Phase recovery and holographic image reconstruction using deep learning in neural networks

作     者：Yair Rivenson Yibo Zhang Harun Günaydın Da Teng Aydogan Ozcan 

作者机构：Electrical and Computer Engineering DepartmentUniversity of CaliforniaLos AngelesCA 90095USA Bioengineering DepartmentUniversity of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI)University of CaliforniaLos AngelesCA 90095USA Computer Science DepartmentUniversity of CaliforniaLos AngelesCA 90095USA Department of SurgeryDavid Geffen School of MedicineUniversity of CaliforniaLos AngelesCA 90095USA 

出 版 物：《Light(Science & Applications)》 (光（科学与应用)（英文版）)

年 卷 期：2017年第6卷第1期

页      面：192-200页

核心收录：

学科分类：070207[理学-光学] 07[理学] 08[工学] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：Horizon 2020 Framework Programme, H2020, (659595) Horizon 2020 Framework Programme, H2020 

主　　题：deep learning holography machine learning neural networks phase recovery 

摘      要：Phase recovery from intensity-only measurements forms the heart of coherent imaging techniques and *** this study,we demonstrate that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate *** deep learning-based approach provides an entirely new framework to conduct holographic imaging by rapidly eliminating twin-image and self-interference-related spatial *** neural network-based method is fast to compute and reconstructs phase and amplitude images of the objects using only one hologram,requiring fewer measurements in addition to being computationally *** validated this method by reconstructing the phase and amplitude images of various samples,including blood and Pap smears and tissue *** results highlight that challenging problems in imaging science can be overcome through machine learning,providing new avenues to design powerful computational imaging systems.