Neural Network Regression of Eyes Location in Face Images

  • Krzysztof Rusek
  • Piotr Guzik
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 368)

Abstract

Automatic eye localisation is a crucial part of many computer vision algorithms for processing face images. Some of the existing algorithms can be very accurate unfortunately at the cost of computational complexity. In this paper the new solution to the problem of automatic eye localisation is proposed. Eye localisation is posed as a nonlinear regression problem solved by standard feed-forward multilayer perceptron (MLP) with two hidden layers. Additionally the procedure for artificial training samples generation is proposed.

The input feature vector is constructed from coefficients of two dimensional discrete cosine transform(DCT) of a face image. Both, the feature extraction and neural network prediction have known efficient implementations, thus the entire procedure can be very fast.

Obtained results indicate that the accuracy of the proposed approach is comparable or better than existing ones.

Keywords

eye localisation neural network DCT computer vision 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    BioID face database, http://www.bioid.com
  2. 2.
    Bishop, C.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer (2006)Google Scholar
  3. 3.
    Campadelli, P., Lanzarotti, R., Lipori, G.: Precise eye and mouth localization. International Journal of Pattern Recognition and Artificial Intelligence 23(03), 359–377 (2009)CrossRefGoogle Scholar
  4. 4.
    Enge, J., Głowacz, A., Grega, M., Leszczuk, M., Papir, Z., Romaniak, P., Simko, V.: OASIS archive – open archiving system with internet sharing. In: Mauthe, A., Zeadally, S., Cerqueira, E., Curado, M. (eds.) FMN 2009. LNCS, vol. 5630, pp. 254–259. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  5. 5.
    Everingham, M., Zisserman, A.: Regression and classification approaches to eye localization in face images. In: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition, pp. 441–448 (2006)Google Scholar
  6. 6.
    Głowacz, A., Grega, M., Leszczuk, M., Papir, Z., Romaniak, P., Fornalski, P., Lutwin, M., Enge, J., Lurk, T., Šimko, V.: Open internet gateways to archives of media art. Multimedia Tools Appl.Google Scholar
  7. 7.
    Hudson Beale, M., Hagan, M.T., Demuth, H.B.: Neural Network Toolbox User’s Guide. MathWorks, Natick (2012)Google Scholar
  8. 8.
    Ioannou, S., Kessous, L., Caridakis, G., Karpouzis, K., Aharonson, V., Kollias, S.: Adaptive on-line neural network retraining for real life multimodal emotion recognition. In: Kollias, S., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 81–92. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Jesorsky, O., Kirchberg, K.J., Frischholz, R.W.: Robust face detection using the hausdorff distance. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 90–95. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  10. 10.
    Kroon, B., Maas, S., Boughorbel, S., Hanjalic, A.: Eye localization in low and standard definition content with application to face matching. Comput. Vis. Image Underst. 113(8), 921–933 (2009)CrossRefGoogle Scholar
  11. 11.
    Riopka, T., Boult, T.: The eyes have it. In: Proceedings of ACM SIGMM Multimedia Biometrics Methods and Applications Workshop, pp. 9–16 (2003)Google Scholar
  12. 12.
    Rusek, K., Orzechowski, T., Dziech, A.: LDA for face profile detection. In: Dziech, A., Czyżewski, A. (eds.) MCSS 2011. CCIS, vol. 149, pp. 144–148. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Valenti, R., Gevers, T.: Accurate eye center location and tracking using isophote curvature. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8 (June 2008)Google Scholar
  14. 14.
    Yang, F., Huang, J., Yang, P., Metaxas, D.: Eye localization through multiscale sparse dictionaries. In: 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshops (FG 2011), pp. 514–518 (March 2011)Google Scholar
  15. 15.
    Zhou, Z.H., Geng, X.: Projection functions for eye detection. Pattern Recognition 37(5), 1049–1056 (2004)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Krzysztof Rusek
    • 1
  • Piotr Guzik
    • 1
  1. 1.Department of TelecommunicationsAGH University of Science and TechnologyKrakowPoland

Personalised recommendations