Advertisement

On the Performance of Classic and Deep Neural Models in Image Recognition

  • Ricardo García-Ródenas
  • Luis Jiménez Linares
  • Julio Alberto López-Gómez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10614)

Abstract

Deep learning has arisen in the last years as a powerful and ultimate tool for machine learning problems. This article analyses the performance of classic and deep neural network models in a challenging problem like face recognition. The aim of this article is to study what the main advantages and disadvantages deep neural networks provide and when they will be more suitable than classic models, which have also obtained really good results in some complex problems. Is it worth using deep learning? The results show that deep models increase the learning capabilities of classic neural networks in problems with high non-linearities features.

Keywords

Deep neural networks Convolutional neural networks Face recognition Object recognition 

Notes

Acknowledgment

The authors would like to express his thanks to the project with number PEIC-2014- 003-P and to the authorities that give their support to its development, the FEDER and the Junta de Comunidades de Castilla la Mancha.

References

  1. 1.
    Berthold, M.R., Diamond, J.: Constructive training of probabilistic neural networks. Neurocomputing 19(1–3), 167–183 (1998)CrossRefGoogle Scholar
  2. 2.
    Abate, A., Nappi, M., Riccio, D., Sabatino, G.: 2d and 3d face recognition: a survey. Pattern Recogn. Lett. 28(14), 1885–1906 (2007)CrossRefGoogle Scholar
  3. 3.
    Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1475–1490 (2004)CrossRefGoogle Scholar
  4. 4.
    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS (including LNAI and LNB), vol. 2353, pp. 113–127. Springer, Heidelberg (2002). doi: 10.1007/3-540-47979-1_8 CrossRefGoogle Scholar
  5. 5.
    Barr, J., Bowyer, K., Flynn, P., Biswas, S.: Face recognition from video: a review. Int. J. Pattern Recogn. Artif. Intell. 26(5), 1266002 (2012)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–27 (2009)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Candès, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 11:1–11:37 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  8. 8.
    Damas, S., Cordón, O., Ibáñez, O., Santamaría, J., Alemán, I., Botella, M., Navarro, F.: Forensic identification by computer-aided craniofacial superimposition: a survey. ACM Comput. Surv. 43(4), 27:1–27:27 (2011)CrossRefGoogle Scholar
  9. 9.
    Dantone, M., Bossard, L., Quack, T., Van Gool, L.: Augmented faces, pp. 24–31 (2011)Google Scholar
  10. 10.
    Fasel, B., Luettin, J.: Automatic facial expression analysis: a survey. Pattern Recogn. 36(1), 259–275 (2003)CrossRefzbMATHGoogle Scholar
  11. 11.
    Ibáñez, O., Ballerini, L., Cordón, O., Damas, S., Santamaría, J.: An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification. Inf. Sci. 179(23), 3998–4028 (2009)CrossRefGoogle Scholar
  12. 12.
    Ilves, M., Gizatdinova, Y., Surakka, V., Vankka, E.: Head movement and facial expressions as game input. Entertain. Comput. 5(3), 147–156 (2014)CrossRefGoogle Scholar
  13. 13.
    Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  14. 14.
    Lee, J.D., Huang, C.H., Huang, T.C., Hsieh, H.Y., Lee, S.T.: Medical augment reality using a markerless registration framework. Expert Syst. Appl. 39(5), 5286–5294 (2012)CrossRefGoogle Scholar
  15. 15.
    Li, Y., Li, W., Wu, G.: An intrusion detection approach using SVM and multiple kernel method. Int. J. Adv. Comput. Technol. 4(1), 463–469 (2012)Google Scholar
  16. 16.
    Lu, D., Weng, Q.: A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens. 28(5), 823–870 (2007)CrossRefGoogle Scholar
  17. 17.
    Ma, L., Tan, T., Wang, Y., Zhang, D.: Efficient Iris recognition by characterizing key local variations. IEEE Trans. Image Process. 13(6), 739–750 (2004)CrossRefGoogle Scholar
  18. 18.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE International Conference on Neural Networks, vol. 1, pp. 586–591 (1993)Google Scholar
  19. 19.
    Snelick, R., Uludag, U., Mink, A., Indovina, M., Jain, A.: Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 450–455 (2005)CrossRefGoogle Scholar
  20. 20.
    Yin, L., Wei, X., Sun, Y., Wang, J., Rosato, M.: A 3d facial expression database for facial behavior research, pp. 211–216 (2006)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Ricardo García-Ródenas
    • 1
  • Luis Jiménez Linares
    • 1
  • Julio Alberto López-Gómez
    • 1
  1. 1.Department of MathematicsUniversity of Castilla la ManchaCiudad RealSpain

Personalised recommendations