CASIA OpenIR  > 类脑智能研究中心
GAN based Sample Simulation for SEM-Image Super Resolution
Yang MK(杨茂柯)1,2; Li Guoqing(李国庆)1; Shu Chang(舒畅)1,2; Pan Zhao(赵盼)1; Hua Han(韩华)1,2
2017-10
会议名称The Chinese Conference on Computer Vision
会议日期2017-10-12
会议地点Tianjin, China
摘要We propose to employ image super resolution to  accelerate collection speed of scanning electric microscopes(SEM). This process can be done by collecting images in lower resolution, and then upscale the collected images with image super-resolution algorithms. However, because of physical factors, SEM-images collected in different resolution changed not only in their scale, but also with noise level and physical distortion. Consequently, it is hard to obtain training dataset. In order to solve this problem, we designed a generative adversarial network (GAN) to fit the noise of SEM images, and then generate realistic training samples from high resolution SEM data. Finally,  a fully convolutional network have been designed to perform image super-resolution and image denoise at the same time. This pipeline works well on our SEM-image dataset.
关键词Image Super Resolution Generative Adversarial Network Scanning Electric Microscope
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/21511
专题类脑智能研究中心
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Yang MK,Li Guoqing,Shu Chang,et al. GAN based Sample Simulation for SEM-Image Super Resolution[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Paper0367.pdf(4248KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yang MK(杨茂柯)]的文章
[Li Guoqing(李国庆)]的文章
[Shu Chang(舒畅)]的文章
百度学术
百度学术中相似的文章
[Yang MK(杨茂柯)]的文章
[Li Guoqing(李国庆)]的文章
[Shu Chang(舒畅)]的文章
必应学术
必应学术中相似的文章
[Yang MK(杨茂柯)]的文章
[Li Guoqing(李国庆)]的文章
[Shu Chang(舒畅)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Paper0367.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。