Phase retrieval occurs in many research areas. There are some classical phase retrieval methods such as hybrid input-output (HIO) and difference map (DM). However, phase retrieval results are sensitive to noise, and the reconstructed images always include artefacts. In this paper, we use the DM algorithm together with DNN to get better phase retrieval results. We train one deep neural network using amplitude images and phase images, respectively. First, using DM, we get initial reconstructed amplitude and phase results. Then, using DNN improves both amplitude and phase results. Finally, using the DM algorithm again improves the DNN results further. The numerical experimental results show that using DM gives better results than HIO, and using DNN improves phase information better than just using DNN to train for amplitude information alone. Compared with only using DNN improves amplitude methods, our method using DM plus DNN plus DM yields a better reconstruction performance for both amplitude and phase.

相位检索出现在许多研究领域。有一些经典的相位检索方法，例如混合输入输出（HIO）和差异图（DM）。然而，相位检索结果对噪声敏感，重建的图像总是包含人为因素。在本文中，我们将 DM 算法与 DNN 结合使用以获得更好的相位检索结果。我们分别使用振幅图像和相位图像训练一个深度神经网络。首先，使用 DM，我们得到初始重构幅度和相位结果。然后，使用 DNN 改善幅度和相位结果。最后，再次使用 DM 算法进一步改进了 DNN 结果。数值实验结果表明，使用 DM 比 HIO 给出更好的结果，并且使用 DNN 比仅使用 DNN 单独训练幅度信息更好地改善相位信息。