Choosing the structure of convolutional neural networks for face recognition

Authors

Kabul Khudaybergenov, National University of UzbekistanFollow

Abstract

Evaluating the number of hidden neurons and hidden layers necessary for solving of face recognition, pattern recognition and classification tasks is one of the key problems in artificial neural networks. In this note, we show that artificial neural network with a two hidden layer feed forward neural network with d inputs, d neurons in the first hidden layer, 2d+2 neurons in the second hidden layer, k outputs and with a sigmoidal infinitely differentiable function can solve face recognition tasks. This result can be applied to design pattern recognition and classification models with optimal structure in the number of hidden neurons and hidden layers. In addition, we propose a new type of convolutional neural network, which is capable to extract most powerful features. The experimental results over well-known benchmark datasets shows that the convergence and the accuracy of the proposed model of artificial neural network is acceptable. Findings in this paper are experimentally analyzed on five different face datasets from machine learning repository.

First Page

20

Last Page

32

References

1. Saez D.T., Meng L., Hartnett M. Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss. Image and Vision Computing, Vol. 79, 99–108 (2018).

2. Li Y., Zheng W., Cui Z., Zhang T. Face recognition based on recurrent regression neural network. Neurocomputing, Vol. 297, 50–58 (2018).

3. Jain N., Kumar S., Kumar A., Shamsolmoali P., Zareapoor M. Hybrid deep neural networks for face emotion recognition. Pattern Recognition Letters, Vol. 115, 101–106 (2018).

4. Zhao J., Lv Y., Zhou Z., Cao F. A novel deep learning algorithm for incomplete face recognition: Low-rank-recovery network. Neural Networks, Vol. 94, 115–124 (2017).

5. Yamashita R., Nishio M., Do R.K., Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging, Vol. 9, Issue 4, 611–629 (2018).

6. Diamantopoulou M.J., Antonopoulos V.Z., Papamichail D.M. Cascade Correlation Artificial Neural Networks for Estimating Missing Monthly Values of Water Quality Parameters in Rivers. Water Resources Management, Vol. 21, Issue 3, 649–662 (2007).

8. Zhang Q., Yang L.T., Chen Z., Li P. A survey on deep learning for big data. Information Fusion, Vol. 42, 146–157 (2018).

9. Liu W., Wang Z., Liu X., Zeng N., Liu Y., Alsaadi F.E. A survey of deep neural network architectures and their applications. Neurocomputing, Vol. 234, 11–26 (2017).

10. Wu Z., Pan S., Chen F., Long G., Zhang C., Yu P.S. (2019). A Comprehensive Survey on Graph Neural Networks. ArXiv, abs/1901.00596.

11. Chandra B., Sharma R.K. On improving recurrent neural network for image classification. 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, 1904–1907 (2017).

12. Marakhimov A.R., Khudaybergenov K.K. One approach to the synthesis of structure of neural networks in problems of classification. International Journal of Computing. Vol. 19, Issue 1, 34–41 (2020).

13. Marakhimov A.R., Khudaybergenov K.K. Convergence analysis of feedforward neural networks with backpropagation. Bulletin of National University of Uzbekistan: Mathematics and Natural Sciences: Vol. 2, Issue 2, 77–93 (2019).

14. Yusupbekov N.R., Marakhimov A.R., Igamberdiev H.Z., Umarov Sh.X. An adaptive fuzzy-logic traffic control system in conditions of saturated transport stream. Scientific World Journal, Vol. 1, 21–33 (2016).

15. Zhixiang Ch., Feilong C. The approximation operators with sigmoidal functions. Computers & Mathematics with Applications, Vol. 58, Issue 4, 758–765 (2009).

16. Ren S., Cao X., Wei Y., Sun J. Face alignment at 3000 fps via regressing local binary features. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, U.S.A, 1685–1692 (2014).

17. Phillips P.J., Wechsler H., Huang J., Rauss P.J. The FERET database and evaluation procedure for face-recognition algorithms. Image Vis. Comput., Vol. 16, Issue 5, 295–306 (1998).

18. Grgic M., Delac K., Grgic S. SCface - surveillance cameras face database. Multimedia Tools and Applications Journal, Vol. 51, No. 3, 863–879 (2011).

19. Simonyan K., Zisserman A. Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv:1409.1556.

20. Girshick R., Donahue J., Darrell T., Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, U.S.A, 580–587 (2014).

21. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in neural information processing systems, Harrahs and Harveys, Lake Tahoe, 1097–1105 (2012).

22. Gumus E., Kilic N., Sertbas A. Evaluation of face recognition techniques using PCA, wavelets and SVM. Expert Systems with Applications, Vol. 37, Issue 9, 6404–6408 (2010).

23. Agarwal M., Agrawal H., Jain N., Kumar M. Face recognition using principle component analysis, eigenface and neural network. Proceedings of the International Conference on Signal Acquisition and Processing, Bangalore, 310–314 (2010).

24. Yang J., Zhang D., Frangi A., Yang J. Two-dimensional PCA a new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, Issue 1, 131–137 (2004).

25. Taigman Y., Yang M., Ranzato M., Wolf L. Deepface: Closing the gap to human-level performance in face verification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, U.S.A, 1701–1708 (2014).

26. Sun Y., Wang X., Tang X. Deep learning face representation from predicting 10,000 classes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, U.S.A, 1891–1898 (2014).

27. Sun Y., Wang X., Tang X. Hybrid deep learning for face verification. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia, 1489–1496 (2013).

28. Marakhimov A. R., Khudaybergenov K. K. A fuzzy MLP approach for identification of nonlinear systems. Contemporary problems in mathematics and physics, CMFD, 65, no. 1, Peoples’ Friendship University of Russia, M., 44–53 (2019). (DOI: 10.22363/2413-3639-2019-65-1-44-53).

Recommended Citation

Khudaybergenov, Kabul (2020) "Choosing the structure of convolutional neural networks for face recognition," Bulletin of National University of Uzbekistan: Mathematics and Natural Sciences: Vol. 3: Iss. 1, Article 2.
DOI: https://doi.org/10.56017/2181-1318.1050