文献知网节
  • 记笔记

A Method for Single Image Phase Unwrapping based on Generative Adversarial Networks

Cong LiYong TianJiandong Tian

College of Physics and Optoelectronic Engineering,Shenzhen University

摘要:Phase unwrapping technology plays an important role in phase measurement profilo metry.The unwrapping results directly affect the measurement accuracy.With the develop ment of deep learning theory,it is opening a new direction to phase unwrapping algorith m.In this paper,a new neural net work model based on an improved generation adversarial network(iGA N) is proposed for phase unwrapping.Co mpared with traditional methods,it can effectively suppress the influence of noise such as shadows,and does not need any referenced grating information.In addit ion,it can realize the phase unwrapping with a single image.Specifically,the algorith m is verified by the three-dimensional reconstruction with structured light based on the simulat ion data.The results indicate that the proposed method can successfully unwrap the phase via a single image.It also can well suppress the influence of frequency and shadows.
会议名称:

2019第十一届数字图像处理国际会议

会议时间:

2019-05-10

会议地点:

中国广东广州

  • 专辑:

    信息科技

  • 专题:

    计算机软件及计算机应用; 自动化技术

  • DOI:

    10.26914/c.cnkihy.2019.007682

  • 分类号:

    TP18;TP391.41

  • 手机阅读
    即刻使用手机阅读
    第一步

    扫描二维码下载

    "移动知网-全球学术快报"客户端

    第二步

    打开“全球学术快报”

    点击首页左上角的扫描图标

    第三步

    扫描二维码

    手机同步阅读本篇文献

  • CAJ下载
  • PDF下载

下载手机APP用APP扫此码同步阅读该篇文章

下载:7 页码:906-912 页数:7 大小:587k

引文网络
  • 参考文献
  • 引证文献
  • 共引文献
  • 同被引文献
  • 二级参考文献
  • 二级引证文献
  • 批量下载
相关推荐
  • 相似文献
  • 读者推荐
  • 相关基金文献
  • 相关法规
  • 关联作者
  • 相关视频