In this paper, a phase retrieval method based on deep learning is proposed and applied to the phase-modulated holographic storage system. The phase-modulated holographic storage system has become a research hotspot because of its higher encoding rate and higher signal-to-noise ratio (SNR). Since the phase data cannot be detected directly by the detector, the intensity image is used to retrieve the phase. The traditional interferometric phase retrieval method is not suitable for the storage system because its optical system is complex and is easily affected by environmental disturbances. The non-interferometric phase modulation storage system uses iterative methods to solve the phase data, and the number of iterations will affect the data transmission rate in the holographic data system. In this paper, a simulated non-interferometric phase retrieval system based on deep learning is established, which uses a convolutional neural network to directly establish the relationship between phase and intensity images captured by CCD. The neural network is trained by learning the dataset of intensity images and phase data images. After training, the phase can be obtained by a single calculation, which greatly improves the data transmission speed. In the process of deep learning training, we introduced embedded data to improve the precision of phase reconstruction and reduce the bit error rate. According to our investigation, this is the first application of deep learning in phase retrieval of optical holographic storage.
The single-shot iterative Fourier transform algorithm as a common non-interferometric phase retrieval algorithm is very suitable for phase-modulated holographic data storage due to its fast, simple and stable properties. It retrieves the phase in the object domain iteratively from the intensity image in the Fourier domain captured by the detector. Because of the effects by complex noises of the experimental system, there is always an intensity image degradation which increases the phase decoding bit error rate. This paper proposed a denoising method based on end-to-end convolutional neural networks by learning the relationship between the captured intensity images and the simulation results to improve image quality significantly. Then the denoised intensity image was used in the phase retrieval. The experiment results showed that the bit error rate can be reduced by 6.7 times using the denoised image, which proved the feasibility of the neural network denoising method in the phase-modulated holographic data storage system.