Advertisement

Sensing Forest for Pattern Recognition

  • Irina BurciuEmail author
  • Thomas Martinetz
  • Erhardt Barth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10617)

Abstract

We introduce the Sensing Forest as a novel way of learning how to efficiently sense the visual world for a particular recognition task. The efficiency is evaluated in terms of the resulting recognition performance. We show how the performance depends on the number of sensing values, i.e., the depth of the trees and the size of the forest. We here simulate the sensing process by re-sampling digital images; in future applications one might use dedicated hardware to solve such recognition tasks without acquiring images. We show that our algorithm outperforms traditional Random Forests on the benchmarks MNIST and COIL-100. The basic Sensing Forest is a prototype-based Random Forest with prototypes learned with k-means clustering. Recognition performance can be further increased by using Learning Vector Quantization.

References

  1. 1.
    O’Regan, J.K.: Solving the “real” mysteries of visual perception: the world as an outside memory. Can. J. Psychol. 46(3), 461–488 (1992)CrossRefGoogle Scholar
  2. 2.
    Liu, S.C., Yang, M.H., Steiner, A., Moeckel, R., Delbruck, T.: 1 kHz 2D visual motion sensor using 20 x 20 silicon retina optical sensor and DSP microcontroller. IEEE Trans. Biomed. Circ. Syst. 9(2), 207–216 (2015)CrossRefGoogle Scholar
  3. 3.
    Candès, E., Wakin, M.: Introduction to compressive sampling. IEEE Signal Process. Mag. 25(2), 21–30 (2008)CrossRefGoogle Scholar
  4. 4.
    Olshausen, B., Field, D.: Natural image statistics and efficient coding. Netw. Comput. Neural Syst. 7(2), 333–339 (1996)CrossRefGoogle Scholar
  5. 5.
    Donoho, D.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Burciu, I., Ion-Mărgineanu, A., Martinetz, T., Barth, E.: Visual manifold sensing. In: Rogowitz, B.E., Pappas, T.N., de Ridder, H. (eds.) Proceedings of SPIE Electronic Imaging Human Vision and Electronic Imaging XIX, vol. 9014, pp. 48:1–48:8 (2014)Google Scholar
  7. 7.
    Burciu, I., Martinetz, T., Barth, E.: Foveated manifold sensing for object recognition. In: Proceedings of IEEE Black Sea Conference on Communications and Networking, pp. 196–200 (2015)Google Scholar
  8. 8.
    Seung, H., Lee, D.: The manifold ways of perception. Science 290, 2268–2269 (2000)CrossRefGoogle Scholar
  9. 9.
    DiCarlo, J., Cox, D.: Untangling invariant object recognition. Trends Cogn. Sci. 11(8), 333–341 (2007)CrossRefGoogle Scholar
  10. 10.
    Burciu, I., Martinetz, T., Barth, E.: Hierarchical manifold sensing with foveation and adaptive partitioning of the dataset. J. Imaging Sci. Technol. 60(2), 20402:1–20402:10 (2016)CrossRefGoogle Scholar
  11. 11.
    Schütze, H., Barth, E., Martinetz, T.: An adaptive hierarchical sensing scheme for sparse signals. In: Rogowitz, B.E., Pappas, T.N., de Ridder, H. (eds.) Proceedings of SPIE Electronic Imaging, Human Vision and Electronic Imaging XIX, vol. 9014, pp. 15:1–15:8 (2014)Google Scholar
  12. 12.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer Series in Statistics. Springer, New York (2001).  https://doi.org/10.1007/978-0-387-21606-5 CrossRefzbMATHGoogle Scholar
  13. 13.
    Coates, A., Ng, A.Y.: Learning feature representations with k-means. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 561–580. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-35289-8_30 CrossRefGoogle Scholar
  14. 14.
    Arthur, D., Vassilvitskii, S.: K-means++: the advantages of careful seeding. In: SODA 2007 Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035 (2007)Google Scholar
  15. 15.
    Villmann, T., Bohnsack, A., Kaden, M.: Can learning vector quantization be an alternative to SVM and deep learning? Recent trends and advanced variants of learning vector quantization for classification learning. JAISCR 7(1), 65–81 (2017)Google Scholar
  16. 16.
    Kohonen, T.: Improved versions of learning vector quantization. In: IJCNN International Joint Conference on Neural Networks (1990)Google Scholar
  17. 17.
    Nova, D., Estvez, P.A.: A review of learning vector quantization classifiers. Neural Comput. Appl. 25(3), 511524 (2014)Google Scholar
  18. 18.
    Breiman, L.: Random forest. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  19. 19.
    Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library (COIL-100). Technical report CUCS-006-96 (1996)Google Scholar
  20. 20.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Institute for Neuro- and BioinformaticsUniversity of LübeckLübeckGermany

Personalised recommendations