Abstract
This paper addresses the problem of phase images corrupted with speckle noise. DnCNN residual networks with different depths were built and trained with various holographic noisy phase data. All models are evaluated in terms of phase error with HOLODEEP benchmark data and with 3 unseen images corresponding to different experimental conditions. The best results are obtained using a network with only 4 residual blocks, and trained with a wide range of noisy speckle patterns.
© 2021 The Author(s)
PDF ArticleMore Like This
Silvio Montresor, Marie Tahon, and Pascal Picart
DTh1D.1 Digital Holography and Three-Dimensional Imaging (DH) 2021
Silvio Montresor, Marie Tahon, Antoine Laurent, and Pascal Picart
HTu4B.4 Digital Holography and Three-Dimensional Imaging (DH) 2020
Silvio Montresor, Ketao Yan, Marie Tahon, Kemao Qian, Yingjie Yu, and Pascal Picart
HW3C.4 Digital Holography and Three-Dimensional Imaging (DH) 2023