Photoelastic Dispersion Coefficient by Holographic Reconstruction with Neural Networks and the Fresnel Method

Author(s)

Prado, Felipe Maia ; Miho de Souza, Pedro Henrique ; da Silva, Sidney Leal ; Wetter, Niklaus Ursus ; IEEE

• Document type: Journal article
• Source: 2023 INTERNATIONAL CONFERENCE ON OPTICAL MEMS AND NANOPHOTONICS, OMN AND SBFOTON INTERNATIONAL OPTICS AND PHOTONICS CONFERENCE, SBFOTON IOPC; v. N/A, p. 2-pg., 2023-01-01.

Abstract

Here we report the characterization of the photoelastic dispersion coefficient using digital holography with two distinct reconstruction methods: one based on the Fresnel method and the other utilizing convolutional neural networks (CNN). The CNN was trained with reconstruction from the Fresnel method and was able to provide reconstructions with an average Mean Squared Error of 0.006. (AU)

• FAPESP's process: 22/15276-0 - Optical neural networks with new non-linear activation functions for phase recovery applied to digital holography
• Grantee: Felipe Maia Prado
• Support Opportunities: Scholarships in Brazil - Doctorate