Artificial intelligence and Fourier optics: application of DeepLabV3+in the recovery of a diffracting aperture in light propagation (7 pages)

• C. Camacho-Bello ^[1] ; L. Gutiérrez-Lazcano ^[1] ; R.M. Ortega-Mendoza ^[1]
  1. [1] Universidad Politécnica de Tulancingo

     Universidad Politécnica de Tulancingo

     México

     
• Localización: Revista Mexicana de Física, ISSN-e 0035-001X, Vol. 70, Nº. 1, 2024
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • The combination of Fourier Optics and Artificial Intelligence has driven significant advances in image processing and modeling of optical systems, with the UNet architecture being the main protagonist. However, the DeepLabV3+ network has recently shown promising performance detecting diffracting apertures. In this study, we investigate the effectiveness of DeepLabV3+ in identifying diffracting apertures in light propagation models and compare its performance with that of UNet. The results reveal that DeepLabV3+ outperforms UNet in accuracy and robustness in identifying diffracting apertures, even in the presence of noise and aperture shape variations.