Fringe pattern denoising based on deep learning

Yan, Kun; Yu, Yingjie; Huang, Chongtian; Sui, Liansheng; Kemao, Qian; Asundi, Anand Krishna

doi:10.1016/j.optcom.2018.12.058

Cited by 144 publications

(53 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is vital to note that there are single-frame fringe analysis algorithms 86 – 91 reported to be able to surpass the overlapping spectrum limitation but they were only applied to well defined (polynomial-based) slowly varying continuous phase functions. In QPI the objective is to study detail-rich highly diversified bio-samples; as every cell is different it is not possible to model all of them universally and retrieve correct detail-preserved phase map in optimization based manner 86 – 91 . Single-shot versatility of the VHQPI, understood as ability to accurately retrieve phase from single interferogram regardless the cell specificity and variability, is a considerable advantage and novelty in the QPI field.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, the VHQPI www.nature.com/scientificreports/ employs automatic procedure to generate error-minimized fringe direction map and uses it to boost quality of the phase demodulation. In a consequence the VHQPI is remarkably versatile similarly to emerging deep learning approaches [82][83][84][85] with the crucial difference that it requires no training at all and the result, i.e., Figs. 4d, 5c, 6d and 7e, is just one click away basing on the notion of default purely numerical add-on module.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Variational Hilbert Quantitative Phase Imaging

Trusiak

Cywińska

Micó

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Utilizing the refractive index as the endogenous contrast agent to noninvasively study transparent cells is a working principle of emerging quantitative phase imaging (QPI). In this contribution, we propose the Variational Hilbert Quantitative Phase Imaging (VHQPI)-end-to-end purely computational add-on module able to improve performance of a QPI-unit without hardware modifications. The VHQPI, deploying unique merger of tailored variational image decomposition and enhanced Hilbert spiral transform, adaptively provides high quality map of sample-induced phase delay, accepting particularly wide range of input single-shot interferograms (from off-axis to quasi on-axis configurations). It especially promotes high space-bandwidth-product QPI configurations alleviating the spectral overlapping problem. The VHQPI is tailored to deal with cumbersome interference patterns related to detailed locally varying biological objects with possibly high dynamic range of phase and relatively low carrier. In post-processing, the slowly varying phase-term associated with the instrumental optical aberrations is eliminated upon variational analysis to further boost the phase-imaging capabilities. The VHQPI is thoroughly studied employing numerical simulations and successfully validated using static and dynamic cells phase-analysis. It compares favorably with other single-shot phase reconstruction techniques based on the Fourier and Hilbert-Huang transforms, both in terms of visual inspection and quantitative evaluation, potentially opening up new possibilities in QPI. Optical imaging is a central aspect of biological research, biomedical examination, and medical diagnosis. Optical microscope is indispensable in biological and medical research facilitating a "seeing is believing" paradigm 1. Despite its rich history and well-established position, significant efforts are contemporarily put on developing new imaging modalities enabling enhanced resolution, contrast, depth, speed and information content. Among a suite of modern microscopy techniques, quantitative phase imaging (QPI) 2-4 stands out as a vividly blossoming label-free approach. It provides unique means for imaging cells and tissues merging beneficial features identified with microscopy 1 , interferometry and holography 5 , and numerical computations. Using refractive index as the endogenous contrast agent 6,7 QPI numerically converts recorded interference pattern into a nanoscale-precise subcellular-specific map of optical delay introduced by examined transparent specimen 7-9. This non-phototoxic non-destructive imaging technique brings biology and metrology closer as it generates quantitative maps of analyzed live bio-structure (related to cell mass, volume, surface area, and their evolutions in time). Therefore, QPI enables upgrading phase-contrast based 6 visualization of the sample to stain-free non-invasive measurement of sample-induced optical phase delay (related to refractive index and/or thickness variations). Impressive details can be imaged, e.g., via super-resolut...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Variational Hilbert Quantitative Phase Imaging

Trusiak

Cywińska

Micó

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…is novel method includes a deep learning system in which the coded aperture is put as a first convolution layer is linked to the coded aperture and the reconstruction network. In [25], the authors proposed a novel algorithm denosing fringe patterns. e proposed algorithm recovers high-quality fringe patterns compared with other denosing algorithms.…”

Section: Literature Reviewmentioning

confidence: 99%

GAN-Holo: Generative Adversarial Networks-Based Generated Holography Using Deep Learning

Khan

Zhang

et al. 2021

Complexity

Self Cite

View full text Add to dashboard Cite

Current development in a deep neural network (DNN) has given an opportunity to a novel framework for the reconstruction of a holographic image and a phase recovery method with real-time performance. There are many deep learning-based techniques that have been proposed for the holographic image reconstruction, but these deep learning-based methods can still lack in performance, time complexity, accuracy, and real-time performance. Due to iterative calculation, the generation of a CGH requires a long computation time. A novel deep generative adversarial network holography (GAN-Holo) framework is proposed for hologram reconstruction. This novel framework consists of two phases. In phase one, we used the Fresnel-based method to make the dataset. In the second phase, we trained the raw input image and holographic label image data from phase one acquired images. Our method has the capability of the noniterative process of computer-generated holograms (CGHs). The experimental results have demonstrated that the proposed method outperforms the existing methods.

show abstract

“…A number of other investigations [ 31 , 32 , 33 , 34 , 35 ] have also shown promising results on using the CNN models to improve the estimation and determination of phase distributions. In addition, various techniques have been proposed to reduce the noise in fringe pattern analysis using deep learning schemes [ 36 , 37 , 38 ].…”

Section: Introductionmentioning

confidence: 99%

Single-Shot 3D Shape Reconstruction Using Structured Light and Deep Convolutional Neural Networks

Nguyen

Wang

2020

Sensors

104

View full text Add to dashboard Cite

Single-shot 3D imaging and shape reconstruction has seen a surge of interest due to the ever-increasing evolution in sensing technologies. In this paper, a robust single-shot 3D shape reconstruction technique integrating the structured light technique with the deep convolutional neural networks (CNNs) is proposed. The input of the technique is a single fringe-pattern image, and the output is the corresponding depth map for 3D shape reconstruction. The essential training and validation datasets with high-quality 3D ground-truth labels are prepared by using a multi-frequency fringe projection profilometry technique. Unlike the conventional 3D shape reconstruction methods which involve complex algorithms and intensive computation to determine phase distributions or pixel disparities as well as depth map, the proposed approach uses an end-to-end network architecture to directly carry out the transformation of a 2D image to its corresponding 3D depth map without extra processing. In the approach, three CNN-based models are adopted for comparison. Furthermore, an accurate structured-light-based 3D imaging dataset used in this paper is made publicly available. Experiments have been conducted to demonstrate the validity and robustness of the proposed technique. It is capable of satisfying various 3D shape reconstruction demands in scientific research and engineering applications.

show abstract

Fringe pattern denoising based on deep learning

Cited by 144 publications

References 18 publications

Variational Hilbert Quantitative Phase Imaging

Variational Hilbert Quantitative Phase Imaging

GAN-Holo: Generative Adversarial Networks-Based Generated Holography Using Deep Learning

Single-Shot 3D Shape Reconstruction Using Structured Light and Deep Convolutional Neural Networks

Contact Info

Product

Resources

About