###
上海电力大学学报:2021,37(4):402-406
本文二维码信息
码上扫一扫!
基于DCGANs的二维页岩图像重构方法
(1.上海电力大学 计算机科学与技术学院;2.上海第二工业大学 工学部)
2D Shale Image Reconstruction Based on DCGANs
(1.School of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China;2.College of Engineering, Shanghai Polytechnic University, Shanghai 201209, China)
摘要
图/表
参考文献
本刊相似文献
All Journals 相似文献
All Journals 引证文献
本文已被:浏览 847次   下载 420
投稿时间:2020-02-14    
中文摘要: 利用现代物理实验技术可以有效获取真实的页岩孔隙图像,但是成本高昂。采用数值模拟方法重构页岩,提出了利用深度卷积生成对抗网络重构页岩图像,且该对抗网络允许隐式描述二维图像数据集所表示的概率分布。实验结果证明,该方法能够生成与真实样本更相似的页岩二维图像。
Abstract:Although modern physical experiments can effectively obtain real shale images of pore spaces,the cost is quite high.Numerical simulation method is used.The reconstruction method of shale images using deep convolutional generative adversarial networks that allow implicit description of the probability distribution represented by a two-dimensional image dataset is proposed.Experimental results show that this method can generate two-dimensional shale images more similar to real samples than filtersim method.
文章编号:20214016     中图分类号:TP399    文献标志码:
基金项目:国家自然科学基金(41672114,41702148)。
引用文本:
张挺,王先武,杜奕,等.基于DCGANs的二维页岩图像重构方法[J].上海电力大学学报,2021,37(4):402-406.
ZHANG Ting,WANG Xianwu,DU Yi,et al.2D Shale Image Reconstruction Based on DCGANs[J].Journal of Shanghai University of Electric Power,2021,37(4):402-406.