计算机与现代化

• 图像处理 • 上一篇    下一篇

基于高低维度特征融合的双通道卷积神经网络

  

  1. (广东工业大学信息工程学院,广东广州510006)
  • 收稿日期:2018-08-15 出版日期:2019-01-03 发布日期:2019-01-04
  • 作者简介:文元美(1968-),女,湖北荆州人,广东工业大学信息工程学院副教授,博士,研究方向:智能信息处理; 罗志鹏(1993-),男,广东韶关人,硕士研究生,研究方向:物体识别,深度学习; 凌永权(1973-),男,香港人,教授,博士,研究方向:最优信号处理与时频分析。
  • 基金资助:
    国家自然科学基金资助项目(61372173, 61671163)

Double Channel CNN Based on High & Low Dimensions Feature Fusion

  1. (School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China)
  • Received:2018-08-15 Online:2019-01-03 Published:2019-01-04

摘要: 为了充分利用图像中所隐藏的特征信息,提出将低级维度特征融合在全连接层,构建出融合了高低级维度特征的双通道卷积神经网络。首先构建一个传统的双通道卷积神经网络,在两通道上设置不同大小的卷积核,将双通道的池化层分别连接到全连接层,同时将两通道卷积神经网络的第一池化层提取的特征也直接送到全连接层,使提取得到的初级和高级特征图在全连接层上进行融合,融合后的数据输入到Softmax分类器进行分类。不同算法在fashion-mnist和CIFAR-10数据库上的对比仿真结果表明,本文模型获得了较高的分类准确率。

关键词: 特征融合, 双通道卷积神经网络, 卷积核, 池化层

Abstract: In order to make full use of the feature information hidden in the image, this paper proposes to fusion the low latitude feature in fully connected layer, then constructs a double-channel convolutional neural network with the high-low level latitude feature. First, we construct a traditional double-channel convolutional neural network, and then set different sizes of convolution kernel on each channel, connect the double-channel CNN pooling layer to the full connection layer, at the same time, the features extracted from the first layer of the two channel convolution neural network are also directly transmitted to the fully connected layer, and this allows the extracted primary and advanced feature maps to be fused on the full link layer. Finally, the fusion data is input to the Softmax classifier to classify.  Simulation results of different algorithms on fashion-mnist and CIFAR-10 databases show that this model obtains higher classification accuracy.

Key words: feature fusion, double-channel convolutional neural network, convolution kernel, pooling layer

中图分类号: