We propose a new learning and inferring model that generates digital holograms using deep neural networks (DNNs). This DNN uses a generative adversarial network, trained to infer a complex two-dimensional fringe pattern from a single object point. The intensity and fringe patterns inferred for each object point were multiplied, and all the fringe patterns were accumulated to generate a perfect hologram. This method can achieve generality by recording holograms for two spaces (16 Space and 32 Space). The reconstruction results of both spaces proved to be almost the same as numerical computer-generated holograms by showing the performance at 44.56 and 35.11 dB, respectively. Through displaying the generated hologram in the optical equipment, we proved that the holograms generated by the proposed DNN can be optically reconstructed.
Much research and development have been made to implement deep neural networks for various purposes with hardware. We implement the deep learning algorithm with a dedicated processor. Watermarking technology for ultra-high resolution digital images and videos needs to be implemented in hardware for real-time or high-speed operation. We propose an optimization methodology to implement a deep learning-based watermarking algorithm in hardware. The proposed optimization methodology includes algorithm and memory optimization. Next, we analyze a fixed-point number system suitable for implementing neural networks as hardware for watermarking. Using these, a hardware structure of a dedicated processor for watermarking based on deep learning technology is proposed and implemented as an application-specific integrated circuit (ASIC).
This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique.
In this paper, we propose a new method for coding a full complex hologram with random phase. Since holograms with random phase have very unique spatial and frequency characteristics, a new compression method suitable for such holograms is required. We analyze the frequency characteristics of holograms with random phases and propose a new adaptive discrete wavelet transform (aDWT). Next, we propose a new modified zerotree alogrithm (mZTA) suitable for the subband configuration generated by the modified wavelet transform method. The results of the compression using the proposed method showed higher efficiency than the previous method, and the reconstructed images showed visually superior results.