Convolutional Neural Networks with Fused Layers Applied to Face Recognition A. R. Syafeeza * , ‡ , M. Khalil-Hani † , § , S. S. Liew † ,¶ and R. Bakhteri † ,|| * FKEKK, Universiti Teknikal Malaysia Melaka Hang Tuah Jaya, 76100 Durian Tunggal Melaka, Malaysia † VeCAD Research Laboratory Faculty of Electrical Engineering Universiti Teknologi Malaysia 81310 Skudai, Johor, Malaysia ‡ syafeeza@utem.edu.my § khalil@fke.utm.my ¶ gladion89@live.com || rabiabakhteri@utm.my Received 28 December 2013 Revised 5 April 2015 Published 14 September 2015 In this paper, we propose an e®ective convolutional neural network (CNN) model to the problem of face recognition. The proposed CNN architecture applies fused convolution/ subsampling layers that result in a simpler model with fewer network parameters; that is, a smaller number of neurons, trainable parameters, and connections. In addition, it does not require any complex or costly image preprocessing steps that are typical in existing face rec- ognizer systems. In this work, we enhance the stochastic diagonal Levenberg–Marquardt al- gorithm, a second-order back-propagation algorithm to obtain faster network convergence and better generalization ability. Experimental work completed on the ORL database shows that a recognition accuracy of 100% is achieved, with the network converging within 15 epochs. The average processing time of the proposed CNN face recognition solution, executed on a 2.5 GHz Intel i5 quad-core processor, is 3 s per epoch, with a recognition speed of less than 0.003 s. These results show that the proposed CNN model is a computationally e±cient archi- tecture that exhibits faster processing and learning times, and also produces higher recognition accuracy, outperforming other existing work on face recognizers based on neural networks. Keywords: Convolutional neural network; face recognition; back-propagation; neural network learning; cross-validation. 1. Introduction Much research has been done on face recognition problems over the past few decades; however, it remains a challenging task. This is due to the fact that the performance of the automatic face recognition system is greatly a®ected by changes in illumination, angles of faces, and variations in poses, occlusions, and facial expressions. In general, International Journal of Computational Intelligence and Applications Vol. 14, No. 3 (2015) 1550014 (19 pages) # . c Imperial College Press DOI: 10.1142/S1469026815500145 1550014-1 Int. J. Comp. Intel. Appl. 2015.14. Downloaded from www.worldscientific.com by UNIVERSITI TEKNOLOGI MALAYSIA on 04/26/16. For personal use only.