On the use of deep learning for phase recovery

Light Science & Applications, Год журнала: 2024, Номер 13(1)

Опубликована: Янв. 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

Язык: Английский

---

High-throughput microplastic assessment using polarization holographic imaging

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Янв. 29, 2024

Abstract Microplastic (MP) pollution has emerged as a global environmental concern due to its ubiquity and harmful impacts on ecosystems human health. MP assessment therefore become increasingly necessary common in experimental samples. Microscopy spectroscopy are widely employed for the physical chemical characterization of MPs. However, these analytical methods often require time-consuming pretreatments samples or expensive instrumentation. In this work, we develop portable cost-effective polarization holographic imaging system that prominently incorporates deep learning techniques, enabling efficient, high-throughput detection dynamic analysis MPs aqueous environments. The integration enhances identification classification MPs, eliminating need extensive sample preparation. simultaneously captures interference patterns states, allowing multimodal information acquisition facilitate rapid detection. characteristics light waves registered, birefringence features leveraged classify material composition structures Furthermore, automates real-time counting morphological measurements various materials, including sheets additional natural substances. This innovative approach significantly improves monitoring provides valuable their effective filtration management.

Язык: Английский

---

Smart polarization and spectroscopic holography for real-time microplastics identification

Communications Engineering, Год журнала: 2024, Номер 3(1)

Опубликована: Фев. 17, 2024

Abstract Optical microscopy technologies as prominent imaging methods can offer rapid, non-destructive, non-invasive detection, quantification, and characterization of tiny particles. However, optical systems generally incorporate spectroscopy chromatography for precise material determination, which are usually time-consuming labor-intensive. Here, we design a polarization spectroscopic holography to automatically analyze the molecular structure composition, namely smart (SPLASH). This approach improves evaluation performance by integrating multi-dimensional features, thereby enabling highly accurate efficient identification. It simultaneously captures states-related, holographic, texture features spectroscopy, without physical implementation system. By leveraging Stokes mask (SPM), SPLASH achieves simultaneous four states. Its effectiveness has been demonstrated in application microplastics (MP) With machine learning methods, such ensemble subspace discriminant classifier, k-nearest neighbors support vector machine, depicts MPs with anisotropy, interference fringes, refractive index, morphological characteristics performs explicit discrimination over 0.8 value area under curve less than 0.05 variance. technique is promising tool addressing increasing public concerning issues MP pollution assessment, source identification, long-term water monitoring.

Язык: Английский

---

Hybrid Optimization of Phase Masks: Integrating Non-Iterative Methods with Simulated Annealing and Validation via Tomographic Measurements

Symmetry, Год журнала: 2025, Номер 17(4), С. 530 - 530

Опубликована: Март 31, 2025

The development of holography has facilitated significant advancements across a wide range disciplines. A phase-only spatial light modulator (SLM) plays crucial role in realizing digital holography, typically requiring phase mask as its input. Non-iterative (NI) algorithms are widely used for generation, yet they often fall short delivering precise solutions and lack adaptability complex scenarios. In contrast, the Simulated Annealing (SA) algorithm provides global optimization approach capable addressing these limitations. This study investigates integration NI with SA to enhance generation holography. Furthermore, we examine how adjusting annealing parameters, especially cooling strategy, can significantly improve system performance symmetry. Notably, observe considerable improvement efficiency when non-iterative methods employed generate initial mask. Our method achieves perfect representation symmetry desired fields. efficacy optimized masks is evaluated through optical tomographic measurements using two-dimensional mutually unbiased bases (MUBs), resulting average similarity reaching 0.99. These findings validate effectiveness our methodin optimizing underscore potential high-precision mode recognition analysis.

Язык: Английский

---

Deep-Learning Computational Holography: A Review

Frontiers in Photonics, Год журнала: 2022, Номер 3

Опубликована: Март 28, 2022

Deep learning has been developing rapidly, and many holographic applications have investigated using deep learning. They shown that can outperform previous physically-based calculations lightwave simulation signal processing. This review focuses on computational holography, including computer-generated holograms, displays, digital We also discuss our personal views the promise, limitations future potential of in holography.

Язык: Английский

---

Hyperspectral vision beyond 3D: A review

Optics and Lasers in Engineering, Год журнала: 2024, Номер 178, С. 108238 - 108238

Опубликована: Апрель 17, 2024

Язык: Английский

---

Out-of-focus artifact removal for Fresnel incoherent correlation holography by deep learning

Optics and Lasers in Engineering, Год журнала: 2024, Номер 178, С. 108195 - 108195

Опубликована: Март 18, 2024

Язык: Английский

---

Generative adversarial neural network for 3D-hologram reconstruction

Laser Physics Letters, Год журнала: 2024, Номер 21(4), С. 045201 - 045201

Опубликована: Фев. 14, 2024

Abstract Neural-network-based reconstruction of digital holograms can improve the speed and quality micro- macro-object images, as well reduce noise suppress twin image zero-order. Usually, such methods aim to reconstruct 2D object or amplitude phase distribution. In this paper, we investigated feasibility using a generative adversarial neural network 3D-scenes consisting set cross-sections. The method was tested on computer-generated optically-registered inline holograms. It enabled all layers scene from each hologram. is improved 1.8 times when compared U-Net architecture normalized standard deviation value.

Язык: Английский

---

Differentiable Imaging: A New Tool for Computational Optical Imaging

Advanced Physics Research, Год журнала: 2023, Номер 2(6)

Опубликована: Март 23, 2023

Abstract The field of computational imaging has made significant advancements in recent years, yet it still faces limitations due to the restrictions imposed by traditional techniques. Differentiable programming offers a solution combining strengths classical optimization and deep learning, enabling creation interpretable model‐based neural networks. Through integration physics into modeling process, differentiable imaging, which employs potential overcome challenges posed sparse, incomplete, noisy data. As result, play key role advancing its various applications.

Язык: Английский

---

Untrained deep network powered with explicit denoiser for phase recovery in inline holography

Applied Physics Letters, Год журнала: 2023, Номер 122(13)

Опубликована: Март 27, 2023

Single-shot reconstruction of the inline hologram is highly desirable as a cost-effective and portable imaging modality in resource-constrained environments. However, twin image artifacts, caused by propagation conjugated wavefront with missing phase information, contaminate reconstruction. Existing end-to-end deep learning-based methods require massive training data pairs environmental system stability, which very difficult to achieve. Recently proposed prior (DIP) integrates physical model formation into neural networks without any requirement. process fitting output single measured results interference-related noise. To overcome this problem, we have implemented an untrained network powered explicit regularization denoising (RED), removes images noise Our work demonstrates use alternating directions multipliers method (ADMM) combine DIP RED robust single-shot recovery process. The ADMM, based on variable splitting approach, made it possible plug play different denoisers need differentiation. Experimental show that sparsity-promoting give better over terms signal-to-noise ratio (SNR). Considering computational complexities, conclude total variation denoiser more appropriate for

Язык: Английский

---