Ghost imaging gives the possibility of imaging objects with extremely low levels of light, which could be particularly useful for light-sensitive objects. In this study, we varied different important experimental parameters of our all-digital set-up, that condition both the acquisition time and quality of the reconstructed image, with the idea of finding the optimal ones. In addition to this, we introduced machine-learning techniques to include a recognition algorithm that further reduces the time necessary to identify the imaged object. This improvement in efficiency paves the way to use ghost imaging for living specimens.

© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Valeria Rodríguez-Fajardo, Jonathan Pinell, Christopher Ayala, and Andrew Forbes, "Intelligent ghost imaging (Conference Presentation)," Proc. SPIE 11134, Quantum Communications and Quantum Imaging XVII, 111340Q (Presented at SPIE Optical Engineering + Applications: August 12, 2019; Published: 10 September 2019); https://doi.org/10.1117/12.2528757.6084683992001.