Advertisement

Distributed SVM face recognition based on Hadoop

  • Boping Zhang
Article

Abstract

In the work, we analyzed the face recognition method under the cloud computing platform. Based on the distributed support vector machine classification model, face recognition method was established on Hadoop platform to develop parallel computing advantage of MapReduce, thus improving recognition efficiency. With different functions in face feature recognition, conventional and depth LBP operators were integrated by weighted approach to play their respective advantages. Finally, face recognition method under cloud computing platform was conducted with example analysis by Yale B, ORL and FERET face databases, which were most widely used in face recognition field. Under the same cloud computing platform, the classifier was established by BP and RBF neural networks to compare with the research method in the work. The results showed that the SVM classifier has better face recognition effect than BP and RBF neural network classifier under cloud computing platform. The research method in the work has higher recognition accuracy than traditional method.

Keywords

Cloud computing Hadoop platform Face recognition Support vector machine Neural network 

Notes

Acknowledgements

The paper is subsidized by science and technology key project of Henan Province, NO. 172102210462.

References

  1. 1.
    Christmann, A., Hable, R.: Consistency of support vector machines using additive kernels for additive models[J]. Comput. Stat. Data Anal. 56(4), 854–873 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Qing, Wu, Bo, Liang, Wan, Wang: Face recognition method based on multi-class classification of smooth support vector machine [J]. J. Comput. Appl. z1, 122–126 (2015)Google Scholar
  3. 3.
    Tian, H., Zhao, L., Tian, Z.: An approach to face recognition based on SVD-TRIM and LSSVM algorithm [J]. J. Eng. Gr. 5, 74–80 (2010)Google Scholar
  4. 4.
    gan Lu, Z., Xu, C., Sun, N., Miao, X.: Improved face emotion identification algorithm by MLS-SVM with modified gauss kernel function [J]. Comput. Sci. 41(6), 132–135 (2014)Google Scholar
  5. 5.
    LIANG, S.: Face recognition research under the no limit condition based on LBP and deep learning [J]. J. Commun. 35(6), 154–160 (2014)Google Scholar
  6. 6.
    Xiong, C., Li, D., Da, B.: Face recognition based on LBP and PCA feature extraction [J]. J. South Central Univ. Natl. 30(2), 75–79 (2011)Google Scholar
  7. 7.
    Li, Y., Liu, K.: PCA and SVM face recognition method based on human face segmentation [J]. Microcomput. Appl. 35(15):51, 53–56 (2016)Google Scholar
  8. 8.
    Sweeney, C., Liu, L., Arietta, S.: HIPI: A Hadoop Image Processing Interface for Image-based MapReduce Tasks [J]. University of Virginia, Chris (2011)Google Scholar
  9. 9.
    Soyata, T., Muraleedharan, R., Funai, C.: Cloud-vision: real-time face recognition using a mobile-cloudlet-cloud acceleration architecture [C]. 2012 IEEE Symposium on Computers and Communications (ISCC), Cappadocia, 59–66 (2012)Google Scholar
  10. 10.
    Research on Face Recognition Based on A Cloud Computing Platform [Z]. http://www.facecity.com.cn (2014)
  11. 11.
    Maatta, J., Hadid, A., Pietikainen, M.: Face spoofing detection from single images using texture and local shape analysis [J]. IET Biom. 1(1), 3–10 (2012)CrossRefGoogle Scholar
  12. 12.
    Lin, Y., Lv, F., Zhu, S. et al.: Large-scale image classification: fast feature extraction and svm training [C]. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 1689–1696 (2011)Google Scholar
  13. 13.
    Liu, C., Wechsler, H.: Gabor based classification using the enhanced fisher linear discriminant model for face recognition [J]. IEEE Trans. Image Process. 11(4), 467–76 (2002)CrossRefGoogle Scholar
