Mohamed HANI KHALIL, Syafeeza AHMAD RADZI, Rabia BAKHTERI, Shan Sung LIEW

Gender classification: a convolutional neural network approach

An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, we replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of SUMS and AT&T. We achieve classification accuracies of 98.75% and 99.38% on the SUMS and AT&T databases, respectively. The neural network is able to process and classify a 32 × 32 pixel face image in less than 0.27 ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition.

PDF

___

[1] Tivive FHC, Bouzerdoum A. A gender recognition system using shunting inhibitory convolutional neural networks. In: International Joint Conference on Neural Networks; 2006; Vancouver, Canada. New York, NY, USA: IEEE. pp. 53365341.
[2] Khalajzadeh H, Mansouri M, Teshnehlab M. Face recognition using convolutional neural network and simple logistic classifier. Stud Comp Intell 2013; 223: 197207.
[3] Strigl D, Kofler K, Podlipnig S. Performance and scalability of GPU-based convolutional neural networks. In: 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing; 1719 February 2010; Pisa, Italy. New York, NY, USA: IEEE. pp. 317324.
[4] LeCun Y, Bottou L, Bengio Y, Haffner. P. Gradient-based learning applied to document recognition. P IEEE 1998; 86: 22782324.
[5] Duffner S. Face Image Analysis with Convolutional Neural Networks. Munich, Germany: GRIN Verlag, 2009.
[6] Fan J, Wei X, Ying W, Yihong G. Human tracking using convolutional neural networks. IEEE T Neural Networ 2010; 21: 16101623.
[7] Lian HC, Lu BL. Multi-view gender classification using local binary patterns and support vector machines. Lect Notes Comput Sc 2006; 3972: 202209.
[8] Nazir M, Ishtiaq M, Batool A, Jaffar MA, Mirza AM. Feature selection for efficient gender classification. In: Proceedings of the 11th WSEAS International Conference; 2010. pp. 7075.
[9] Golomb BA, Lawrence DT, Sejnowski TJ. SEXNET: A neural network identifies sex from human faces. In: Proceedings of NIPS; 1990. pp. 572579.
[10] Sun Z, Yuan X, Bebis G, Louis SJ. Neural-network-based gender classification using genetic search for eigenfeature selection. In: Proceedings of the 2002 International Joint Conference on Neural Networks; 1217 May 2002; Honolulu, HI, USA. New York, NY, USA: IEEE. pp. 24332438.
[11] Dawwd SA, Mahmood BS. Video Based Face Recognition Using Convolutional Neural Network. Rijeka, Croatia: InTech, 2011.
[12] Simard PY, Steinkraus D, Platt JC. Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis. Redmond, WA, USA: Microsoft Research, 2003.
[13] Mamalet F, Garcia C. Simplifying ConvNets for fast learning. In: Villa A, Duch W, Erdi P, Masulli F, Palm G, ´ editors. Artificial Neural Networks and Machine Learning ICANN 2012. Vol. 7553. Berlin, Germany: Springer, 2012, pp. 5865.
[14] Ji S, Wei X, Ming Y, Kai Y. 3D convolutional neural networks for human action recognition. IEEE T Patten Anal 2013; 35: 221231.
[15] Mamalet F, Roux S, Garcia C. Embedded facial image processing with convolutional neural networks. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems; 30 May2 June 2010; Paris, France. New York, NY, USA: IEEE. pp. 261264.
[16] LeCun Y, Bottou L, Orr G, M¨uller KR. Efficient BackProp. Lect Notes Comp Sc 2002; 1524: 950.
[17] Khan MNA, Qureshi SA, Riaz N. Gender classification with decision trees. International Journal of Signal Processing, Image Processing and Pattern Recognition 2013; 6: 165176.
[18] Majid A, Khan A, Mirza AM. Gender classification using discrete cosine transformation: a comparison of different classifiers. In: 7th International Multi Topic Conference; 9 December 2003; Islamabad, Pakistan. New York, NY, USA: IEEE. pp. 5964.
[19] Jiao Y, Yang J, Fang Z, Xie S, Park D. Comparing studies of learning methods for human face gender recognition. Lect Notes Comp Sc 2012; 7701: 6774.
[20] Basha AF, Jahangeer GSB. Face gender image classification using various wavelet transform and support vector machine with various kernels. International Journal of Computer Science Issues 2012; 9: 150157.
[21] Berbar M. Three robust features extraction approaches for facial gender classification. Visual Comput 2013; 30: 1931.