Face Recognition Based on DWT Feature for CNN
Bendjillali Ridha Ilyas, Mohammed Beladgham, Khaled Merit · 2019
In the last decade, facial recognition techniques are considered the most important fields of research in biometric technology. In this research paper, we present a Face Recognition (FR) system based on the Viola-Jones face detection algorithm, discrete wavelet transform (DWT), facial image enhancement using histogram equalization (HE) algorithm, and deep convolution neural network. Extraction results of facial features using DWT are used directly to train the CNN network, this network composed of three convolution layers, two pooling layers, a fully-connected layer, and one softmax regression layer. The face recognition rate based on this network is 99.85% and 99.80%. The face recognition rate of the ORL face database and the AR face database based on this network achieved 99.85% and 99.80% respectively.