KEYWORDS: Reconstruction algorithms, Deep learning, Digital holography, Holograms, Technology, Holography, Spherical lenses, Phase retrieval, Image resolution, Education and training
Lensless Coaxial Digital Holographic Imaging (LCDHI) has great advantages of wide-field, high resolution and non-destructive measurement. By removing traditional lenses and utilizing a coaxial optical path, the lens-aberration can be avoided, and the imaging process is greatly simplified, which is one of the powerful tools for observing of micro components and biological cells. With the help of an open-source hardware and deep learning technology, a simple and portable experimental device based on the principle of lensless coaxial digital holography is designed and set up in this study. In order to avoid the problems of difficult data-acquisition and time-consuming training caused by supervised learning, a deep convolutional neural network (CNN) based on an auto-encoder is embedded into the Gerchberg-Saxton (GS) iterative process of LCDHI to accomplish phase retrieval. Compared with the traditional GS algorithm, more accurate amplitude and phase results can be reconstructed by the proposed low-cost device and the designed CNN through several experiments.
Coded Aperture Snapshot Spectral Imaging (CASSI) is an effective tool to capture spectral images, which has the advantages of snapshot imaging, high luminous flux, high signal-to-noise ratio and low sampling frequency. However, conventional CASSI generally uses refractive prisms or gratings for spectral dispersion, which leads to the nonlinear dispersion phenomenon and the requirement of large detector chip respectively. To overcome these issues, conventional refractive prisms or gratings are replaced by an axially dispersive diffractive optical element (DOE, i.e., computational optics) together with a RGB Bayer filter (i.e., a color-coded aperture) in this study. Specifically, the spatial-spectral information of a test scene is jointly modulated by the DOE and the Bayer filter integrated with a sensor chip. A fully differentiable imaging model is built based on the principle of diffractive optics and the deep learning technology. Furthermore, an optimization design of the DOE with the coded aperture is realized through an end-to-end approach, the output spectral images of which are restored by a Res-Unet neural network. Several simulation results show that up to 31 high-fidelity spectral bands in the range of 400 to 700 nm with a good spatial and spectral resolution can be recovered by the proposed snapshot system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.