Face identification using back-propagation adaptive multiwavenet

Abstract EN

Face Identification is an important research topic in the field of computer vision and pattern recognition and has become a very active research area in recent decades.

Recently multiwavelet-based neural networks (multiwavenets) have been used for function approximation and recognition, but to our best knowledge it has not been used for face Identification.

This paper presents a novel approach for the Identification of human faces using Back-Propagation Adaptive Multiwavenet.

The proposed multiwavenet has a structure similar to a multilayer perceptron (MLP) neural network with three layers, but the activation function of hidden layer is replaced with multiscaling functions.

In experiments performed on the ORL face database it achieved a recognition rate of 97.75 % in the presence of facial expression, lighting and pose variations.

Results are compared with its wavelet-based counterpart where it obtained a recognition rate of 10.4 %.

The proposed multiwavenet demonstrated very good recognition rate in the presence of variations in facial expression, lighting and pose and outperformed its wavelet-based counterpart.