Deep learning in optical metrology: a review (2022-02-23T00:00:00.000000Z)

TL;DR

An overview of the current status and the latest progress of deep-learning technologies in the field of optical metrology is presented, 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.

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.

Authors

Chao Zuo

1 papers

Jiaming Qian

3 papers

Shijie Feng

3 papers

TL;DR

Abstract

Authors

References459 items

Three-dimensional Shape Reconstruction from Single-shot Speckle Image Using Deep Convolutional Neural Networks

Phase error compensation based on Tree-Net using deep learning

A multi-code 3D measurement technique based on deep learning

Highlighting photonics: looking into the next decade

Generalized framework for non-sinusoidal fringe analysis using deep learning

Large-scale phase retrieval

Single-shot 3D shape measurement using an end-to-end stereo matching network for speckle projection profilometry.

Optimized loss function in deep learning profilometry for improved prediction performance

Deep neural network for fringe pattern filtering and normalization.

Coding-Net: A multi-purpose neural network for Fringe Projection Profilometry

Concept, implementations and applications of Fourier ptychography

High-resolution real-time 360∘ 3D surface defect inspection with fringe projection profilometry

Single-shot fringe projection profilometry based on Deep Learning and Computer Graphics

Transport of intensity equation: a tutorial

Fringe denoising algorithms: A review

A single-shot phase retrieval method for phase measuring deflectometry based on deep learning

Recognition of wavefront aberrations types corresponding to single Zernike functions from the pattern of the point spread function in the focal plane using neural networks

Fringe projection profilometry by conducting deep learning from its digital twin.

Comparison of crack segmentation using digital image correlation measurements and deep learning

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

High-speed high dynamic range 3D shape measurement based on deep learning

Composite deep learning framework for absolute 3D shape measurement based on single fringe phase retrieval and speckle correlation

Non-destructive hand vein measurement with self-supervised binocular network

Single-shot spatial frequency multiplex fringe pattern for phase unwrapping using deep learning

Gamma correction by using deep learning

Temporal phase unwrapping with a lightweight deep neural network

Real-time, wide-field and high-quality single snapshot imaging of optical properties with profile correction using deep learning.

Quantitative phase imaging in dual-wavelength interferometry using a single wavelength illumination and deep learning.

When Deep Learning Meets Digital Image Correlation

On the use of deep learning for computational imaging

Random two-frame interferometry based on deep learning.

Y4-Net: a deep learning solution to one-shot dual-wavelength digital holographic reconstruction.

Deep learning-based fringe modulation-enhancing method for accurate fringe projection profilometry.

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

Deep learning assisted Shack-Hartmann wavefront sensor for direct wavefront detection.

End-to-end deep learning-based fringe projection framework for 3D profiling of objects

Deep learning based method for phase analysis from a single closed fringe pattern

Deep Learning-Based Wrapped Phase Denoising Method for Application in Digital Holographic Speckle Pattern Interferometry

A brief review of the technological advancements of phase measuring deflectometry

A Matrix Algebra Approach to Artificial Intelligence

Phase imaging with an untrained neural network

Wrapped phase denoising using convolutional neural networks

Speckle Reconstruction with Corruption through Multimode Fibers using Deep Learning

Intensity-enhanced deep network wavefront reconstruction in Shack-Hartmann sensors.

Single-shot absolute 3D shape measurement with deep-learning-based color fringe projection profilometry.

Deep Phase Shifter for Quantitative Phase Imaging

PhaseNet 2.0: Phase Unwrapping of Noisy Data Based on Deep Learning Approach

Computational de-noising based on deep learning for phase data in digital holographic interferometry

Deep-learning-enabled geometric constraints and phase unwrapping for single-shot absolute 3D shape measurement

Single-shot phase extraction for fringe projection profilometry using deep convolutional generative adversarial network

Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach

Single-shot isotropic quantitative phase microscopy based on color-multiplexed differential phase contrast

Learned sensing: jointly optimized microscope hardware for accurate image classification.

Structural light 3D reconstruction algorithm based on deep learning

High-speed 3D shape measurement with the multi-view system using deep learning

Learning-based Shack-Hartmann wavefront sensor for high-order aberration detection.

Strain measurement during tensile testing using deep learning-based digital image correlation

Y-Net: a one-to-two deep learning framework for digital holographic reconstruction.

Micro deep learning profilometry for high-speed 3D surface imaging

Label enhanced and patch based deep learning for phase retrieval from single frame fringe pattern in fringe projection 3D measurement.

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

Unsupervised Domain Adaptation for Depth Prediction from Images

Real-time 3D shape measurement using 3LCD projection and deep machine learning.

Phase Extraction from Single Interferogram Including Closed-Fringe Using Deep Learning

Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging.

A learning method to optimize depth accuracy and frame rate for Time of Flight camera

Rapid and robust two-dimensional phase unwrapping via deep learning.

No-search focus prediction at the single cell level in digital holographic imaging with deep convolutional neural network.

Non-destructive three-dimensional measurement of hand vein based on self-supervised network

Dynamic 3-D measurement based on fringe-to-fringe transformation using deep learning.

Deep neural networks for single shot structured light profilometry.

Multi-Level Context Ultra-Aggregation for Stereo Matching

Hierarchical Deep Stereo Matching on High-Resolution Images

LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation

Learning to Minify Photometric Stereo

Phase unwrapping in optical metrology via denoised and convolutional segmentation networks.