MDD-Net: A generalized network for speckle removal with structure protection and shape preservation for various kinds of ESPI fringe patterns

Xu, Min; Tang, Chen; Hong, Nian; Lei, Zhenkun

doi:10.1016/j.optlaseng.2022.107017

Cited by 5 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FPD-CNN method provides superior denoising performance for fringe patterns with varying densities. In 2022, Wang et al [24] To improve the generalization ability of the model, in 2022, Xu et al from Tianjin University [25] constructed an MDD-Net network model using a skip connection method to filter various types of ESPI fringe patterns. The team applied this method to the measurement of the out-of-plane displacement of thermal changes in PCB boards, and its measurement accuracy can reach the nanometer level.…”

Section: Application Of Deep Learning In Espi Fringe Pattern Filteringmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning in the Phase Extraction of Electronic Speckle Pattern Interferometry

Jiang,

Ren,

2024

Electronics

View full text Add to dashboard Cite

Electronic speckle pattern interferometry (ESPI) is widely used in fields such as materials science, biomedical research, surface morphology analysis, and optical component inspection because of its high measurement accuracy, broad frequency range, and ease of measurement. Phase extraction is a critical stage in ESPI. However, conventional phase extraction methods exhibit problems such as low accuracy, slow processing speed, and poor generalization. With the continuous development of deep learning in image processing, the application of deep learning in phase extraction from electronic speckle interferometry images has become a critical topic of research. This paper reviews the principles and characteristics of ESPI and comprehensively analyzes the phase extraction processes for fringe patterns and wrapped phase maps. The application, advantages, and limitations of deep learning techniques in filtering, fringe skeleton line extraction, and phase unwrapping algorithms are discussed based on the representation of measurement results. Finally, this paper provides a perspective on future trends, such as the construction of physical models for electronic speckle interferometry, improvement and optimization of deep learning models, and quantitative evaluation of phase extraction quality, in this field.

show abstract

Section: Application Of Deep Learning In Espi Fringe Pattern Filteringmentioning

confidence: 99%

“…13, x FOR PEER REVIEW 8 of 25ESPI fringe patterns, SOOPDE, WFF, BL-Hilbert-L2, FDD-Net, and MDD-Net methods, respectively)[25].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in the Phase Extraction of Electronic Speckle Pattern Interferometry

Jiang,

Ren,

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…The network was trained using a paired dataset. Xu et al [30] used a multi-dilated dense network (MDD-Net) for speckle denoising in images acquired using electronic speckle pattern interferometry. The key feature of MDD-Net is the inclusion of a multi-dilated dense module, which comprises a dilated convolution, batch normalization unit, and ReLU activation.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised speckle denoising in digital holographic interferometry based on 4-f optical simulation integrated cycle-consistent generative adversarial network

Yu,

Fang,

Song

et al. 2024

Appl. Opt.

View full text Add to dashboard Cite

The speckle noise generated during digital holographic interferometry (DHI) is unavoidable and difficult to eliminate, thus reducing its accuracy. We propose a self-supervised deep-learning speckle denoising method using a cycle-consistent generative adversarial network to mitigate the effect of speckle noise. The proposed method integrates a 4-f optical speckle noise simulation module with a parameter generator. In addition, it uses an unpaired dataset for training to overcome the difficulty in obtaining noise-free images and paired data from experiments. The proposed method was tested on both simulated and experimental data, with results showing a 6.9% performance improvement compared with a conventional method and a 2.6% performance improvement compared with unsupervised deep learning in terms of the peak signal-to-noise ratio. Thus, the proposed method exhibits superior denoising performance and potential for DHI, being particularly suitable for processing large datasets.

show abstract

“…30,31 Further, Navabian et al, 32 described shearlet-transform based antcolony optimization for despeckling IVUS images using three thresholds. Deep learning has become prevalent in recent years for dealing with speckle removal in various domains such as ESPI fringe patterns, 33 synthetic aperture radar images, 34 and medical images. [35][36][37] Despite being applied for multiple domains, a recent review by Ilesanmi et al, 38 concluded that very few deep learningbased algorithms are employed for denoising the medical images due to the difficulty in tackling unsupervised learning challenges and the non-availability of large number of noise-free images as data labels .…”

Section: Introductionmentioning

confidence: 99%

Performance analysis of various denoising filters on intravascular ultrasound coronary artery images

Arora

Singh

Girdhar

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

MDD-Net: A generalized network for speckle removal with structure protection and shape preservation for various kinds of ESPI fringe patterns

Cited by 5 publications

References 50 publications

Deep Learning in the Phase Extraction of Electronic Speckle Pattern Interferometry

Deep Learning in the Phase Extraction of Electronic Speckle Pattern Interferometry

Unsupervised speckle denoising in digital holographic interferometry based on 4-f optical simulation integrated cycle-consistent generative adversarial network

Performance analysis of various denoising filters on intravascular ultrasound coronary artery images

Contact Info

Product

Resources

About