Advertisement

Analysis of Tensor-Based Image Segmentation Using Echo State Networks

  • Charles Donkor
  • Emmanuel Sam
  • Sebastián BasterrechEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11472)

Abstract

In pixel classification-based segmentation both the quality of the feature set and the pixel classification technique employed may influence the accuracy of the process. Motivated by the potential of Structural Tensors in the extraction of hidden information about texture between neighboring pixels and the computational capabilities of Echo State Network (ESN), this study proposes a tensor-based segmentation approach using the standard ESN. The pixel features of the image are initially extracted by incorporating Structural Tensors in order to enrich it with information about image texture. Then the resulting feature set is fed into ESN and the output is trained to classify unseen pixels from the testing set. The effect of the two main parameters that impact the accuracy of ESN: reservoir size and spectral radius, was also evaluated. The results are promising when compared to recent state-of-the-art segmentation approaches.

Keywords

Image segmentation Image processing Echo State Network Support Vector Machine Feature extraction 

References

  1. 1.
    Basterrech, S.: Empirical analysis of the necessary and sufficient conditions of the echo state property. In: 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, AK, USA, 14–19 May 2017, pp. 888–896 (2017).  https://doi.org/10.1109/IJCNN.2017.7965946
  2. 2.
    Basterrech, S., Rubino, G.: Echo State Queueing Networks: a combination of reservoir computing and random neural networks. Probab. Eng. Inf. Sci. 31, 457–476 (2017).  https://doi.org/10.1017/S0269964817000110MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994).  https://doi.org/10.1109/72.279181CrossRefGoogle Scholar
  4. 4.
    Drucker, H., Burges, C., Kaufman, L., Smola, A., Vapnik, V.: Support vector regression machines. In: Neural Information Processing Systems, no. 1, pp. 155–161 (1996). 10.1.1.10.4845Google Scholar
  5. 5.
    Jackowski, K., Cyganek, B.: A learning-based colour image segmentation with extended and compact structural tensor feature representation. Pattern Anal. Appl. 20, 401–414 (2017)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. Technical report 148, German National Research Center for Information Technology (2001)Google Scholar
  7. 7.
    Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)CrossRefGoogle Scholar
  8. 8.
    Lathauwer, L.D.: Signal Processing Based on Multilinear Algebra. Katholieke Universiteit Leuven Faculteit der Toegepaste Wetenschappen Department Elektrotechniek (1997)Google Scholar
  9. 9.
    Lukos̆evic̆ius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127–149 (2009).  https://doi.org/10.1016/j.cosrev2009.03.005CrossRefGoogle Scholar
  10. 10.
    Lukoševičius, M.: A practical guide to applying echo state networks. In: Montavon, G., Orr, G., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol. 7700, pp. 659–686. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-35289-8_36CrossRefGoogle Scholar
  11. 11.
    Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for a neural computation based on perturbations. Neural Comput. 14, 2531–2560 (2002)CrossRefGoogle Scholar
  12. 12.
    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of 8th International Conference on Computer Vision, vol. 2, pp. 416–423, July 2001Google Scholar
  13. 13.
    Pal, N.R., Pal, S.K.: A review on image segmentation techniques. Pattern Recognit. 26, 1274–1294 (1993)Google Scholar
  14. 14.
    Prater, A.: Classification via tensor decompositions of echo state networks. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–8 (2017).  https://doi.org/10.1109/SSCI.2017.8280968
  15. 15.
    Souahlia, A., Belatreche, A., Benyettou, A., Curran, K.: An experimental evaluation of echo state network for colour image segmentation. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 1143–1150 (2016).  https://doi.org/10.1109/IJCNN.2016.7727326, http://ieeexplore.ieee.org/document/7727326/

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Cape CoastCape CoastGhana
  2. 2.School of Computing and TechnologyWisconsin International University CollegeAccraGhana
  3. 3.Department of Computer Science, Faculty of Electrical EngineeringCzech Technical UniversityPragueCzech Republic

Personalised recommendations