The week's pick
Random Articles
Reseach Article
Improving the Neural Network Training for Face Recognition using Adaptive Learning Rate, Resilient Back Propagation and Conjugate Gradient Algorithm
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 34 - Number 2 |
| Year of Publication: 2011 |
| Authors: Hamed Azami, Saeid Sanei, Karim Mohammadi |
10.5120/4072-5859
|
Hamed Azami, Saeid Sanei, Karim Mohammadi . Improving the Neural Network Training for Face Recognition using Adaptive Learning Rate, Resilient Back Propagation and Conjugate Gradient Algorithm. International Journal of Computer Applications. 34, 2 ( November 2011), 22-36. DOI=10.5120/4072-5859
Abstract
Face recognition is a method for verifying or identifying a person from a digital image. In this paper an approach for classifying images based on discrete wavelet transform (DWT) and neural network (NN) has been suggested. In the proposed approach, DWT decomposes an image into images with different frequency bands. An NN is a trainable and dynamic system which can acceptably estimate input-output functions. Although the basic BP has been the most popular learning algorithm throughout all NNs applications and can be used as estimator, detector or classifier. It usually requires a very long training time. To overcome the problem, we propose several high performance algorithms that can converge few times faster than the algorithm used previously (basic BP). In this paper, the BP with adaptive learning rate, resilient back propagation (RPROP), and conjugate gradient algorithm are used to train an MLP. The simulation results show the clear superiority of the proposed method by ORL face databases.
References
- M. R. M. Rizk and A. Taha, “Analysis of neural networks for face recognition systems with feature extraction to develop an eye localization based method”, pp. 847-850, 2002.
- J. Daugman, "Face and gesture recognition: overview”. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 675-676, July 1997.
- L. Wiskott, J. Fellous, N. Kruger and C. Malsburg, “Face recognition by elastic bunch graph matching”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 775-779, 1997.
- M. Firdaus, “Face recognition using neural networks”, International Conference on Intelligent System (ICIS), CD-ROM, 2005.
- . M. Firdaus, “Dimensions reductions for face recognition using principal component analysis”, Proc. 11th International Symp artificial life and robotics (AROB 11th 06), CD-ROM 2006.
- L. sufen and G. junying, “Face recognition algorithm based on Local wavelet transform and DCT”, vol. 22, no. 1, pp. 205-208, 2006.
- Y. A. Georghiades, P. Belhumeur and D. Kriegman, “From few to many: illumination cone models for face recognition under variable lighting and pose” IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 643-660, 2001.
- P. J. Phillips, P. J. Flynn, T. Scruggs, K. W. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min and W. Worek, “Overview of the face recognition grand challenge,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 947-954, 2005.
- M. Ghazel, “Adaptive fractal and wavelet image denoising”, Waterloo, Ontario, Canada, 2004.
- M. R. Mosavi, “GPS receivers timing data processing using neural networks: optimal estimation and errors modeling”, Journal of Neural Systems, vol. 17, no. 5, pp. 383-393, 2007.
- M. R. Mosavi, “Precise real-time positioning with a low cost GPS engine using neural networks”, Journal of Survey Review, vol.39, no. 306, pp. 316-327, 2007.
- C. Igel and M. Husken, “Empirical evaluation of the improved RPROP learning algorithms”, Neurocomputing, vol. 50, pp. 105–123, 2003.
- F. Paulin and A. Santhakumaran, “Classification of breast cancer by comparing back propagation training algorithms”, International Journal on Computer Science and Engineering, vol. 3, no. 1, pp. 327-332, 2011.
- D. L. Donoho, “Nonlinear wavelet methods for recovery of signals, densities, and spectra from indirect and noisy data”, in Proceeding. of Symposia in Applied Mathematics, vol. 47, pp. 173-205, 1993.
- M. R. Mosavi and H. Azami, “Applying neural network ensembles for clustering of GPS satellites” International Journal of Geoinformatics, (accepted).
- D. J. Jwo and C. C. Lai, “Neural network-based GPS GDOP approximation and classification”, Journal of GPS Solutions, vol. 11, no. 1, pp. 51-60, 2007.
- I. Ahmad, M. A. Ansari and S. Mohsin, “Performance comparison between backpropagation algorithms applied to intrusion detection in computer network systems”, International Conference on Neural Networks, pp. 231-236, 2008.
- P. A. Mastorocostas, “Resilient back propagation learning algorithm for recurrent fuzzy neural networks”, Electronics Letters, vol. 40, no. 1, 2004.
- K. Gupta and S. Kang, “Implementation of resilient backpropagation & fuzzy clustering based approach for finding fault prone modules in open source software systems” International Journal of Research in Engineering and Technology (IJRET), vol. 1, no. 1, pp. 38-43, 2011.
Index Terms
Keywords