Title :
Artificial neural network-based face recognition
Author :
Reda, A. ; Aoued, B.
Author_Institution :
Dept. of Comput. Sci., Sidi Bel-Abbes Univ., Algeria
Abstract :
This document demonstrates how a face recognition system can be designed with artificial neural network. Note that the training process did not consist of a single call to a training function. Instead, the network was trained several times on various input ideal and noisy images, the images that contents faces. In this case training a network on different sets of noisy images forced the network to learn how to deal with noise, a common problem in the real world.
Keywords :
backpropagation; face recognition; neural nets; artificial neural network; face recognition system; noisy images; training process; Artificial neural networks; Design engineering; Distributed information systems; Face detection; Face recognition; Humans; Image databases; Laboratories; Neural networks; Neurons;
Conference_Titel :
Control, Communications and Signal Processing, 2004. First International Symposium on
Conference_Location :
Hammamet, Tunisia
Print_ISBN :
0-7803-8379-6
DOI :
10.1109/ISCCSP.2004.1296323