5. Face Recognition using PCA and Multilayer Feedforward Neural Networks
This paper presents a report on various phases of our proposed face recognition system. It covers the following topics. The description and structure of image data, analysis ofimage features, analysis of methods for feature processing and extraction, suchas principal components analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA), analysis of recognition methods, such asmulti-class and pair-wise neural networks (MCNN & PWNN), implementation and designing of recognition methods. Finally the report demonstrates the various experimental results on our face recognition system and concludes on the basis of these experimental outcomes. As a part of future works an implementation of 3D face recognition system is suggested.
Keywords: Face Recognition, PCA,ICA, LDA, ANN, MCNN, PWNN, Gradient Descent, feed-forward, multi-layer,back-propagation, mse, Levenberg-Marquardt
*Corresponding author E-mail: firstname.lastname@example.org
EUJAST © All Rights Reserved