Open AccessImaging through scattering media based on semi-supervised learning
Author(s) -
Kaoru Yamazaki,
Ryoichi Horisaki,
Jun Tanida
Publication year - 2020
Publication title -
applied optics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.668
H-Index - 197
eISSN - 2155-3165
pISSN - 1559-128X
DOI - 10.1364/ao.402428
Subject(s) - artificial intelligence , computer science , computer vision , translation (biology) , scattering , object (grammar) , optics , spatial frequency , image translation , image (mathematics) , light scattering , pattern recognition (psychology) , physics , biochemistry , chemistry , messenger rna , gene
We present a method for less-invasive imaging through scattering media. We use an image-to-image translation, which is called a cycle generative adversarial network (CycleGAN), based on semi-supervised learning with an unlabeled dataset. Our method was experimentally demonstrated by reconstructing object images displayed on a spatial light modulator between diffusers. In the demonstration, CycleGAN was trained with captured images and object candidate images that were not used for image capturing through the diffusers and were not paired with the captured images.