Advertisement

Selecting Optimal Orientations of Gabor Wavelet Filters for Facial Image Analysis

  • Tianqi Zhang
  • Bao-Liang Lu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6134)

Abstract

Gabor wavelet-based methods have been widely used to extract representative features for face analysis. However, the existing methods usually suffer from high computational complexity of Gabor wavelet transform (GWT), and the Gabor parameters are fixed to a few conventional values which are assumed to be the best choice. In this paper we show that, for some facial analysis applications, the conventional GWT could be simplified by selecting the most discriminating Gabor orientations. In the selection process, we analyze the histogram of oriented gradient (HOG) of the average face image in a dataset, and eliminate the less significant orientation combinations. Then we traverse the rest combinations and select the best according to classification performance. We find that the selected orientations match the analysis of HOG well, and are therefore consistent with the intrinsic gradient characteristics of human face images. In order to assess the performance of the selected Gabor filters, we apply the proposed method to two tasks: face recognition and gender classification. The experimental results show that our method improves the accuracy of the classifiers and reduces the computation cost.

References

  1. 1.
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. Journal of the Optical Society of America A 2(7), 1160–1169 (1985)CrossRefGoogle Scholar
  2. 2.
    Marcelja, S.: Mathematical description of the responses of simple cortical cells. Journal of the Optical Society of America 70(11), 1297–1300 (1980)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Liu, C.: Gabor-based kernel PCA with fractional power polynomial models for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(5), 572–581 (2004)CrossRefGoogle Scholar
  4. 4.
    Liu, C., Wechsler, H.: A Gabor feature classifier for face recognition. In: Proceedings of IEEE International Conference on Computer Vision, vol. 2 (2001)Google Scholar
  5. 5.
    Lian, H., Lu, B.: Multi-view gender classification using local binary patterns and support vector machines. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3972, p. 202. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Liu, C., Wechsler, H.: Independent component analysis of Gabor features for face recognition. IEEE Transactions on Neural Networks 14(4), 919–928 (2003)CrossRefGoogle Scholar
  7. 7.
    Zhang, W., Shan, S., Gao, W., Chen, X., Zhang, H.: Local Gabor binary pattern histogram sequence (LGBPHS): A novel non-statistical model for face representation and recognition. In: Proceedings of ICCV, pp. 786–791 (2005)Google Scholar
  8. 8.
    Xia, B., Sun, H., Lu, B.: Multi-view gender classification based on local Gabor binary mapping pattern and support vector machines. In: Proceedings of IEEE International Joint Conference on Neural Networks, pp. 3388–3395 (2008)Google Scholar
  9. 9.
    Moreno, P., Bernardino, A., Santos-Victor, J.: Gabor parameter selection for local feature detection. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3522, pp. 11–19. Springer, Heidelberg (2005)Google Scholar
  10. 10.
    Wu, H., Yoshida, Y., Shioyama, T.: Optimal Gabor filters for high speed face identification. Vectors 3, 5 (2002)Google Scholar
  11. 11.
    Wang, L., Zhang, Y., Feng, J.: On the euclidean distance of images. IEEE transactions on pattern analysis and machine intelligence 27, 1334–1339 (2005)CrossRefGoogle Scholar
  12. 12.
    Li, J., Lu, B.: An adaptive image Euclidean distance. Pattern Recognition 42, 349–357 (2009)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Zhu, S., Song, Z., Feng, J.: Face recognition using local binary patterns with image Euclidean distance. In: Proceedings of SPIE, vol.  6970, 67904Z (2007)Google Scholar
  14. 14.
    Burr, D., Morrone, M., Spinelli, D.: Evidence for edge and bar detectors in human vision. Vision Research 29, 419–431 (1989)CrossRefGoogle Scholar
  15. 15.
    Field, D.: Relations between the statistics of natural images and the response properties of cortical cells. Journal of the Optical Society of America A 4, 2379–2394 (1987)CrossRefGoogle Scholar
  16. 16.
    Jones, J., Palmer, L.: An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology 58, 1233 (1987)Google Scholar
  17. 17.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, p. 886. Citeseer (2005)Google Scholar
  18. 18.
    Sobel, I., Feldman, G.: A 3x3 isotropic gradient operator for image processing. Presentation for Stanford Artificial Project (1968)Google Scholar
  19. 19.
    Pollen, D.A., Ronner, S.F.: Phase relationships between adjacent simple cells in the cat. Science 212, 1409–1411 (1981)CrossRefGoogle Scholar
  20. 20.
    Gao, W., Cao, B., Shan, S., Chen, X., Zhou, D., Zhang, X., Zhao, D.: The CAS-PEAL large-scale Chinese face database and baseline evaluations. IEEE Transactions on Systems Man and Cybernetics Part A Systems and Humans 38, 149 (2008)CrossRefGoogle Scholar
  21. 21.
    Phillips, P., Wechsler, H., Huang, J., Rauss, P.: The FERET database and evaluation procedure for face-recognition algorithms. Image and Vision Computing 16, 295–306 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Tianqi Zhang
    • 1
  • Bao-Liang Lu
    • 1
    • 2
  1. 1.Dept. of Computer Sci. & Eng.Shanghai Jiao Tong UniversityShanghaiChina
  2. 2.MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent SystemsShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations