Online Face Recognition

Mohd Azril Aliff , Jusoh (2009) Online Face Recognition. Project Report. UTeM, Melaka,Malaysia. (Submitted)

	PDF (24 Pages) Online_Face_Recognition_Mohd_Azril_Aliff_Bin_Jusoh_TK7882.B56.M39_2009_-_24_Pages.pdf - Submitted Version Download (2MB)
	PDF (Full Text) Online_Face_Recognition_Mohd_Azril_Aliff_Bin_Jusoh_TK7882.B56.M39_2009.pdf - Submitted Version Restricted to Registered users only Download (6MB)

Abstract

This project is to perform the online face recognition by usmg Scaled Conjugate Gradient algorithm (SCG). The SCG algorithm is based upon a class of optimization techniques well known in numerical analysis. The SCG uses second order information from the neural network but requires only N memory usage where N is the number of weights in the network. The SCG in particular trainscg, seen to perform well over a wide variety of problems, particularly for networks with a large number of weight. The SCG algorithm is almost as fast as the Levenberg Marquardt algorithm (LM) on function approximation problems (faster for large network) and is almost as fast as Reselient Bacpropagation algorithm (RP) on pattern recognition problems. Its performance does not degrade as quickly as RP performance does when the error is reduced. The SCG algorithm has relatively modest memory requirements. In this report, the SCG perform well in recognize the face that contains in database and image that captured from webcam.

Actions (login required)

View Item