• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Liu, Chen (Liu, Chen.) | Li, Xiaoguang (Li, Xiaoguang.) | Zhuo, Li (Zhuo, Li.) | Li, Jiafeng (Li, Jiafeng.) | Zhou, Qingfeng (Zhou, Qingfeng.)

收录:

EI Scopus

摘要:

In the preservation of old movies, there will be various degradations, such as scratches and dust. Although there have been many studies on denoising, those methods have not been effective in the restoration of old movies. In this paper, we propose a novel old film speckle noise removal method, which includes speckle noise detection and an inpainting based speckle noise reduction procedures. The spatiotemporal information is employed in speckle noise detection. Meanwhile, a deep image prior based deep auto-encoder-decoder network is designed to remove the speckle noise. Experiment results show that the proposed method can achieve better results compared with other methods. © 2018 IEEE.

关键词:

Biomedical engineering Decoding Learning systems Motion pictures Network coding Speckle

作者机构:

  • [ 1 ] [Liu, Chen]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 2 ] [Li, Xiaoguang]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 3 ] [Zhuo, Li]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 4 ] [Li, Jiafeng]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 5 ] [Zhou, Qingfeng]School of Computer and Information, Hefei University of Technology, Hefei, China

通讯作者信息:

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

年份: 2018

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次: 2

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:2152/2922039
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司