  14. 14.
    Hadoop[EB/OL]. http://hadoop.apache.org/ (2012)
  15. 15.
    Liao, Z., Xie, X., Liu, J.: Data classification based on support vector machines in cloud computing environment [J]. J. Guilin Univ. Technol. 4, 765–769 (2013)Google Scholar
  16. 16.
    Boyacioglu, M.A., Kara, Y., Baykan, B.K.: Predicting bank financial failwes using newal networks support vector machines and multivariate statistical methods: a comparative analysis in the sample of savings deposit inswance fund (SDIF) transferred banks in Twkey [J]. Exp. Syst. Appl. 36(2), 3355–3366 (2009)CrossRefGoogle Scholar
  17. 17.
    Caruana, G., Li, M., Qi, M.A.: MapReduce based parallel SVM for large scale spam filtering [C]. In: 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD). IEEE 4:2659–2662 (2011)Google Scholar
  18. 18.
    Alham, N.K., Li, M., Liu, Y., et al.: A MapReduce-based distributed SVM algorithm for automatic image annotation [J]. Comput. Math. Appl. 62(7), 2801–2811 (2011)CrossRefzbMATHGoogle Scholar
  19. 19.
    Catak, F.O., Balaban, M.E.: C1oudSVM: Training an SVM Classifier in Cloud Computing Systems [M]. Pervasive Computing and the Networked World, pp. 57–68. Springer, Berlin (2013)Google Scholar
  20. 20.
    Ma, Y., Wang, L., Li, L.: A parallel and convergent support vector machine based on MapReduce [M]. Computer Engineering and Networking, pp. 585–592. Springer, Berlin (2014)Google Scholar
  21. 21.
    Alham, N.K., Li, M., Liu, Y., et al.: A MapReduce-based distributed SVM ensemble for scalable image classification and annotation [J]. Comput. Math. Appl. 66(10), 1920–1934 (2013)CrossRefzbMATHGoogle Scholar
  22. 22.
    Zhang, W., Wang, W.: Face recognition based on local binary pattern and deep learning [J]. J. Comput. Appl. 35(5), 474–1478 (2015)Google Scholar
  23. 23.
    Chen, L., Zhao, F.: Application of local binary pattern weighting algorithm based on support vector machine in face recognition [J]. Bull. Sci. Technol. 7, 111–114 (2015)Google Scholar
  24. 24.
    Ballavia, F., Tegolo, D., Valenti, C.: Improving harris corner selection strategy [J]. IET Comput. Vis. 5(2), 87–96 (2011)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Bao, W., Zhou, H., Lu, W., Xie, F.: The system of knowledge management using web based learning and education technology [J]. Comput. Syst. Sci. Eng. 31(6), 469–473 (2016)Google Scholar
  26. 26.
    Zhou, Q., Luo, J.: The study on evaluation method of urban network security in the big data era. Intell. Autom. Soft Comput. (2017).  https://doi.org/10.1080/10798587.2016.1267444
  27. 27.
    Zhou, Q.: Multi-layer affective computing model based on emotional psychology. Electron. Commer. Res. (2017).  https://doi.org/10.1007/s10660-017-9265-8
  28. 28.
    Zhou, Q., Luo, J.: The service quality evaluation of ecologic economy systems using simulation computing. Comput. Syst. Sci. Eng. 31(6), 453–460 (2016)MathSciNetGoogle Scholar
  29. 29.
    Zhou, Q.: Research on heterogeneous data integration model of group enterprise based on cluster computing. Clust. Comput. 19, 1275 (2016).  https://doi.org/10.1007/s10586-016-0580-y
  30. 30.
    Annan, L., Shiguang, S., Wen, G.: Coupled bias–variance tradeoff for cross-pose face recognition [J]. IEEE Trans. Image Proces. 21(1), 305–315 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  31. 31.
    Xiang, Z., Tan, H., Ma, Z.: Performance research of HOG in face recognition [J]. Comput. Eng. 15, 194–196 (2012)Google Scholar
  32. 32.
    Kim, D., Lee, S., Sohn, M.: Face recognition via Local directional pattern[J]. Int. J. Secur. Appl. 7(2), 191–200 (2013)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.School of Information EngineeringXuchang UniversityXuchangChina

Personalised recommendations