Journal article
R. Guo, Soren Nelson, R. Menon
Applied Optics, 2021
Applied Optics, 2021
Semantic Scholar
DOI
PubMed
Cite
Cite
APA
Click to copy
Guo, R., Nelson, S., & Menon, R. (2021). Needle-based deep-neural-network camera. Applied Optics.
Chicago/Turabian
Click to copy
Guo, R., Soren Nelson, and R. Menon. “Needle-Based Deep-Neural-Network Camera.” Applied Optics (2021).
MLA
Click to copy
Guo, R., et al. “Needle-Based Deep-Neural-Network Camera.” Applied Optics, 2021.
BibTeX Click to copy
@article{r2021a,
title = {Needle-based deep-neural-network camera.},
year = {2021},
journal = {Applied Optics},
author = {Guo, R. and Nelson, Soren and Menon, R.}
}
Abstract
We experimentally demonstrate a camera whose primary optic is a cannula/needle (diameter=0.22mm and length=12.5mm) that acts as a light pipe transporting light intensity from an object plane (35 cm away) to its opposite end. Deep neural networks (DNNs) are used to reconstruct color and grayscale images with a field of view of 18° and angular resolution of ∼0.4∘. We showed a large effective demagnification of 127×. Most interestingly, we showed that such a camera could achieve close to diffraction-limited performance with an effective numerical aperture of 0.045, depth of focus ∼16µm, and resolution close to the sensor pixel size (3.2 µm). When trained on images with depth information, the DNN can create depth maps. Finally, we show DNN-based classification of the EMNIST dataset before and after image reconstructions. The former could be useful for imaging with enhanced privacy.