Deep learning in optical metrology: a review

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.

Multilevel threshold image segmentation for COVID-19 chest radiography: A framework using horizontal and vertical multiverse optimization

“…6 . A fair comparison is a well-accepted rule in the optimization and machine learning community, which we also followed in these experiments [ [124] , [125] , [126] , [127] ]. These fair rules can guarantee that the experiments are done under the same settings, and there is no bias towards a specific method in competition [ [128] , [129] , [130] ].…”

Deflectometry for specular surfaces: an overview

“…As with many other applications of ANNs, it remains unclear to which extent the models trained in a given constellation with certain objects can be transferred to different problems. Presently we leave these methods out of the discussion until their "generalization power" [138] is understood better.…”

PSOWNNs-CNN: A Computational Radiology for Breast Cancer Diagnosis Improvement Based on Image Processing Using Machine Learning Methods

“…Sharifi et al [ 41 ] shown how to diagnose tired and untired feet using digital footprint images. According to Zuo et al [ 42 ], deep-learning technologies have improved optical metrology in recent years. He et al [ 43 ] introduced a number of feature selection techniques for reducing the dimensionality of data.…”