Author:
Xu Ke,Long Wenhan,Sun Yuan,Lin Yichao
Abstract
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.
Subject
General Physics and Astronomy
Reference12 articles.
1. Imagenet classification with deep convolutional neural networks;Krizhevsky,2012
2. A unified approach to transfer learning of deep neural networks with applications to speaker adaptation in automatic speech recognition;Huang;Neurocomputing,2016
3. Distributed representations of words and phrases and their compositionality;Mikolov,2013
4. MiRTDL: a deep learning approach for miRNA target prediction;Cheng;IEEE/ACM Trans. Comput. Biology Bioinform,2016
5. Deep learning in neural networks: an overview;Schmidhuber;Neural Networks,2015
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献