Learning to see through multimode fibers
Published on 2018-08-09T13:41:36Z (GMT) by
Deep Neural Networks (DNNs) are used to classify and reconstruct the input images from the intensity of the speckle patterns that result after the inputs propagated through the multimode fiber (MMF). We were able to demonstrate this result for fibers up to 1km long by training the DNNs with a database of 16,000 handwritten digits. Better recognition accuracy was obtained when the DNNs were first trained to reconstruct the input and then classify based on the recovered image. We observed remarkable robustness against environmental instabilities and tolerance to deviations of the input pattern from the patterns with which the DNN was originally trained.
Cite this collection
Borhani, Navid; Kakkava, Eirini; Moser, Christophe; Psaltis, Demetri (2018): Learning to see through multimode fibers. The Optical Society. Collection.