No Access

HIERARCHICAL STRUCTURE BASED CONVOLUTIONAL NEURAL NETWORK FOR FACE RECOGNITION

Intelligent Systems Laboratory (ISLAB), Faculty of Electrical & Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran

Search for more papers by this author

MOHAMMAD MANSOURI

Intelligent Systems Laboratory (ISLAB), Faculty of Electrical & Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran

Search for more papers by this author

, and

MOHAMMAD TESHNEHLAB

Intelligent Systems Laboratory (ISLAB), Faculty of Electrical & Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran

Search for more papers by this author

https://doi.org/10.1142/S1469026813500181Cited by:17 (Source: Crossref)

Abstract

In this paper, a hierarchical structure based convolutional neural network is proposed to provide the ability for robust information processing. The weight sharing ability of convolutional neural networks (CNNs) is considered as a level of hierarchy in these networks. Weight sharing reduces the number of free parameters and improves the generalization ability. In the proposed structure, a small CNN which is used for feature extractor is shared between the whole input image pixels. A scalable architecture for implementing extensive CNNs is resulted using a smaller and modularized trainable network to solve a large and complicated task. The proposed structure causes less training time, fewer numbers of parameters and higher test data accuracy. The recognition accuracy for recognizing unseen data shows improvement in generalization. Also presented are application examples for face recognition. The comprehensive experiments completed on ORL, Yale and JAFFE face databases show improved classification rates and reduced training time and network parameters.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

G. D. C. Cavalcanti , T. I. Ren and J. F. Pereira , Expert Syst. Appl. 40 , ( 2013 ) . Google Scholar
S. Oha , S. Yooa and W. Pedrycz , Expert Sits. Appl. 40 , 1451 ( 2013 ) . Crossref, Google Scholar
R. M. Makwana , V. K. Thakar and N. C. Chauhan , Int. J. Comput. Intell. Appl. 10 , 313 ( 2011 ) . Link, Google Scholar
S. Karungaru , M. Fukumi and N. Akamatsu , Int. J. Comput. Intell. Appl. 5 , ( 2005 ) . Link, Google Scholar
R. Kong and B. Zhang, A new face recognition method based on fast least squares support vector machine, Int. Conf. Phys. Sci. Technol.22 (2011) pp. 616–621. Google Scholar
X. Fan and B. Verma , Expert Syst. Appl. 36 , 7157 ( 2009 ) . Crossref, Google Scholar
S. C. B. Lo et al. , IEEE Trans. Med. Imag. 21 , 150 ( 2002 ) . Crossref, Google Scholar
Y. H. Hu and J. Hwang , Handbook of Neural Network Signal Processing ( CRC Press , 2002 ) . Google Scholar
A. Gepperth, Object detection and feature base learning by sparse convolutional neural networks, Lecture Notes in Artificial Intelligence 4807 (Springer Verlag, Berlin, 2006), pp. 221–231 . Google Scholar
D. Bouchain, Character recognition using convolutional neural networks, Seminar Statistical Learning Theory, University of Ulm, Germany (2006/2007) . Google Scholar
Y. LeCun et al. , Proc. IEEE 86 , 2278 ( 1998 ) . Crossref, Google Scholar
S. S. Ahranjany, F. Razzazi and M. H. Ghassemian, A very high accuracy handwritten character recognition system for Farsi/Arabic digits using convolutional neural networks, IEEE Fifth Int. Conf. Bio-Inspired Computing: Theories and Applications (BIC-TA) (2010) pp. 1585–1592. Google Scholar
S. Lawrence et al. , IEEE Trans. Neural Netw. 8 , 98 ( 1997 ) . Crossref, Google Scholar
D. Schulz and S. Behnke, Accelerating large-scale convolutional neural networks with parallel graphics multiprocessors, Proc. 20th Int. Conf. Artificial Neural Networks (ICANN'10) (2010) pp. 1–4. Google Scholar
ORL face database, http://www.uk.research.att.com/facedatabase.html . Google Scholar
Yale face database, http://cvc.yale.edu/projects/yalefaces/yalefaces.html . Google Scholar
M. Lyonset al., Coding facial expressions with gabor wavelets, Third IEEE Int. Conf. Automatic Face and Gesture Recognition (1998) pp. 200–205. Google Scholar
B. Fasel, Robust face analysis using convolutional neural networks, 16th Int. Conf. Pattern Recognition (2002) pp. 40–43. Google Scholar
X. Shu , Y. Gao and H. Lu , Pattern Recog. 45 , 1892 ( 2012 ) . Crossref, Google Scholar
S. Duffner, Face image analysis with convolutional neural networks, Doctoral Dissertation, University of Freiburg (2009) . Google Scholar
S. Lawrance, C. L. Giles and A. C. Tsoi, Convolutional neural networks for face recognition, IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR) (1996) pp. 217–222. Google Scholar
S. A. Dawwd and B. S. Mahmood, A reconfigurable interconnected filter for face recognition based on convolution neural network, 4th Int. Design and Test Workshop (IDT) (2009) pp. 1–6. Google Scholar