Characterizing the SOM Feature Detectors Under Various Input Conditions

  • Macario O. CordelIIEmail author
  • Arnulfo P. Azcarraga
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


A classifier with self-organizing maps (SOM) as feature detectors resembles the biological visual system learning mechanism. Each SOM feature detector is defined over a limited domain of viewing condition, such that its nodes instantiate the presence of an object’s part in the corresponding domain. The weights of the SOM nodes are trained via competition, similar to the development of the visual system. We argue that to approach human pattern recognition performance, we must look for a more accurate model of the visual system, not only in terms of the architecture, but also on how the node connections are developed, such as that of the SOM’s feature detectors. This work characterizes SOM as feature detectors to test the similarity of its response vis-á-vis the response of the biological visual system, and to benchmark its performance vis-á-vis the performance of the traditional feature detector convolution filter. We use various input environments i.e. inputs with limited patterns, inputs with various input perturbation and inputs with complex objects, as test cases for evaluation.


Feature detectors Self-organizing maps Multilayer perceptron Pattern recognition 


  1. 1.
    Arevalo, J., Cruz-Roa, A., Arias, V., Romero, E., Gonzalez, F.: An unsupervised feature learning framework for basal cell carcinoma image analysis. Artif. Intell. Med. 64, 131–145 (2015)CrossRefGoogle Scholar
  2. 2.
    Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3034–3042, June 2016Google Scholar
  3. 3.
    Carlson, M., Hubel, D.H., Wiesel, T.N.: Effects of monocular exposure to oriented lines on monkey striate cortex. Dev. Brain Res. 25(1), 71–81 (1986)CrossRefGoogle Scholar
  4. 4.
    Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649 (2012)Google Scholar
  5. 5.
    Cordel, M.O., Antioquia, A.M.C., Azcarraga, A.P.: Self-organizing maps as feature detectors for supervised neural network pattern recognition. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9950, pp. 618–625. Springer, Cham (2016). Scholar
  6. 6.
    Cordel, M.O., Azcarraga, A.P.: Measuring the contribution of filter bank layer to performance of convolutional neural networks. Int. J. Knowl.-Based Intell. Eng. Syst. 21(1), 15–27 (2017)Google Scholar
  7. 7.
    Dong, Z., Wu, Y., Pei, M., Jia, Y.: Vehicle type classification using semisupervised convolutional neural network. IEEE Trans. Intell. Transp. Syst. 16, 2247–2256 (2015)CrossRefGoogle Scholar
  8. 8.
    Fu, M., Xu, P., Li, X., Liu, Q., Ye, M., Zhu, C.: Fast crowd density estimation with convolutional neural networks. Eng. Appl. Artif. Intell. 43, 81–88 (2015)CrossRefGoogle Scholar
  9. 9.
    Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980)CrossRefGoogle Scholar
  10. 10.
    Fukushima, K.: Artificial vision by multi-layered neural networks: neocognitron and its advances. Neural Netw. 37, 103–119 (2013)CrossRefGoogle Scholar
  11. 11.
    Haines, D.E., Mihailoff, G.A.: The visual system. In: Fundamental Neuroscience for Basic and Clinical Applications, Chap. 20. Elsevier (2018)Google Scholar
  12. 12.
    Haoxiang, L., Zhe, L., Xiaohui, S., Jonathan, B., Gang, H.: A convolutional neural network cascade for face detection. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5325–5334 (2015)Google Scholar
  13. 13.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the International Conference on Computer Vision (ICCV) (2017)Google Scholar
  14. 14.
    Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex. J. Physiol. 106, 106–154 (1962)CrossRefGoogle Scholar
  15. 15.
    Hubel, D.H., Wiesel, T.N.: Effects of visual deprivation on morphology and physiology of cells in the cats lateral geniculate body. J. Neurophysiol. 26, 978–993 (1963)CrossRefGoogle Scholar
  16. 16.
    Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture in two nonstriate visual areas of the cat. J. Neurophysiol. 28, 229–289 (1965)CrossRefGoogle Scholar
  17. 17.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  18. 18.
    Mohebi, E., Bagirov, A.: A convolutional recursive modified self organizing map for handwritten digits recognition. Neural Netw. 60, 104–118 (2014)CrossRefGoogle Scholar
  19. 19.
    Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: British Machine Vision Conference (2015)Google Scholar
  20. 20.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Sabour, S., Frosst, N., Hinton, G.: Dynamic routing for between capsules. In: Advances in Neural Information Processing Systems, pp. 3859–3869 (2017)Google Scholar
  22. 22.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815–823. IEEE Computer Society (2015)Google Scholar
  23. 23.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolution networks. In: International Conference on Learning Representations (2014)Google Scholar
  24. 24.
    Tu, Z., et al.: Multi-stream CNN: learning representations based on human-related regions for action recognition. Pattern Recogn. 79, 32–43 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Computer StudiesDe La Salle UniversityManilaPhilippines

Personalised recommendations