Phase unwrapping is a classical signal processing problem, which refers to the recovery of the original phase value from the wrapped phase. Two dimensional phase unwrapping is widely used in optical measurement technology, such as digital holographic interferometry, fringe projection profilometry, synthetic aperture radar and many other applications. In this paper, a phase unwrapping method with the convolution neural network is proposed, and the feasibility is analyzed by numerical simulation. The convolution neural networks with different parameters are set up, and the phase screens used for the training set and testing set of convolution neural network are simulated with MATLAB software. The numerical simulation results show that the four convolution neural network models can be used for phase unwrapping, but the parameters have a significant impact on its accuracy.
For adaptive optics without wavefront detection, the wavefront control method based on deep learning is analyzed. The simulation model of adaptive optics is established,The far-field spot data collected by the photodetector is used as the input of the neural network model, and the Zernike mode coefficient is used as the output. The fully trained model can quickly and accurately recover and control the low-order wavefront. The simulation results show that convolution neural network can effectively extract image features, which is better than ordinary depth neural network model. For convolution network model, the larger the number of training sets, the smaller the value of loss function after convergence, and the higher the accuracy of the model. Compared with the traditional iterative optimization control method, the control method based on neural network model has obvious advantages in real-time.