测试技术学报2018，Vol.32Issue(3)：201-206,6.DOI:10.3969/j.issn.1671-7449.2018.03.004
基于卷积神经网络的多波段融合图像彩色化方法
Multiband Image Fusion Results Colorization Based on Convolution Neural Network
摘要
Abstract
In order to improve the observation effect of human eyes on multi-band fusion image in gray space,a multi band fusion image colorization method based on deep convolution neural network (DCNN) is proposed.Firstly,the color fusion results which are made of color migration and pseudo-color fusion are added into the training set;secondly,the training images are converted to YUV color space;then the convolution neural network is constructed,and the Y channel image is input at the input end,the UV channel image is taken as the target training network,so that the UV channel can be generated automati-cally according to the input;finally,the gray level fusion results are input to the trained network as Y channel,and the output UV channel and input are converted to RGB space to obtain the color fusion re-sult.The experimental results show that DCNN can automatically color the gray fusion results.The method is simple and easy,and the color is more convenient to be observed.关键词
图像融合/深度学习/彩色化/卷积神经网络/多波段探测Key words
image fusion/deep learning/colorization/convolution neural network/multiband detection分类
信息技术与安全科学引用本文复制引用
韩泽,蔺素珍,黄福升,赵竞超,刘震..基于卷积神经网络的多波段融合图像彩色化方法[J].测试技术学报,2018,32(3):201-206,6.基金项目
山西省应用基础研究资助项目(201701D121062) （201701D121062）
中北大学第十四届研究生科技立项资助项目(20171443) （20171443）
