A Study on Neural Network Training Algorithm for Multiface Detection in Static Images

This paper reports the study results on neural network training algorithm of numerical optimization techniques multiface detection in static images. The training algorithms involved are scale gradient conjugate backpropagation, conjugate gradient backpropagation with Polak-Riebre updates, conjugate gradient backpropagation with Fletcher-Reeves updates, one secant backpropagation and resilent backpropagation. The final result of each training algorithms for multiface detection application will also be discussed and compared.




References:
[1] Zulhadi Zakaria, Nor Ashidi Mat Isa, and Shahrel A. Suandi,
"Combining Skin Color and Neural Network for Multiface Detection in
Static Images," Symposium on Progress in Information &
Communication Technology, Kuala Lumpur, pp. 147-154, 2009.
[2] Zweiri, Y.H., Whidborne, J.F. and Sceviratne, L.D. A Three-term
Backpropagation Algorithm. Neurocomputing. 50: 305-318. 2002.
[3] 10. C.M. Bishop. Neural Networks for Pattern Recognition. Chapter 7,
pp.253-294. Oxford University Press. 1995.
[4] Mathworks Online. Available: http://www. www.mathworks.com, 2009.
[5] Jonathan Richard Shewchuk, An Introduction to the Conjugate Gradient
Method Without the Agonizing Pain, August 1994.
[6] Martin Fodslette Moller. A Scaled Conjugate Gradient Algorithm For
Fast Supervised Learning. Neural Networks, 6:525-533, 1993.
[7] Caltech Image Database. California Institute of Technology. Available:
http://www.vision.caltech.edu/Image_Datasets/faces/ faces.tar, 2007.
[8] Georgia Face Image Database. Georgia Institute of Technology.
Available: http://www.anefian.com/gt_db.zip, 2007.
[9] UCD Color Face Image Database. College of Engineering, Mathematics
and Physical Sciences UCD, Dublin. Available: http://ee.ucd.ie/~prag/.
March, 2007.
[10] Demuth, H., Beale, M. Neural Network Toolbox (Mathworks, Natick,
Massachusetts, 1998).