Yuan Shizhu, Hu Yao, Hao Qun, Zhang Shaohui
Opt Express. 2021 Jan 18;29(2):2538-2554. doi: 10.1364/OE.413385.
Interferogram demodulation is a fundamental problem in optical interferometry. It is still challenging to obtain high-accuracy phases from a single-frame interferogram that contains closed fringes. In this paper, we propose a neural network architecture for single-frame interferogram demodulation. Furthermore, instead of using real experimental data, an interferogram generation model is constructed to generate the dataset for the network's training. A four-stage training strategy adopting appropriate optimizers and loss functions is developed to guarantee the high-accuracy training of the network. The experimental results indicate that the proposed method can achieve a phase demodulation accuracy of 0.01 λ (root mean square error) for actual interferograms containing closed fringes.
干涉图解调是光学干涉测量中的一个基本问题。从包含闭合条纹的单帧干涉图中获取高精度相位仍然具有挑战性。在本文中，我们提出了一种用于单帧干涉图解调的神经网络架构。此外，我们构建了一个干涉图生成模型来生成网络训练所需的数据集，而不是使用实际的实验数据。我们开发了一种采用适当优化器和损失函数的四阶段训练策略，以确保网络的高精度训练。实验结果表明，对于包含闭合条纹的实际干涉图，所提出的方法能够实现0.01 λ（均方根误差）的相位解调精度。
