Performance of Autofocus Capability of Deep Convolutional Neural Networks in Digital Holographic Microscopy

Pitkäaho, Tomi; Manninen, Aki; Naughton, Thomas J.

doi:10.1364/dh.2017.w2a.5

Cited by 20 publications

(20 citation statements)

References 7 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pioneer work of depth prediction in digital holography was presented by T. Pitkäaho, A. Manninen and T. J. Naughton [17], [18]. The difference between the proposed method and those applied in previous studies [17], [18] is that in these studies, the depth prediction was solved as a classification problem, so that the predicted depth becomes a discrete value. On the other hand, since the proposed method solves the problem as a multiple regression, the predicted depth becomes a continuous value.…”

Section: Proposed Methodsmentioning

confidence: 99%

Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography

Shimobaba

Kakue

Ito

2018

2018 IEEE 27th International Symposium on Industrial Electronics (ISIE)

View full text Add to dashboard Cite

Digital holography enables us to reconstruct objects in three-dimensional space from holograms captured by an imaging device. For the reconstruction, we need to know the depth position of the recoded object in advance. In this study, we propose depth prediction using convolutional neural network (CNN)-based regression. In the previous researches, the depth of an object was estimated through reconstructed images at different depth positions from a hologram using a certain metric that indicates the most focused depth position; however, such a depth search is time-consuming. The CNN of the proposed method can directly predict the depth position with millimeter precision from holograms.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography

Shimobaba

Kakue

Ito

2018

2018 IEEE 27th International Symposium on Industrial Electronics (ISIE)

View full text Add to dashboard Cite

show abstract

“…The 3D image formation properties of phase retrieval have also been investigated as depth prediction with robust automatic focusing [241,242], image reconstruction with a single-shot in-line hologram [243], extended depth of field [244,245], and transparent 3D sample reconstruction from diffraction images obtained at multiple angles (phase tomography) [246]. In the results shown in Fig.…”

Section: B Quantitative Phase Retrieval and Lensless Imagingmentioning

confidence: 99%

On the use of deep learning for computational imaging

Barbastathis

Ozcan

Situ

2019

Optica

583

225

View full text Add to dashboard Cite

Since their inception in the 1930-1960s, the research disciplines of computational imaging and machine learning have followed parallel tracks and, during the last two decades, experienced explosive growth drawing on similar progress in mathematical optimization and computing hardware. While these developments have always been to the benefit of image interpretation and machine vision, only recently has it become evident that machine learning architectures, and deep neural networks in particular, can be effective for computational image formation, aside from interpretation. The deep learning approach has proven to be especially attractive when the measurement is noisy and the measurement operator ill posed or uncertain. Examples reviewed here are: super-resolution; lensless retrieval of phase and complex amplitude from intensity; photon-limited scenes, including ghost imaging; and imaging through scatter. In this paper, we cast these works in a common framework. We relate the deep-learning-inspired solutions to the original computational imaging formulation and use the relationship to derive design insights, principles, and caveats of more general applicability. We also explore how the machine learning process is aided by the physics of imaging when ill posedness and uncertainties become particularly severe. It is hoped that the present unifying exposition will stimulate further progress in this promising field of research.

show abstract

“…Rivenson et al have proposed a holographic image reconstruction method based on the convolutional neural network (CNN) that can reconstruct the phase and amplitude of images of objects using only a hologram [ 25 ]. Pitkaaho et al have employed the CNN to focus on automatic distance calculation in holographic image reconstruction [ 26 ]. Wang et al have proposed a one-step end-to-end learning-based method for in-line holographic reconstruction that creates a network called eHoIoNet to avoid phase shifting [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

A Fringe Phase Extraction Method Based on Neural Network

Miao

Yan

et al. 2021

Sensors

View full text Add to dashboard Cite

In optical metrology, the output is usually in the form of a fringe pattern, from which a phase map can be generated and phase information can be converted into the desired parameters. This paper proposes an end-to-end method of fringe phase extraction based on the neural network. This method uses the U-net neural network to directly learn the correspondence between the gray level of a fringe pattern and the wrapped phase map, which is simpler than the exist deep learning methods. The results of simulation and experimental fringe patterns verify the accuracy and the robustness of this method. While it yields the same accuracy, the proposed method features easier operation and a simpler principle than the traditional phase-shifting method and has a faster speed than wavelet transform method.

show abstract

Performance of Autofocus Capability of Deep Convolutional Neural Networks in Digital Holographic Microscopy

Abstract: Autofocusing of digital holograms of microscopic objects is a challenging problem. In this paper, an application of a deep learning in autofocusing is described. Its generalisation performance is analyzed.

Cited by 20 publications

References 7 publications

Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography

Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography

On the use of deep learning for computational imaging

A Fringe Phase Extraction Method Based on Neural Network

Contact Info

Product

Resources

About