REMOVAL OF UNWANTED TERMS FROM SINGLE SHOT INLINE DIGITAL HOLOGRAMS BY CONVOLUTIONAL NEURAL NETWORK

Duman B., Esmer G. B.

Unconventional Optical Imaging IV 2024, Strasbourg, France, 8 - 11 April 2024, vol.12996, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 12996
  • Doi Number: 10.1117/12.3017233
  • City: Strasbourg
  • Country: France
  • Keywords: Deep Learning, Digital Holographic Microscopy, Scalar Optical Diffraction
  • Marmara University Affiliated: Yes

Abstract

A model to achieve high-resolution three-dimensional microscopic images from synthetically generated digital holograms by using Convolutional Neural Networks (CNNs) is proposed. By employing low-cost microscopy systems and computational techniques, we demonstrate that proposed model provides viable alternative to costly high-resolution microscopic systems. Specifically, the study focuses on the elimination of the unwanted terms in backward-propagated holograms to closely approximate original high-resolution objects.