Filters








1,051 Hits in 5.4 sec

Holographic 3D Particle Imaging With Model-Based Deep Network

Ni Chen, Congli Wang, Wolfgang Heidrich
2021 IEEE Transactions on Computational Imaging  
To cope with this problem, we propose a modelbased holographic network (MB-HoloNet) for three-dimensional particle imaging.  ...  The physical prior makes the network efficient and stable for both localization and 3D particle size reconstructions. inverse problems.  ...  Yuqi Li for his contributions to an earlier version of loop-unrolled networks for digital holography, which has inspired this work [39] .  ... 
doi:10.1109/tci.2021.3063870 fatcat:aiuqqk5v35fuxmz2opnpjzbuzy

Deep-Learning Computational Holography: A Review (Invited)

Tomoyoshi Shimobaba, David Blinder, Tobias Birnbaum, Ikuo Hoshi, Harutaka Shiomi, Peter Schelkens, Tomoyoshi Ito
2022 Frontiers in Photonics  
Deep learning has been developing rapidly, and many holographic applications have been investigated using deep learning.  ...  They have shown that deep learning can outperform previous physically-based calculations using lightwave simulation and signal processing.  ...  Digital holographic particle measurement can measure one-shot 3D particles; however, it requires timeconsuming post-processing using diffraction calculations and particle position detection. 3D particle  ... 
doi:10.3389/fphot.2022.854391 fatcat:6yekzxerlvbj7bs4tkr6xuqufe

Deep learning in holography and coherent imaging

Yair Rivenson, Yichen Wu, Aydogan Ozcan
2019 Light: Science & Applications  
Recent advances in deep learning have given rise to a new paradigm of holographic image reconstruction and phase recovery techniques with real-time performance.  ...  Through data-driven approaches, these emerging techniques have overcome some of the challenges associated with existing holographic image reconstruction methods while also minimizing the hardware requirements  ...  In this deep-learning-based framework, which is termed Holographic Imaging using Deep Learning for Extended Focus (HIDEF), the network is trained using pairs of randomly defocused (backpropagated) holograms  ... 
doi:10.1038/s41377-019-0196-0 pmid:31645929 pmcid:PMC6804620 fatcat:25ns3ekq25c7ho2as474z7t4ny

Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery

Yichen Wu, Yair Rivenson, Yibo Zhang, Zhensong Wei, Harun Günaydin, Xing Lin, Aydogan Ozcan
2018 Optica  
Here we demonstrate a convolutional neural network (CNN) based approach that simultaneously performs auto-focusing and phase-recovery to significantly extend the depth-of-field (DOF) in holographic image  ...  This deep learning based DOF extension method is non-iterative, and significantly improves the algorithm time-complexity of holographic image reconstruction from O(nm) to O(1), where n refers to the number  ...  We term this approach as HIDEF (Holographic Imaging using Deep learning for Extended Focus) and it relies on training a CNN with not only in-focus image patches, but also with randomly de-focused holographic  ... 
doi:10.1364/optica.5.000704 fatcat:fapvcpbss5euvpxqa2oerkzw6a

Front Matter: Volume 10679

Peter Schelkens, Touradj Ebrahimi, Gabriel Cristóbal
2018 Optics, Photonics, and Digital Technologies for Imaging Applications V  
These two-number sets start with 00, 01, 02, 03,  ...  SPIEDigitalLibrary.org Paper Numbering: Proceedings of SPIE follow an e-First publication model. A unique citation identifier (CID) number is assigned to each article at the time of publication.  ...  A multiphase active contour model based on the Hermite transform for texture segmentation [10679-52] 10679 1K Particle image models for optical flow-based velocity field estimation in image velocimetry  ... 
doi:10.1117/12.2503293 fatcat:ulusck3hurczbp4sfx763xnlxm

2020 Index IEEE Transactions on Computational Imaging Vol. 6

2020 IEEE Transactions on Computational Imaging  
Coherent Plug-and-Play: Digital Holographic Imaging Through Atmospheric Turbulence Using Model-Based Iterative Reconstruction and Convolutional Neural Networks.  ...  ., +, TCI 2020 1033-1043 Physics Coherent Plug-and-Play: Digital Holographic Imaging Through Atmospheric Turbulence Using Model-Based Iterative Reconstruction and Convolutional Neural Networks.  ... 
doi:10.1109/tci.2021.3054596 fatcat:puij7ztll5ai7alxrmqzsupcny

Quantitative Digital Microscopy with Deep Learning [article]

Benjamin Midtvedt and Saga Helgadottir and Aykut Argun and Jesús Pineda and Daniel Midtvedt and Giovanni Volpe
2020 arXiv   pre-print
We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification.  ...  Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis.  ...  ACKNOWLEDGMENTS The authors would like to thank Carlo Manzo for providing the experimental images used in the fourth case study, Jose Alvarez for designing the logo of DeepTrack 2.0, as well as the European  ... 
arXiv:2010.08260v1 fatcat:wo6iwmlvjfajdgvmj5nclqbph4

Computational cytometer based on magnetically modulated coherent imaging and deep learning

