4.5 Article

Deep learning assisted non-contact defect identification method using diffraction phase microscopy

Related references

Note: Only part of the references are listed.
Article Optics

Identification of defects in composite laminates by comparison of mode shapes from electronic speckle pattern interferometry

X. N. Li et al.

Summary: A new technique for identifying defects in carbon fibre reinforced plates has been developed. Modal analysis and amplitude-fluctuation electronic speckle pattern interferometry were used to obtain resonant frequencies and mode shapes. A specially-developed algorithm and Fourier descriptors were used for contour extraction and dimensionality reduction, respectively. The differences in contours between defect-free and defective specimens showed that certain mode shapes can be used for identifying the presence of waviness defects.

OPTICS AND LASERS IN ENGINEERING (2023)

Article Optics

Deep learning based single shot multiple phase derivative retrieval method in multi-wave digital holographic interferometry

Allaparthi Venkata Satya Vithin et al.

Summary: In this paper, a deep learning approach is proposed to directly extract multiple phase derivative information in digital holographic interferometry, even in the presence of severe noise, without the need for multiple phase-shifted frames, dedicated experimental control and numerical operations.

OPTICS AND LASERS IN ENGINEERING (2023)

Article Optics

Noise free defect detection in ceramic tableware using a portable digital holographic camera

Lavlesh Pensia et al.

Summary: This paper describes the detection of cracks in ceramic tableware using a portable digital holographic camera. Digital image processing techniques are applied to the amplitude and phase information obtained from numerically reconstructed wavefronts to locate the position of defects. The study analyzes the effect of kernel size on the quality of the interferometric phase and suggests using an averaging filter to minimize speckle noise. The experimentally obtained crack size on a ceramic cup is validated with a mechanical profiler. This study has implications for improving the quality criteria of tableware items.

APPLIED OPTICS (2022)

Article Mechanics

Shearography non-destructive testing of thick GFRP laminates: Numerical and experimental study on defect detection with thermal loading

Nan Tao et al.

Summary: This paper investigates the defect detection capabilities of shearography for inspecting thick glass fiber-reinforced polymer laminates. Both finite element simulations and experimental tests are conducted to determine the thresholds and influence factors of shearography for thick composite inspection.

COMPOSITE STRUCTURES (2022)

Article Optics

Phase derivative estimation in digital holograph interferometry using a deep learning approach

Allaparthi Venkata Satya Vithin et al.

Summary: In this paper, a deep learning-based approach is proposed for direct estimation of phase derivatives in digital holographic interferometry. The robustness and practical utility of the proposed method are demonstrated through numerical simulations and experimental data.

APPLIED OPTICS (2022)

Article Engineering, Multidisciplinary

Optical nondestructive evaluation for minor debonding defects and interfacial adhesive strength of solid propellant

Bin Liu et al.

Summary: This study proposes a real-time phase processing method to detect minor debonding defects and evaluate interfacial adhesive strengths in shearography/ESPI optical nondestructive measurement systems. The stable and high-contrast phase maps obtained through this method enhance the detection capabilities of shearography/ESPI.

MEASUREMENT (2022)

Review Optics

Deep learning in optical metrology: a review

Chao Zuo et al.

Summary: Optical metrology, with the advances in deep learning technologies, has become a versatile problem-solving tool in various fields such as manufacturing, fundamental research, and engineering applications. This review provides an overview of the current status and latest progress of deep learning in optical metrology, covering applications in tasks like fringe denoising, phase retrieval, and error compensation. The challenges and future research directions are also discussed.

LIGHT-SCIENCE & APPLICATIONS (2022)

Article Optics

Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization

Hanlong Chen et al.

Summary: This study introduces a deep learning framework called Fourier Imager Network (FIN) that performs end-to-end phase recovery and image reconstruction from raw holograms of new types of samples. The FIN architecture, based on spatial Fourier transform modules, exhibits superior generalization to new types of samples and faster image inference speed.

LIGHT-SCIENCE & APPLICATIONS (2022)

Article Optics

Subspace analysis based machine learning method for automated defect detection from fringe patterns

Dhruvam Pandey et al.

