Persistent Identifier
|
doi:10.18710/BBU6JD |
Publication Date
|
2022-11-16 |
Title
| Supplementary data for "Object detection neural network improves Fourier ptychography reconstruction" |
Author
| Ströhl, Florian (UiT The Arctic University of Norway) - ORCID: 0000-0002-2603-0780
Jadhav, Suyog S. (UiT The Arctic University of Norway) - ORCID: 0000-0003-3299-4292
Ahluwalia, Balpreet Singh (UiT The Arctic University of Norway) - ORCID: 0000-0001-7841-6952
Agarwal, Krishna (UiT The Arctic University of Norway) - ORCID: 0000-0001-6968-578X
Prasad, Dilip K. (UiT The Arctic University of Norway) - ORCID: 0000-0002-3693-6973 |
Point of Contact
|
Use email button above to contact.
Jadhav, Suyog S. (UiT The Arctic University of Norway) |
Description
| This dataset holds the trained deep learning models for our paper "Object detection neural network improves Fourier ptychography reconstruction". The results produced in the paper can be replicated through the use of these models in conjunction with the inference scripts provided in our GitHub repository: External Link. (2022-11-03)
Abstract High resolution microscopy is heavily dependent on superb optical elements and superresolution microscopy even more so. Correcting unavoidable optical aberrations during post-processing is an elegant method to reduce the optical system’s complexity. A prime method that promises superresolution, aberration correction, and quantitative phase imaging is Fourier ptychography. This microscopy technique combines many images of the sample, recorded at differing illumination angles akin to computed tomography and uses error minimisation between the recorded images with those generated by a forward model. The more precise knowledge of those illumination angles is available for the image formation forward model, the better the result. Therefore, illumination estimation from the raw data is an important step and supports correct phase recovery and aberration correction. Here, we derive how illumination estimation can be cast as an object detection problem that permits the use of a fast convolutional neural network (CNN) for this task. We find that faster-RCNN delivers highly robust results and outperforms classical approaches by far with an up to 3-fold reduction in estimation errors. Intriguingly, we find that conventionally beneficial smoothing and filtering of raw data is counterproductive in this type of application. We present a detailed analysis of the network’s performance and provide all our developed software openly. (2022-11-15) |
Subject
| Computer and Information Science; Physics |
Keyword
| Fourier Ptychography
Object Detection
Super Resolution Microscopy |
Related Publication
| Ströhl, F., Jadhav, S., Ahluwalia, B.S., Agarwal, K. and Prasad, D.K., 2020. Object detection neural network improves Fourier ptychography reconstruction. Optics Express, 28(25), pp.37199-37208. doi: 10.1364/OE.409679 https://doi.org/10.1364/oe.409679 |
Language
| English |
Producer
| UiT The Arctic University of Norway (UiT) https://en.uit.no/ |
Production Date
| 2020-09-08 |
Contributor
| Project Leader : Ströhl, Florian
Researcher : Jadhav, Suyog S.
Supervisor : Ahluwalia, Balpreet Singh
Supervisor : Agarwal, Krishna
Supervisor : Prasad, Dilip K. |
Funding Information
| The Research Council of Norway: 285571
European Research Council: 336716
European Research Council: 804233
European Research Council: 836355 |
Distributor
| UiT The Arctic University of Norway (UiT The Arctic University of Norway) https://dataverse.no/dataverse/uit |
Depositor
| Jadhav, Suyog S. |
Deposit Date
| 2022-11-03 |
Date of Collection
| Start Date: 2020-06-01 ; End Date: 2020-09-08 |
Data Type
| Deep Learning Models |
Software
| Detectron2, Version: 0.2
PyTorch, Version: 1.10.0 |
Related Material
| GitHub repository: https://github.com/IAmSuyogJadhav/NN-Illumination-Estimation-FPM |