Learning-based imaging through scattering media
Learning-based imaging through scattering media
复制标题
DOI：
10.1364/oe.24.013738
复制
发表时间：
2016-06-27
期刊：
影响因子：
3.8
通讯作者：
Tanida, Jun
中科院分区：
文献类型：
--
作者：
Horisaki, Ryoichi;Takagi, Ryosuke;Tanida, Jun
提出了一种基于机器学习的散射介质单次成像方法。通过学习大量的训练目标-散斑对，基于非线性回归算法计算逆散射过程。在实验演示中，散射板之间的多层相位物体的重建从强度测量。我们的方法使无模型传感，它是没有必要知道的传感过程/模型。(C)2016美国光学学会
We present a machine-learning-based method for single-shot imaging through scattering media. The inverse scattering process was calculated based on a nonlinear regression algorithm by learning a number of training object-speckle pairs. In the experimental demonstration, multi-layer phase objects between scattering plates were reconstructed from intensity measurements. Our approach enables model-free sensing, where it is not necessary to know the sensing processes/models. (C) 2016 Optical Society of America