Summary: We propose a reliable and robust defect detection method from the noisy fringe patterns obtained in optical interferometry. The proposed method utilizes a naive Bayes classifier based machine learning model, using phase derivatives computed using fringe signal subspace analysis as feature vectors to achieve automated defect identification without the need for manual threshold selection. Simulation analysis of various types of defects and experimental fringes obtained in diffraction phase microscopy validate the practical applicability of the proposed method.

OPTIK (2022)

Article Optics

Deep neural network for fringe pattern filtering and normalization

Alan Reyes-Figueroa et al.

Summary: This paper introduces a new framework for processing fringe patterns using deep neural networks, proposing the use of U-net and V-net models for denoising and normalization tasks. Extensive experimental evidence shows the high-quality results of the V-net model in FP filtering and normalization, with potential improvements seen in modifications such as the ResV-net and fast operating version.

APPLIED OPTICS (2021)

Article Optics

Automated defect identification from carrier fringe patterns using Wigner-Ville distribution and a machine learning-based method

Ankur Vishnoi et al.

Summary: This study introduces a method for automated defect identification from fringe patterns using a supervised machine learning algorithm, which enables robust detection of defect patterns and alleviates limitations associated with thresholding-based techniques. The potential and practical applicability of the proposed method are demonstrated through numerical simulations and experimental results.

APPLIED OPTICS (2021)

Article Optics

Generalized framework for non-sinusoidal fringe analysis using deep learning

Shijie Feng et al.

Summary: The study introduces a deep learning technique to analyze fringe images resulting from various non-sinusoidal factors and even their coupling. By training deep neural networks, it effectively suppresses phase errors caused by different types of non-sinusoidal patterns.

PHOTONICS RESEARCH (2021)

Article Optics

Fringe pattern denoising based on deep learning

Ketao Yan et al.

OPTICS COMMUNICATIONS (2019)

Article Engineering, Multidisciplinary

Graphics processing unit assisted diffraction phase microscopy for fast non-destructive metrology

Jagadesh Ramaiah et al.

MEASUREMENT SCIENCE AND TECHNOLOGY (2019)

Article Multidisciplinary Sciences

Temporal phase unwrapping using deep learning

Wei Yin et al.

SCIENTIFIC REPORTS (2019)

Article Physics, Multidisciplinary

Defect detection using windowed Fourier spectrum analysis in diffraction phase microscopy

Sreeprasad Ajithaprasad et al.

JOURNAL OF PHYSICS COMMUNICATIONS (2019)

Review Optics

Parallel computing in experimental mechanics and optical measurement: A review (II)

Tianyi Wang et al.

OPTICS AND LASERS IN ENGINEERING (2018)

Article Optics

Diffraction phase microscopy: principles and applications in materials and life sciences

Basanta Bhaduri et al.

ADVANCES IN OPTICS AND PHOTONICS (2014)

Article Materials Science, Multidisciplinary

Interference fringe-patterns association to defect-types in artwork conservation: an experiment and research validation review

Vivi Tornari et al.

APPLIED PHYSICS A-MATERIALS SCIENCE & PROCESSING (2012)

Article Optics

Detection of defects from fringe patterns using a pseudo-Wigner-Ville distribution based method

Gannavarpu Rajshekhar et al.

OPTICS AND LASERS IN ENGINEERING (2012)

Review Optics

Parallel computing in experimental mechanics and optical measurement: A review

Wenjing Gao et al.

OPTICS AND LASERS IN ENGINEERING (2012)

Article Optics

Fringe analysis and enhanced characterization of sub-surface defects using fringe-shifted shearograms

Francesca Celine I. Catalan et al.

OPTICS COMMUNICATIONS (2012)

Article Computer Science, Artificial Intelligence

An introduction to ROC analysis

Tom Fawcett

PATTERN RECOGNITION LETTERS (2006)

Article Engineering, Multidisciplinary

Fault detection by interferometric fringe pattern analysis using windowed Fourier transform

KM Qian et al.

MEASUREMENT SCIENCE AND TECHNOLOGY (2005)

Review Materials Science, Multidisciplinary

Shearography: An optical measurement technique and applications

YY Hung et al.

MATERIALS SCIENCE & ENGINEERING R-REPORTS (2005)

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)