalues, or negative eigenfraction. In this paper, we commence by developing a new measure which gauges the extent to which individual data give rise to departures from metricity in a set of similarity data. This allows us to assess whether the non-Euclidean artifacts in a data-set can be attributed to individual objects or are distributed uniformly. Our second contribution is to develop a new means of rectifying non-Euclidean similarity data. To do this we represent the data using a graph on a curved manifold of constant curvature (i.e. hypersphere). Xu et. al. have shown how the rectification process can be effected by evolving the hyperspheres under the Ricci flow. However, this can have effect of violating the proximity constraints applying to the data. To overcome problem, here we show how to preserve the constraints using a tangent space representation that captures local structures. We demonstrate the utility of our method on the standard “chicken pieces” dataset.

Keywords

Dissimilarity Embedding Ricci flow Spherical embedding Tangent space 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pękalska, E., Harol, A., Duin, R., Spillmann, B., Bunke, H.: Non-euclidean or non-metric measures can be informative. In: Yeung, D.-Y., Kwok, J.T., Fred, A., Roli, F., de Ridder, D. (eds.) SSPR 2006 and SPR 2006. LNCS, vol. 4109, pp. 871–880. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  2. 2.
    Fletcher, P.T., Lu, C., Pizer, S.M., Joshi, S.: Barbara and Bunke, Horst: Principal geodesic analysis for the study of nonlinear statistics of shape. IEEE Transactions on Medical Imaging, 995–1005 (2004)Google Scholar
  3. 3.
    Goldfarb, L.: A new approach to pattern recognition. Progress in Pattern Recognition, 241–402 (1985)Google Scholar
  4. 4.
    Andreu, G., Crespo, A., Valiente, J.M.: Selecting the toroidal self-organizing feature maps (TSOFM) best organized to object recognition. In: ICNN, pp. 1341–1346 (1997)Google Scholar
  5. 5.
    Torsello, A., Hancock, E.R.: Computing approximate tree edit distance using relaxation labeling. Structural, Pattern Recognition Letters, 1089–1097 (2003)Google Scholar
  6. 6.
    Sanfeliu, A., Fu, K.-S.: A Distance measure between attributed relational graphs for pattern recognition. IEEE Transactions on Systems, Man, and Cybernetics, 353–362 (1983)Google Scholar
  7. 7.
    Chow, B., Luo, F.: Combinatorial Ricci flows on surfaces. J. Differential Geom., 97–129 (2003)Google Scholar
  8. 8.
    Xu, W., Hancock, E.R., Wilson, R.C.: Regularising the ricci flow embedding. In: Hancock, E.R., Wilson, R.C., Windeatt, T., Ulusoy, I., Escolano, F. (eds.) SSPR&SPR 2010. LNCS, vol. 6218, pp. 579–588. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Wilson, R.C., Hancock, E.R.: Spherical embedding and classification. In: Hancock, E.R., Wilson, R.C., Windeatt, T., Ulusoy, I., Escolano, F. (eds.) SSPR&SPR 2010. LNCS, vol. 6218, pp. 589–599. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
    Tenenbaum, J.B., Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Weiping Xu
    • 1
  • Edwin R. Hancock
    • 1
  • Richard C. Wilson
    • 1
  1. 1.Dept. of Computer ScienceUniversity of YorkUK

Personalised recommendations