0.8% Nyquist computational ghost imaging via non-experimental deep learning
0.8% Nyquist computational ghost imaging via non-experimental deep learning
复制标题
DOI：
10.1016/j.optcom.2022.128450
复制
发表时间：
2021-08
影响因子：
2.4
通讯作者：
Hao-Liang Song;Xiaoyu Nie;Hairong Su;Hui Chen;Yu Zhou;Xingchen Zhao;Tao Peng;M. Scully
中科院分区：
文献类型：
--
作者：
Hao-Liang Song;Xiaoyu Nie;Hairong Su;Hui Chen;Yu Zhou;Xingchen Zhao;Tao Peng;M. Scully
我们提出了一个基于深度学习和定制粉红噪声散斑图案的计算鬼成像框架。这项工作中的深度神经网络可以学习传感模型并提高图像重建质量，仅通过模拟训练。在不同的噪声条件下，在多个采样率下，比较了常规计算鬼像成像结果、基于深度学习的白色和粉红噪声鬼像成像结果。实验分别用数字、英文字母和汉字进行。我们表明，即使对象在训练数据集之外，该方案也可以以低至0.8%的采样率提供高质量图像，并且对噪音环境具有鲁棒性。该方法可以应用于广泛的应用，包括那些需要低采样率，快速重建，或经历强噪声干扰。
We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns. The deep neural network in this work, which can learn the sensing model and enhance image reconstruction quality, is trained merely by simulation. The conventional computational ghost imaging results, deep learning-based ghost imaging results with white and pink noise are compared under multiple sampling ratios at different noise conditions. The experiments are done with digits, English letters, and Chinese characters. We show that the proposed scheme can provide high-quality images with a sampling ratio as low as 0.8% even when the object is outside the training dataset and robust to noisy environments. The method can be applied to a wide range of applications, including those requiring a low sampling ratio, fast reconstruction, or experiencing strong noise interference.