A deep convolutional neural wavelet network to supervised Arabic letter image classification

Abstract

In this paper, a new approach to supervised image classification is suggested. It's conducted by the combination of two techniques of learning: the wavelet network and the deep learning. This new approach consists of performing the classification of one class versus all the other classes of the dataset by the reconstruction of a convolutional deep neural wavelet network. This network is obtained using a series of stacked auto-encoders and a linear classifier. Finally, a local contrast normalization and an intelligent pooling are applied to our network. The experimental test of our approach performed on Arabic Printed Text Image (APTI) dataset demonstrates that our model is remarkably efficient for image classification compared to a known classifier.