CNN_Fusion
所属分类:图形图象
开发工具:matlab
文件大小:33964KB
下载次数:85
上传日期:2020-07-05 19:54:02
上 传 者:
Refuel
说明: 基于卷积神经网络的图像融合方法,首次将卷积神经网络应用到图像融合领域。
(The image fusion method based on convolutional neural network is first applied to image fusion.)
文件列表:
boxfilter.m (931, 2013-10-04)
CNN_Fusion.m (7782, 2018-12-24)
guidedfilter.m (957, 2013-10-04)
lowcnn.m (358, 2018-12-24)
maxpooling_s2.m (300, 2016-01-28)
model (0, 2018-12-19)
model\cnnmodel.mat (32429373, 2016-02-03)
results (0, 2018-12-24)
results\clcok_decision.jpg (9702, 2018-12-19)
results\clcok_decision_1.jpg (9725, 2018-12-19)
results\clock.jpg (19851, 2018-12-19)
results\fused_cnn.jpg (24465, 2018-12-19)
results\fused_cnn.tif (818656, 2018-12-19)
results\img1_decision.jpg (15947, 2018-12-19)
results\lowpassfused.jpg (10785, 2018-12-24)
Script.m (348, 2018-12-19)
sourceimages (0, 2018-12-24)
sourceimages\1left.jpg (53193, 2018-12-19)
sourceimages\1right.jpg (52409, 2018-12-19)
sourceimages\children_1.tif (818672, 2016-01-30)
sourceimages\children_2.tif (818656, 2016-01-30)
sourceimages\clock1.tif (167703, 2017-08-21)
sourceimages\clock1_low_pass.jpg (10451, 2018-12-23)
sourceimages\clock2.tif (149501, 2017-08-21)
sourceimages\clock2_low_pass.jpg (10501, 2018-12-23)
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
This package contains the MATLAB code which is associated with the following paper:
Yu Liu, Xun Chen, Hu Peng, Zengfu Wang "Multi-focus image fusion with a deep convolutional neural network", INFORMATION FUSION, vol.36, pp.191-207, 2017.
Edited by Yu Liu.
Usage of this code is free for research purposes only.
Please refer to the above publication if you use this code. Thank you.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
The demo file is Script.m.
The CNN model is learned by Caffe and then converted into a '.mat' file.
Please note that the running time reported in the paper is implemented with C++ using Caffe GPU mode. The results obtained with this MATLAB implementation could be used for comparison with your methods. The computational speed is relatively low using MATLAB (about two minutes on a 3.6GHz CPU).
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Dont hesitate to contact me if you meet any problems when using this code.
Author: Yu Liu
Email: yuliu@hfut.edu.cn; lyuxxz@163.com
Homepage: https://sites.google.com/site/yuliu316316 (English)
http://www.escience.cn/people/liuyu1 (Chinese)
Last update: 8-DEC-2016
近期下载者:
相关文件:
收藏者: