A deep stacked wavelet auto-encoders to supervised feature extraction to pattern classification

Abstract

The major issue in pattern classification is in the extraction of features in the training phase. The focus of this work is on combining the ability of wavelet networks and the deep learning techniques to propose a new supervised feature extraction method to pattern classification. This new approach allows the classification of all classes of the dataset by the reconstruction of a Deep Stacked wavelet Auto-Encoder. This Network is obtained after a series of wavelet Auto-Encoders followed by a Softmax classifier at the last layer. Finally, a fine-tuning is applied for the improvement of our result using a back propagation algorithm. Our approach is tested with different image datasets which are the COIL-100, the APTI and the ImageNet datasets and is also tested with two other audio corpuses that contain Arabic words and French words. The experimental test demonstrates the efficiency of our network for image and audio classification compared to other methods.