Filter Size Optimization on a Convolutional Neural Network Using FGSA

  • Yutzil Poma
  • Patricia MelinEmail author
  • Claudia I. González
  • Gabriela E. Martínez
Part of the Studies in Computational Intelligence book series (SCI, volume 862)


This paper presents an approach to optimize the filter size of a convolutional neural network using the fuzzy gravitational search algorithm (FGSA). The FGSA method has been applied in others works to optimize traditional neural networks achieving good results; for this reason, is used in this paper to optimize the parameters of a convolutional neural network. The optimization of the convolutional neural network is used for the recognition and classification of human faces images. The presented model can be used in any image classification, and in this paper the optimization of convolutional neural network is applied in the CROPPED YALE database.


FGSA Convolutional neural network Optimization Neural network Pattern recognition 



We thank sour sponsor CONACYT & the Tijuana Institute of Technology for the financial support provided with the scholarship number 816488.


  1. 1.
    Le Cun Jackel, L.D., Boser, B., Denker, J S., Henderson, D., Howard, R.E., Hubbard, W., Le Cun, B., Denker J., Henderson, D.: Handwritten digit recognition with a back-propagation network. Adv. Neural Inf. Process. Syst. 396–404 (1990)Google Scholar
  2. 2.
    Martínez, G.E., Melin, P., Mendoza, O., Castillo, O.: Face recognition with a Sobel edge detector and the Choquet integral as integration method in a modular neural networks. In: Neural Networks and Nature-Inspired Optimization, pp. 59–70. Springer, Cham (2015)CrossRefGoogle Scholar
  3. 3.
    Melin, P., Sánchez, D.: Multi-objective optimization for modular granular neural networks applied to pattern recognition. Inf. Sci. (Ny) 460–461, 594–610 (2018)MathSciNetCrossRefGoogle Scholar
  4. 4.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2323 (1998)CrossRefGoogle Scholar
  5. 5.
    Jialue, F., Wei, X., Ying, W., Yihong, G.: Human tracking using convolutional neural networks. IEEE Trans. Neural Networks 21(10), 1610–1623 (2010)CrossRefGoogle Scholar
  6. 6.
    Frome, A., Cheung, G., Abdulkader, A., Zennaro, M., Wu, B., Bissacco, A., Hartwig, H., Neven, H., Vincent, L.: Large-scale privacy protection in google street view. In: ICCV, pp. 2373–2380. IEEE (2009)Google Scholar
  7. 7.
    Kanou Kanou, S.E., Ferrari, R.C., Mirza, M., Jean, S., Carrier, P.L., Dauphin, Y., Boulanger-Lewandowski, N., Aggarwal, A., Zumer, J., Lamblin, P., Raymond, J.P., Pal, C., Desjardins, G., Pascanu, R., Warde-Farley, D., Torabi, A., Sharma, A., Bengio, E., Konda, K.R., Wu, Z., Bouthillier, X., Froumenty, P., Gülçehre, G., Memisevic, R., Vincent, P., Courville, A., Bengio, Y.: Combining modality specific deep neural networks for emotion recognition in video. In: Proceeding 15th ACM International Conference Multimodal Interact—ICMI’13, pp. 543–550 (2013)Google Scholar
  8. 8.
    Ning, F., Delhomme, D., LeCun, Y., Piano, F., Bottou, L., Barbano, P.E.: Toward automatic phenotyping of developing embryos from videos. IEEE Trans. Image Process. 14(9), 1360–1371 (2005)CrossRefGoogle Scholar
  9. 9.
    Jain, V., Murray, J., Roth, F., Turaga, S., Zhigulin, V.: Supervised learning of image restoration with convolutional networks supplementary material: specific methods. Parameters 2(2), 3–5 (2007)Google Scholar
  10. 10.
    Poma, Y., Melin, P., González, C.I., Martínez, G.E.: Optimal recognition model based on convolutional neural networks and fuzzy gravitational search algorithm method (2018)Google Scholar
  11. 11.
    Wu, H., Bie, R., Guo, J., Meg, X., Wang, S.: Optimized CNN based image recognition through target region selection 156, 772–777 (2018)Google Scholar
  12. 12.
    Nasse, F., Thurau, C., Fink, G.A.: Face detection using gpu-based convolutional neural networks. Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artificial Intelligence Lect. Notes Bioinformatics), 5702, 83–90 (2009)Google Scholar
  13. 13.
    Sombra, A., Valdez, F., Melin, P., Castillo, O.: A new gravitational search algorithm using fuzzy logic to parameter adaptation. In: Proceeding EEE Congress on Evolutionary Computation (CEC), pp. 1068–1074 (2013)Google Scholar
  14. 14.
    Rashedi, E., Nezamabadi-pour, H., Saryazdi, S.: GSA: a gravitational search algorithm. Inf. Sci. (Ny) 179(13), 2232–2248 (2009)CrossRefGoogle Scholar
  15. 15.
    Hatamlou, A., Abdullah, S., Othman, Z.: Gravitational search algorithm with heuristic search for clustering problems. Conf. Data Min. Optim. June, 190–193 (2011)Google Scholar
  16. 16.
    Verma, O.P., Sharma, R.: Newtonian gravitational edge detection using gravitational search algorithm. In: International Conference on Communication Systems and Network Technologies IEEE, Rajkot, India, pp. 184–188 (2012)Google Scholar
  17. 17.
    Bengio, Y., LeCun, Y.: Convolution networks for images, speech, and time-series. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks. MIT Press, vol. 1, pp. 1–5 (1998)Google Scholar
  18. 18.
    Chellapilla, K., Puri, S., Simard, P.: High performance convolutional neural networks for document processing. Int. Work. Front. Handwrite. Recognition (2006)Google Scholar
  19. 19.
    Venkatesan, R., Li, B.: Convolutional Neural Networks in Visual Computing: A Concise Guide. Engineering, Taylor and Francis Group, CRC Press, Data-Enabled (2017)CrossRefGoogle Scholar
  20. 20.
    Ranzato, M.A., Huang, F.J., Boureau, Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE Conference Computing Vis. Pattern Recognition, pp. 1–8 (2007)Google Scholar
  21. 21.
    Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: ICPR, International Conference Pattern Recognition, pp. 3304–3308 (2012)Google Scholar
  22. 22.
    Lu, L., Zheng, Y., Carneiro, G., Yang, L.: Deep Learning and Convolutional Neural Networks for Medical Image Computing. Springer (2017)Google Scholar
  23. 23.
    Schutz, B.: Gravity from the ground up. Cambridge University Press, Cambridge (2003)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Yutzil Poma
    • 1
  • Patricia Melin
    • 1
    Email author
  • Claudia I. González
    • 1
  • Gabriela E. Martínez
    • 1
  1. 1.Tijuana Institute of TechnologyTijuanaMexico

Personalised recommendations