Speaker: Jian Zhao
Affiliation: CREOL, University of Central Florida
Abstract: Our recent progress unveils that robust and high-fidelity imaging transport can be realized through the disordered glass-air Anderson localizing optical fiber (GALOF). In this talk, we demonstrate a deep-learning based fiber-optic imaging system using GALOF which can transfer real-time artifact-free cell images through a meter-long distance. The cell samples are illuminated by an incoherent LED light source. The deep-learning model training uses data generated by a set-up with straight fiber at room temperature (~20 °C) but can be utilized directly for high fidelity reconstruction of cell images that are transported through the fiber with a few degrees bend and/or fiber with segments heated up to 50 °C. In addition, cell images located several millimeters away from the bare fiber end can be transported and recovered successfully without the assistance of distal optics. We further evidence that the trained neural network is able to transfer its learning to recover cell images featuring very different morphologies and classes not seen during the training of the network.
Biography: Jian Zhao received the B.S. and M.S. degree in Optics from the School of Physics and Engineering in Sun Yat-sen University, Guangzhou, China, in 2012, and CREOL in University of Central Florida, Orlando, US, in 2014, respectively. He is currently working towards the Ph.D. degree (expected Aug. 3, 2019) with Professor Axel Schülzgen at CREOL in University of Central Florida. His research interests include deep learning in optics, fiber optics and ultrafast optics. He received UCF Presentation Travel Award from 2017 to 2019 and was awarded student of the year finalist honor from CREOL in 2019.
For more information, contact Prof. Yair Rivenson ()
Date(s) - Jul 08, 2019
2:00 pm - 3:30 pm
E-IV Tesla Room #53-125
420 Westwood Plaza - 5th Flr., Los Angeles CA 90095