skip to main content

DOE PAGESDOE PAGES

Title: Lensless computational imaging through deep learning

Deep learning has been proven to yield reliably generalizable solutions to numerous classification and decision tasks. Here, we demonstrate for the first time to our knowledge that deep neural networks (DNNs) can be trained to solve end-to-end inverse problems in computational imaging. We experimentally built and tested a lensless imaging system where a DNN was trained to recover phase objects given their propagated intensity diffraction patterns.
Authors:
 [1] ;  [2] ;  [1] ;  [3]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Mechanical Engineering
  2. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Inst. for Medical Engineering Science
  3. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Dept. of Mechanical Engineering ; Singapore-MIT Alliance for Research and Technology (SMART) Centre (Singapore)
Publication Date:
Grant/Contract Number:
FG02-97ER25308
Type:
Published Article
Journal Name:
Optica
Additional Journal Information:
Journal Volume: 4; Journal Issue: 9; Journal ID: ISSN 2334-2536
Publisher:
Optical Society of America
Research Org:
Krell Inst., Ames, IA (United States)
Sponsoring Org:
USDOE Office of Science (SC)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING
OSTI Identifier:
1390388
Alternate Identifier(s):
OSTI ID: 1465165