|
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.
|
