• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 图形与图像 • 上一篇    下一篇

基于边缘的双路卷积神经网络及其可视化

李雨冲,闫昭帆,严国萍   

  1. (长安大学信息工程学院,陕西 西安 710064)
     
  • 收稿日期:2018-11-22 修回日期:2019-04-09 出版日期:2019-10-25 发布日期:2019-10-25
  • 基金资助:

    “弘毅长大”研究生科研创新实践项目(2018103,2018109)

An edge-based 2-channel convolutional
neural network and its visualization
 

LI Yu-chong,YAN Zhao-fan,YAN Guo-ping   

  1. (School of Information Engineering,Chang’an University,Xi’an 710064,China)
  • Received:2018-11-22 Revised:2019-04-09 Online:2019-10-25 Published:2019-10-25

摘要:

为提高小尺度复杂图像识别准确率,通过对LeNet-5卷积神经网络并入一个新通道,让其处理与边缘有关的信息。结合两种通道产生的不同特征构造分类器,提出一种基于边缘的双路卷积神经网络,对小尺度复杂数据集进行识别。在包含10类产品数据上分类的结果表明,双路卷积神经网络的识别准确率远高于传统网络。最后通过神经网络可视化算法对双路卷积神经网络进行了可视化分析。

关键词:

Abstract:

In order to improve the recognition accuracy of small-scale complex images, an edge channel is added into LeNet-5 convolutional neural network to process the edge information. By combining the different features generated by two channels to construct a classifier, a 2-channel convolutional neural network is proposed to identify small-scale complex data sets. Classification results on ten types of product data show that the accuracy of the 2-channel convolutional neural network is much higher than that of the traditional network. Finally, the neural network visualization algorithm is adopted to visualize and analyze the 2-channel convolutional neural network.
 

Key words: image pattern recognition, 2-channel convolutional neural network, small-scale complex image, neural network visualization