Yibo Zhang, Mengxing Ouyang, Aniruddha Ray, Tairan Liu, Janay Kong, Bijie Bai, Donghyuk Kim, Alexander Guziak, Yi Luo, Alborz Feizi, Katherine Tsai, Zhuoran Duan (+8 others)
2019 Light: Science & Applications  
periodic magnetic force and uses lensless time-resolved holographic speckle imaging to rapidly detect the target cells in three dimensions (3D).  ...  pseudo-3D convolutional neural network (P3D CNN), which automatically detects rare cells of interest based on their spatio-temporal features under a controlled magnetic force.  ...  A computational motion analysis (CMA) algorithm 41 and a densely connected pseudo-3D convolutional neural network structure (P3D CNN) 58 then analyse the holographic image sequence that contains the  ... 
doi:10.1038/s41377-019-0203-5 pmid:31645935 pmcid:PMC6804677 fatcat:bpntzyelrfd43lv5u3koh6ufte

Virtual Reality based Hologram for Emergency Situation

2020 International journal of recent technology and engineering  
We have conducted a survey based on various algorithms and methods that are used to create a hologram and for analysing holographic image.  ...  Holography is a pictorial method that records the light scattered from an object, presenting it in a way that appears in a 3D form.  ...  A deep learning network is strained with a group of examples, having a low-resolution hologram as the input and a high-resolution hologram as the output.  ... 
doi:10.35940/ijrte.a1917.059120 fatcat:ydl53mraqrb73ftf6hcmnvbtrq

Recognition of Multiscale Dense Gel Filament-Droplet Field in Digital Holography With Mo-U-Net

Zhentao Pang, Hang Zhang, Yu Wang, Letian Zhang, Yingchun Wu, Xuecheng Wu
2021 Frontiers in Physics  
Accurate particle detection is a common challenge in particle field characterization with digital holography, especially for gel secondary breakup with dense complex particles and filaments of multi-scale  ...  Public model address: https://github.com/Wu-Tong-Hearted/Recognition-of-multiscale-dense-gel-filament-droplet-field-in-digital-holography-with-Mo-U-net.  ...  This study combines semantic segmentation model based on deep neural network with the holographic images of gel secondary atomization field and proposes Mo-U-net to deal with this segmentation task.  ... 
doi:10.3389/fphy.2021.742296 fatcat:ay7f7wrrtrg4fdtwby67nlf6c4

Adaptive 3D descattering with a dynamic synthesis network [article]

Waleed Tahir, Hao Wang, Lei Tian
2022 arXiv   pre-print
We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions.  ...  Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts.  ...  Broadly, we believe this new adaptive deep learning framework can be further adapted to many other imaging applications, including image denoising [35] , non-line-of-sight imaging [58] , deep imaging  ... 
arXiv:2107.00484v2 fatcat:seewl3i2zrfefeh26micnaqy44

Front Matter: Volume 11205

Motoharu Fujigaki, Huimin Xie, Qican Zhang, Song Zhang, Jianguo Zhu, Qian Kemao, Anand Asundi
2019 Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019)  
These two-number sets start with 00, 01, 02, 03, 04,  ...  SPIEDigitalLibrary.org Paper Numbering: Proceedings of SPIE follow an e-First publication model. A unique citation identifier (CID) number is assigned to each article at the time of publication.  ...  -8 vii Proc. of SPIE Vol. 11205 1120501-7 VISION, IMAGING, ACQUISITION, AND DISPLAY 11205 25 Depth information calculation method for unstructured objects based on deep neural network [11205-57]  ... 
doi:10.1117/12.2551765 fatcat:fkizzql7qjcvfbfktmg6ii3cym

Holographic characterisation of subwavelength particles enhanced by deep learning [article]

Benjamin Midtvedt, Erik Olsén, Fredrik Eklund, Fredrik Höök, Caroline Beck Adiels, Giovanni Volpe, Daniel Midtvedt
2020 arXiv   pre-print
We achieve this by developing a weighted average convolutional neural network to analyse the holographic images of the particles.  ...  This technique opens new possibilities for nanoparticle characterisation with a broad range of applications from biomedicine to environmental monitoring.  ...  Here, we demonstrate that holographic imaging combined with deep learning can simultaneously characterise the size and refractive index of subwavelength particles, while using two orders of magnitude shorter  ... 
arXiv:2006.11154v1 fatcat:tu55qwlunjefphkm5n4gepe5sy

Front Matter: Volume 10649

Mohammad S. Alam
2018 Pattern Recognition and Tracking XXIX  
modified particle filters MOTION SENSING AND ESTIMATION ALGORITHMS 0D Nanosensor network for 3D+T motion analysis iii Proc. of SPIE Vol. 10649 1064901-3 ATR performance improvement using images  ...  , HOG, SIFT, SURF, and BRIEF techniques for face recognition [10649-25] 10649 0N Convolutional neural network based image segmentation: a review [10649-26] DEEP LEARNING BASED PATTERN RECOGNITION  ... 
doi:10.1117/12.2501434 fatcat:2jnwikkt7vbclmct2q6gzo5t7u

Front Matter: Volume 10677

Corinne Fournier, Marc P. Georges, Gabriel Popescu
2018 Unconventional Optical Imaging  
These two-number sets start with 00, 01, 02, 03, 04,  ...  SPIEDigitalLibrary.org Paper Numbering: Proceedings of SPIE follow an e-First publication model. A unique citation identifier (CID) number is assigned to each article at the time of publication.  ...  -32] 10677 0Y A dimension reduction method for fast diffuse optical tomography [10677-33] 10677 10 Super-resolution for noisy images via deep convolutional neural network [10677-35] ADVANCED METHODS  ... 
doi:10.1117/12.2503289 fatcat:khsemz52l5fvxlggiegisbfxti
« Previous Showing results 1 — 15 out of 1,051 results