###
计算机系统应用:2020,29(5):196-201
本文二维码信息
码上扫一扫!
基于孪生卷积神经网络的图像融合
(长安大学 信息工程学院, 西安 710064)
Image Fusion Based on Siamese Convolutional Neural Network
(School of Information Engineering, Chang'an University, Xi'an 710064, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 110次   下载 300
投稿时间:2019-09-27    修订日期:2019-10-22
中文摘要: 传统的图像融合算法多有计算复杂程度高、不能有效提取图像纹理等不足,为了弥补以上传统算法,提出了一种基于孪生卷积神经网络(Siamese Convolutional Neural Network,Siamese CNN)的图像融合方法.首先,用孪生卷积神经网络生成一个权重图,该权重图包含了来自两个待融合图像的全部像素信息.然后,用图像金字塔对像素以多尺度的方式进行融合,并且采用了局部相似性策略自适应调整分解系数的融合模式.最后,和现存的几种图像融合的方法进行了对比.实验证明,该方法有较好的融合效果,具有一定的可实用性.
Abstract:Traditional image fusion algorithms have many shortcomings, such as high computational complexity and inability to effectively extract image texture. To compensate these shortcomings of above traditional algorithms, an image fusion method is proposed based on the Siamese Convolutional Neural Network (Siamese CNN). First, we use the Siamese CNN to generate a weight graph, which contains all pixel information from the two images to be fused. Then, the image pyramid is fused in a multi-scale way, and the local similarity strategy is adopted to adjust the decomposition coefficient adaptively. Finally, several existing image fusion methods are compared. Experimental results show that the proposed method has sound fusion effect and is practical to some extent.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
杨雪,郑婷婷,戴阳.基于孪生卷积神经网络的图像融合.计算机系统应用,2020,29(5):196-201
YANG Xue,ZHENG Ting-Ting,DAI Yang.Image Fusion Based on Siamese Convolutional Neural Network.COMPUTER SYSTEMS APPLICATIONS,2020,29(5):196-201

用微信扫一扫

用微信扫一扫