Deep learning on image denoising: An overview.

Recent advances in deep learning have given rise to a new paradigm of holographic image reconstruction and phase recovery techniques with real-time performance. Through data-driven approaches, these emerging techniques have overcome some of the challenges associated with existing holographic image reconstruction methods while also minimizing the hardware requirements of holography. These recent advances open up a myriad of new opportunities for the use of coherent imaging systems in biomedical and engineering research and related applications.

/pdf/deep-learning-in-holography-and-coherent-imaging-4czrbo3sl4.pdf

Deep learning in holography and coherent imaging.

Abstract With the advances in scientific foundations and technological implementations, optical metrology has become versatile problem-solving backbones in manufacturing, fundamental research, and engineering applications, such as quality control, nondestructive testing, experimental mechanics, and biomedicine. In recent years, deep learning, a subfield of machine learning, is emerging as a powerful tool to address problems by learning from data, largely driven by the availability of massive datasets, enhanced computational power, fast data storage, and novel training algorithms for the deep neural network. It is currently promoting increased interests and gaining extensive attention for its utilization in the field of optical metrology. Unlike the traditional “physics-based” approach, deep-learning-enabled optical metrology is a kind of “data-driven” approach, which has already provided numerous alternative solutions to many challenging problems in this field with better performances. In this review, we present an overview of the current status and the latest progress of deep-learning technologies in the field of optical metrology. We first briefly introduce both traditional image-processing algorithms in optical metrology and the basic concepts of deep learning, followed by a comprehensive review of its applications in various optical metrology tasks, such as fringe denoising, phase retrieval, phase unwrapping, subset correlation, and error compensation. The open challenges faced by the current deep-learning approach in optical metrology are then discussed. Finally, the directions for future research are outlined. 

/pdf/deep-learning-in-optical-metrology-a-review-2ggtgtrp.pdf

Deep learning in optical metrology: a review

The Plane Wave Spectrum Representation of Electromagnetic Fields

In recent years, deep learning has been shown to be one of the leading machine learning techniques for a wide variety of inference tasks. In addition to its mainstream applications, such as classification, it has created transformative opportunities for image reconstruction and enhancement in optical microscopy. Some of these emerging applications of deep learning range from image transformations between microscopic imaging systems to adding new capabilities to existing imaging techniques, as well as solving various inverse problems based on microscopy image data. Deep learning is helping us move toward data-driven instrument designs that blend microscopy and computing to achieve what neither can do alone. This article provides an overview of some of the recent work using deep neural networks to advance computational microscopy and sensing systems, also covering their current and future biomedical applications.

/pdf/deep-learning-based-image-reconstruction-and-enhancement-in-1vq4u5f2st.pdf

Deep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy

In this Letter, we propose a fast speckle noise reduction method with only a single reconstructed image based on convolutional neural networks. The proposed network has multi-sized kernels that can capture the speckle noise component effectively from digital holographic images. For robust noise reduction performance, the network is trained with a large noisy image dataset that has object-dependent noise and a wide range of noise levels. The experimental results show the fast, robust, and outstanding speckle noise reduction performance of the proposed approach.

Speckle noise reduction for digital holographic images using multi-scale convolutional neural networks.

Slag foaming is a key factor in terms of quality and productivity in the electric arc furnace (EAF) steelmaking process. Optimal control of slag foaming is required, but is difficult due to the absence of practical on-line measuring methods and the broad process variability. In this study, a soft sensor model, which correlates the influential process variables with the slag foaming height, was developed by using machine learning based long short-term memory (LSTM) networks for modeling sequential and nonlinear data. The developed model was validated using actual steelmaking dataset in terms of performance metrics such as the root mean square error (RMSE), coefficient of determination (R2), and correlation coefficient corresponding to a value for a SS400 carbon steel grade to be 42.3, 0.905, and 0.963, respectively. In order to evaluate the general applicability of the developed model for other steel grades, data for A615 and S355 steel grades were also applied and found to satisfy the benchmark standards indicating that the developed model can be applied to the broad range of other steel grades. Sensitivity-based Pruning (SBP) on the model shows that electricity, carbon and oxygen are the most influential process variables to the slag foaming height and could potentially be used to promote enhanced optimization in terms of energy saving and cost-efficiency for the EAF steelmaking process.

Slag foaming estimation in the electric arc furnace using machine learning based long short-term memory networks

Slag foaming directly affects the productivity and quality of steel during the electric arc furnace (EAF) process. Therefore, the slag foaming height needs to be monitored in real-time. However, direct measurement of the slag foaming height is difficult to achieve because the inside of the EAF consists of harsh environments, i.e., high temperature and the presence of gas and dust. A stepwise regression model of the slag foaming height was created using sensor data from the EAF. A total of 272 operational data sets from the EAF process were used to develop and validate the regression model. This data came from 140ton DC-EAF of Dongkuk Steel in Pohang, Korea. We randomly selected 80% of the data for developing the regression model; the remaining 20% of data were used for model validation. The model was validated using the validation benchmark coefficient of determination (R2) and correlation coefficients. As a result, the important variables of slag foaming were statistically selected a priori. Using the regression model, the slag foaming height can be predicted without additional sensors. Based on the developed model, the effects of oxygen injection and carbon injection on the slag foaming height of EAF were predicted and are discussed herein.

Modeling of slag foaming height of electric arc furnace using stepwise regression analysis

We have focused on rapid and efficient estimator to find object distance from hologram in order to reconstruct original image. Our approach to find it makes the estimator pre-trained through deep learning. Especially in off-axis holography configuration, our method eliminates the unnecessary factors and reduces information loss occurred by resizing image to plug into Convolution Neural Network (CNN). Training is performed on the generated images at several specific distances under various optical conditions and the accuracy of estimation is validated.

Autofocusing using deep learning in off-axis digital holography

https://iopscience.iop.org/article/10.7567/JJAP.57.09SB02/pdf

Kyungchan Son

Papers

Speckle noise reduction for digital holographic images using multi-scale convolutional neural networks.

Slag foaming estimation in the electric arc furnace using machine learning based long short-term memory networks

Modeling of slag foaming height of electric arc furnace using stepwise regression analysis

Autofocusing using deep learning in off-axis digital holography

Autofocusing algorithm for a digital holographic imaging system using convolutional neural networks