In this work, training and recognition of the types of aberrations corresponding to individual Zernike functions have been carried out by the pattern of the intensity of the point scattering function (PSF) using convolutional neural networks. The PSF intensity patterns in the focal plane were modeled using the Fast Fourier Transform algorithm. When training a neural network, the learning coefficient and the number of epochs for a dataset of a given size were selected empirically. The average prediction errors of the neural network for each type of aberration were obtained for a set of 15 Zernike functions from a dataset of 15 thousand PSF pictures. As a result of training, for most types of aberrations, averaged absolute errors were obtained in the range 0.012–0.015, however, the determination of the aberration coefficient (magnitude) requires additional research and data, for example, calculating the PSF in the extrafocal plane.
|