Neural network based subspace analysis for estimation of phase derivatives from noisy interferograms DOI
Dhruvam Pandey,

Viren S Ram,

Rajshekhar Gannavarpu

et al.

Published: Jan. 1, 2024

This article introduces a robust phase derivative estimation method using deep learning-assisted subspace analysis. Simulation results validate the performance of proposed approach under severe noise conditions.

Language: Английский

On the use of deep learning for phase recovery DOI Creative Commons
Kaiqiang Wang, Li Song, Chutian Wang

et al.

Light Science & Applications, Journal Year: 2024, Volume and Issue: 13(1)

Published: Jan. 1, 2024

Phase recovery (PR) refers to calculating the phase of light field from its intensity measurements. As exemplified quantitative imaging and coherent diffraction adaptive optics, PR is essential for reconstructing refractive index distribution or topography an object correcting aberration system. In recent years, deep learning (DL), often implemented through neural networks, has provided unprecedented support computational imaging, leading more efficient solutions various problems. this review, we first briefly introduce conventional methods PR. Then, review how DL provides following three stages, namely, pre-processing, in-processing, post-processing. We also used in image processing. Finally, summarize work provide outlook on better use improve reliability efficiency Furthermore, present a live-updating resource ( https://github.com/kqwang/phase-recovery ) readers learn about

Language: Английский

Citations

77
Deep learning assisted non-contact defect identification method using diffraction phase microscopy DOI

S. Narayan,

Allaparthi Venkata Satya Vithin, Rajshekhar Gannavarpu

et al.

Applied Optics, Journal Year: 2023, Volume and Issue: 62(20), P. 5433 - 5433

Published: June 20, 2023

Reliable detection of defects from optical fringe patterns is a crucial problem in non-destructive interferometric metrology. In this work, we propose deep-learning-based method for pattern defect identification. By attributing the information to pattern's phase gradient, compute spatial derivatives using deep learning model and apply gradient map localize defect. The robustness proposed illustrated on multiple numerically synthesized at various noise levels. Further, practical utility substantiated experimental identification diffraction microscopy.

Language: Английский

Citations

9
Quality enhancement of interferometric fringe pattern based on deep-learning-based denoising of combined noise DOI

Juncheol Bae,

Y.‐M. Kim, Yusuke Ito

et al.

Precision Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Transformer based deep learning hybrid architecture for phase unwrapping DOI Creative Commons
Karthik Goud Bujagouni, Swarupananda Pradhan

Physica Scripta, Journal Year: 2024, Volume and Issue: 99(7), P. 076017 - 076017

Published: June 10, 2024

Abstract A deep learning Hybrid architecture for phase unwrapping has been proposed. The hybrid is based on integration of Convolutional Neural Networks (CNN) with Vision Transformer. performance architecture/network in compared against CNN standard UNET network. Structural Similarity Index (SSIM) and Root Mean Square Error (RMSE) have used as metrics to assess the these networks unwrapping. To train test networks, dataset high mean Entropy generated using Gaussian filtering random noise Fourier plane. tested found superior Their also noisy environment various levels demonstrated better anti-noise capability than was successfully validated real world scenario experimental data from custom built Digital Holographic Microscope. With advent newer architectures hardware, Deep can further improve solving inverse problems.

Language: Английский

Citations

2
Fringe pattern normalization using conditional Generative Adversarial Networks DOI

Viren S Ram,

Rajshekhar Gannavarpu

Optik, Journal Year: 2024, Volume and Issue: 313, P. 171999 - 171999

Published: Aug. 13, 2024

Language: Английский

Citations

2
Deep learning assisted state space method for phase derivative estimation in digital holographic interferometry DOI Creative Commons
Dhruvam Pandey, Rajshekhar Gannavarpu

Optics Continuum, Journal Year: 2024, Volume and Issue: 3(9), P. 1765 - 1765

Published: Sept. 4, 2024

In digital holographic interferometry, the measurement of derivatives interference phase plays a crucial role in deformation testing since displacement corresponding to deformed object are directly related derivatives. this work, we propose recurrent neural network-assisted state space method for reliable estimation The proposed offers high robustness against severe noise and corrupted fringe data regions, its performance is validated via numerical simulations. We also corroborate practical applicability by analyzing experimental test objects interferometry.

Language: Английский

Citations

2
Quantitative phase gradient metrology using diffraction phase microscopy and deep learning DOI
Allaparthi Venkata Satya Vithin, Rajshekhar Gannavarpu

Journal of the Optical Society of America A, Journal Year: 2023, Volume and Issue: 40(3), P. 611 - 611

Published: Jan. 31, 2023

In quantitative phase microscopy, measurement of the gradient is an important problem for biological cell morphological studies. this paper, we propose a method based on deep learning approach that capable direct estimation without requirement unwrapping and numerical differentiation operations. We show robustness proposed using simulations under severe noise conditions. Further, demonstrate method's utility imaging different cells diffraction microscopy setup.

Language: Английский

Citations

5
Non-contact automated defect detection using a deep learning approach in diffraction phase microscopy DOI Creative Commons
Dhruvam Pandey,

Abhinav Saini,

Rajshekhar Gannavarpu

et al.

Optics Continuum, Journal Year: 2023, Volume and Issue: 2(11), P. 2421 - 2421

Published: Nov. 7, 2023

Precision measurement of defects from optical fringe patterns is a problem significant practical relevance in non-destructive metrology. In this paper, we propose robust deep learning approach based on atrous convolution neural network model for defect detection noisy obtained diffraction phase microscopy. The utilizes the wrapped pattern as an input and generates binary image depicting non-defect regions output. effectiveness proposed validated through numerical simulations various under different noise levels. Furthermore, application technique identifying microscopy experiments also confirmed.

Language: Английский

Citations

4
Single-frame noisy interferogram phase retrieval using an end-to-end deep learning network with physical information constraints DOI
Tian Zhang, Runzhou Shi,

Yuqi Shao

et al.

Optics and Lasers in Engineering, Journal Year: 2024, Volume and Issue: 181, P. 108419 - 108419

Published: July 15, 2024

Language: Английский

Citations

1
Two-step differential phase-shifting phase retrieval using generative adversarial network DOI Open Access
Jiaosheng Li, Tianyun Liu, Guangshuo Cai

et al.

Optik, Journal Year: 2023, Volume and Issue: 290, P. 171303 - 171303

Published: Aug. 16, 2023

Language: Английский

Citations

1