摘要
针对Le Net-5网络模型识别分类准确度问题,提出一种基于深度Gabor卷积神经网络的识别分类方法。在Le Net-5模型的基础上,引入了Gabor层,使用Gabor核作为提取图像特征的卷积核,Gabor卷积核从图像频域的不同尺度、不同方向上提取更多特征。为了避免网络训练中的梯度消失问题,使用Relu函数作为网络中的激活函数。将改进后的模型在MNIST手写体数据集上进行试验,识别正确率达到99. 34%。与支持向量机和卷积神经网络等分类方法作比较,结果表明,改进后的深度Gabor卷积神经网络的具有更高的识别性能。
Aiming at the problem of classification accuracy of LeNet-5 network model,a recognition classification method is proposed based on deep Gabor convolution neural network.On the basis of LeNet-5 model,Gabor layer is introduced,and Gabor kernel is used as the convolution kernel to extract image features,which can extract more features from different scales and directions in image frequency domain.To avoid the problem of gradient disappearance in network training,the Relu function is used as an activation function in the network.The improved model was tested on the MNIST handwritten dataset,and the recognition accuracy was 99.34%.Comparisons with classification methods such as SVM and convolutional neural networks show that the improved Gabor convolution neural network with improved depth has higher recognition performance.
作者
杨景明
周豪腾
杨波
王亚超
魏立新
YANG Jingming;ZHOU Haoteng;YANG Bo;WANG Yachao;WEI Lixin(School of Electrical Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China)
出处
《燕山大学学报》
CAS
北大核心
2018年第5期427-433,共7页
Journal of Yanshan University
基金
河北省高等学校创新团队领军人才培育计划项目(LJRC013)
河北省自然科学基金资助项目(F2016203249)
关键词
卷积神经网络
Gabor卷积核
Relu函数
特征提取
识别分类
convolutional neural network
Gabor convolution kernel
Relu function
feature extraction
recognition classification
作者简介
杨景明(1957-),男,黑龙江齐齐哈尔人,博士,教授,博士生导师,主要研究方向为冶金机械综合自动化、先进控制及工程应用、人工智能与神经网络应用等,Email:yangjm@ysu.edu.cn。
