Hao Jianying, Lin Xiao, Lin Yongkun, Song Haiyang, Chen Ruixian, Chen Mingyong, Wang Kun, Tan Xiaodi
Opt Lett. 2021 Sep 1;46(17):4168-4171. doi: 10.1364/OL.433955.
This paper proposes a lensless phase retrieval method based on deep learning (DL) used in holographic data storage. By training an end-to-end convolutional neural network between the phase-encoded data pages and the corresponding near-field diffraction intensity images, the new unknown phase data page can be predicted directly from the intensity image by the network model without any iterations. The DL-based phase retrieval method has a higher storage density, lower bit-error-rate (BER), and higher data transfer rate compared to traditional iterative methods. The retrieval optical system is simple, stable, and robust to environment fluctuations which is suitable for holographic data storage. Besides, we studied and demonstrated that the DL method has a good suppression effect on the dynamic noise of the holographic data storage system.
本文提出了一种用于全息数据存储的基于深度学习（DL）的无透镜相位检索方法。通过在相位编码数据页和相应的近场衍射强度图像之间训练一个端到端的卷积神经网络，网络模型可以直接从强度图像预测新的未知相位数据页，无需任何迭代。与传统的迭代方法相比，基于DL的相位检索方法具有更高的存储密度、更低的误码率（BER）和更高的数据传输速率。检索光学系统简单、稳定，对环境波动具有鲁棒性，适用于全息数据存储。此外，我们研究并证明了DL方法对全息数据存储系统的动态噪声具有良好的抑制效果。
