Presentation
12 September 2021 Design of complex optical thin-films based on light scattering properties and using deep neural networks
Author Affiliations +
Abstract
Optical thin-film design has been intensely studied over the last decades and there exist methods to synthetize numerous optical functions, usually considering only specular spectral responses. Benefiting from the rise of artificial intelligence, new methods seek to provide other solutions. Light scattering properties have rarely been taken into account in the design of thin-films because of their extreme complexity, even though it might be critical for some demanding applications. We propose a light scattering-based design method of complex thin-films using deep neural networks. Our implementation aims to design components with controlled light scattering levels and acceptable specular properties.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Marin Fouchier, Myriam Zerrad, Michel Lequime, and Claude Amra "Design of complex optical thin-films based on light scattering properties and using deep neural networks", Proc. SPIE 11872, Advances in Optical Thin Films VII, 1187205 (12 September 2021); https://doi.org/10.1117/12.2597107
Advertisement
Advertisement
KEYWORDS
Light scattering

Thin films

Inverse optics

Optical design

Neural networks

Optical filters

Evolutionary algorithms

RELATED CONTENT


Back to Top