A novel image feature extraction algorithm based on the fusion AutoEncoder and CNN

Abstract

Deep learning method has very excellent ability of image feature extraction. In order to get rid of disadvantages of traditional methods require a priori knowledge, this paper proposed an image feature extraction algorithm based on the fusion AutoEncoder and convolutional neural networks (CNN). The method introduces a fast sparsity control technique to AutoEncoder and utilizes AutoEncoder to train the basic elements of image and initialize the convolution kernel of CNN. Meanwhile, the algorithm adds filtering mechanism to the CNN network to keep the sparsity of output characteristics. The results of experiments point out that this method has achieved good performance on the Minist handwritten digital library and the Yale face database. Furthermore, the advanced experimental outcomes indicate that the feature extraction model included the filtering technique is more effective than the model without filtering mechanism by using cross-validation with T Test.