Seeing invisible objects with intelligent optics
Transparent objects are invisible to traditional cameras because they can only detect intensity fluctuations, necessitating the need for interferometry followed by computationally intensive digital image processing. Now it is shown that the necessary transformations can be performed optically by combining machine learning and diffractive optics, for a direct in-situ measurement of transparent objects with conventional cameras.
Authors
- Andrew Forbes (ORCID: https://orcid.org/0000-0003-2552-5586)
- Isaac M. Nape (ORCID: https://orcid.org/0000-0001-9517-6612)
Institutions
- University of the Witwatersrand (ZA)
Publication Details
- Journal
- Light Science & Applications
- Published
- 2024-09-05
- DOI
- https://doi.org/10.1038/s41377-024-01575-2
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00