CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 11551 > Article
Presentation
10 October 2020 Dense encoder-decoder network for 3D holographic particle imaging
Yufeng Wu, Jiachen Wu, Shangzhong Jin, Liangcai Cao
Author Affiliations +
Proceedings Volume 11551, Holography, Diffractive Optics, and Applications X; 1155109 (2020) https://doi.org/10.1117/12.2573905
Event: SPIE/COS Photonics Asia, 2020, Online Only
Abstract
Digital holographic imaging is able to reconstruct 3D or phase information of the object from a one-shot 2D lensless hologram. The inverse reconstruction of 3D particle field could be realized based on the deep convolutional neural network. The hologram of a single particle is spread throughout the detector. Deep convolutional neural network could perform particle feature extraction and obtain the 3D position of each particle. We propose a learning-based approach for 3D holographic particle imaging. A dense encoder-decoder U-net network is designed. Compared with the CNN-based U-net network and the residual connection-based U-net network, the proposed network can reduce the number of network parameters, increase the amount of information of each layer of particles, extract accurate particle characteristics, and improve robustness. The Dense-U-net is more efficient in the way it processes data and requires a less memory storage for the learned model.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yufeng Wu, Jiachen Wu, Shangzhong Jin, and Liangcai Cao "Dense encoder-decoder network for 3D holographic particle imaging", Proc. SPIE 11551, Holography, Diffractive Optics, and Applications X, 1155109 (10 October 2020); https://doi.org/10.1117/12.2573905
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 PRESENTATION
WATCH
PRESENTATION SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
KEYWORDS
Particles
3D image processing
Holography
Stereoscopy
Convolutional neural networks
Data modeling
Holograms
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top