Kakkava, EiriniRahmani, BabakBorhani, NavidTegin, UgurLoterie, DamienKonstantinou, GeorgiaMoser, ChristophePsaltis, Demetri2019-11-012019-11-012019-11-012019-11-0110.1016/j.yofte.2019.101985https://infoscience.epfl.ch/handle/20.500.14299/162609WOS:000491237100027Information transmission through multimode fibers (MMFs) has been a topic of great interest for many years. Deep learning algorithms have been applied successfully to MMFs in particular to fiber endoscopy. In this work, we show how Deep Neural Networks (DNNs) can be a versatile technique for classification and recovery of input images that have been significantly distorted while propagating along the MMF forming a speckle pattern. A comparison between holographic and intensity-only recording of the speckle output, which is used as an input to the DNNs, shows that high performance can be achieved without having the full field information (amplitude and phase). Impressive reconstruction fidelity and classification accuracy of the fiber inputs from the intensity-only images of the speckle patterns is reported.Engineering, Electrical & ElectronicOpticsTelecommunicationsEngineeringOpticsTelecommunications3-dimensional microfabricationconfocal microscopyhigh-resolutiontransmissioncompensationmatriximageslightpowertext::journal::journal article::research article