摘要
深度学习方法在图像的特征提取方面具有优势。针对传统特征提取方法需要先验知识的不足,提出一种自动编码器(Auto Encoder)与卷积神经网络(convolutional neural network,CNN)相结合的深度学习特征提取方法。该方法给Auto Encoder加入快速稀疏性控制,据此对图像训练出基本构件,并初始化CNN的卷积核;同时,给CNN加入了滤波机制,使输出特征保持稀疏性。实验结果表明,在Minist手写数字库和Yale人脸库的识别效果上,提出的特征提取方法均取得了较好的结果,实验进一步通过交叉验证T检验指出,引入滤波机制的特征提取模型优于没有采用滤波机制的模型。
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 Auto Encoder and convolutional neural network( CNN). The method introduced a fast sparsity control technique to Auto Encoder and utilized Auto Encoder to train the basic elements of image and initialized the convolution kernel of CNN. Meanwhile,the algorithm added filtering mechanism to the CNN to keep the sparsity of output characteristics. The results of experiments point out that this method achieves 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.
出处
《计算机应用研究》
CSCD
北大核心
2017年第12期3839-3843,3847,共6页
Application Research of Computers
基金
国家自然科学基金资助项目(60975021)
教育部-中国移动科研基金项目(MCM20121061
MCM20121041)
关键词
深度学习
卷积神经网络
自动编码器
滤波
稀疏控制
deep learning(DL)
convolutional neural network
Auto Encoder
filter
sparse control
