Advertisement

A Modified Isomap Approach to Manifold Learning in Word Spotting

  • Sebastian Sudholt
  • Gernot A. Fink
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9358)

Abstract

Word spotting is an effective paradigm for indexing document images with minimal human effort. Here, the use of the Bag-of-Features principle has been shown to achieve competitive results on different benchmarks. Recently, a spatial pyramid approach was used as a word image representation to improve the retrieval results even further. The high dimensionality of the spatial pyramids was attempted to be countered by applying Latent Semantic Analysis. However, this leads to increasingly worse results when reducing to lower dimensions. In this paper, we propose a new approach to reducing the dimensionality of word image descriptors which is based on a modified version of the Isomap Manifold Learning algorithm. This approach is able to not only outperform Latent Semantic Analysis but also to reduce a word image descriptor to up to \(0.12\,\%\) of its original size without losing retrieval precision. We evaluate our approach on two different datasets.

Keywords

Word spotting Manifold learning Isomap Multidimensional scaling Bray Curtis distance Document image analysis 

References

  1. 1.
    Ahonen, T., Hadid, A., Pietik, M., Pietikäinen, M.: Face recognition with local binary patterns. In: European Conference on Computer Vision, pp. 469–481 (2004)Google Scholar
  2. 2.
    Aldavert, D., Rusinol, M., Toledo, R., Llados, J.: Integrating visual and textual cues for query-by-string word spotting. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 511–515 (2013)Google Scholar
  3. 3.
    Almazan, J., Fornes, A., Valveny, E.: Deformable HOG-based shape descriptor. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 1022–1026 (2013)Google Scholar
  4. 4.
    Almazan, J., Gordo, A., Fornes, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2552–2566 (2014)CrossRefGoogle Scholar
  5. 5.
    Bengio, Y., Paiement, J.F., Vincent, P., Delalllaux, O., Le Roux, N., Ouimet, M.: Out-of-sample extensions for LLE, Isomap, MDS, eigenmaps and spectral clustering. In: Advances in Neural Information Processing Systems, vol. 16, pp. 177–184 (2004)Google Scholar
  6. 6.
    Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  7. 7.
    Rath, T.M., Manmatha, R.: Word spotting for historical documents. Int. J. Doc. Anal. Recogn. 9, 139–152 (2007)CrossRefGoogle Scholar
  8. 8.
    Rothacker, L., Rusinol, M., Fink, G.A.: Bag-of-features HMMs for segmentation-free word spotting in handwritten documents. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp. 1305–1309 (2013)Google Scholar
  9. 9.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  10. 10.
    Rusiñol, M., Aldavert, D., Toledo, R., Lladós, J.: Efficient segmentation-free keyword spotting in historical document collections. Pattern Recognit. 48(2), 545–555 (2015)CrossRefGoogle Scholar
  11. 11.
    Silva, V.D., Tenenbaum, J.B.: Global versus local methods in nonlinear dimensionality reduction. In: Advances in Neural Information Processing Systems, vol. 15, pp. 705–712 (2003)Google Scholar
  12. 12.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)CrossRefGoogle Scholar
  13. 13.
    Zhang, Z.Y., Zha, H.Y.: Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM J. Sci. Comput. 26(1), 313–338 (2005)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Open Access This chapter is distributed under the terms of the Creative Commons Attribution Noncommercial License, which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Authors and Affiliations

  1. 1.Technische Universität DortmundDortmundGermany

Personalised recommendations