4.7 Article

Digital image correlation based on convolutional neural networks

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Engineering, Biomedical

Spontaneous formation and spatial self-organization of mechanically induced mesenchymal-like cells within geometrically confined cancer cell monolayers

Feng Lin et al.

Summary: There is spatiotemporal heterogeneity in cell phenotypes and mechanical properties in tumor tissues, which is associated with cancer invasion and metastasis. The study reveals that mechanics heterogeneity alone is enough to spontaneously induce the emergence of mesenchymal-like phenotype and asymmetrical activation of TGF-13-SMAD signaling. This highlights the key role of mechanical cues in triggering phenotypic switch of cancer cells.

BIOMATERIALS (2022)

Article Materials Science, Multidisciplinary

Adaptive Rotated Gaussian Weighted Digital Image Correlation (RGW-DIC) for Heterogeneous Deformation Measurement

X. Ye et al.

Summary: DIC has become a flexible, reliable, and fast optical method for non-contact and full-field surface deformation measurement. However, current methods still need improvement in accurately measuring heterogeneous deformation fields, especially high gradient strain fields. A new approach using RGW-DIC with automatically determined subset weight distribution has been proposed to significantly improve accuracy in measuring severely heterogeneous deformation.

EXPERIMENTAL MECHANICS (2022)

Article Optics

An algorithm for structural health monitoring by digital image correlation: Proof of concept and case study

Jordan Curt et al.

Summary: This paper presents the advantages of using Digital Image Correlation (DIC) in the field of structural health monitoring and proposes a specific DIC technique. By training, a reduced kinematic basis and amplitude distribution can be determined, and non-iterative processing is achieved using filtering and extractors.

OPTICS AND LASERS IN ENGINEERING (2022)

Article Optics

Full-field strain measurement using optimal path search method with error control

J. P. Chen et al.

Summary: Digital image correlation (DIC) is an important optical measurement method for strain fields, but little discussion has been done on calculation errors in positions with abrupt change. This study proposes an optimal path search method (OPSM) to reduce full-field strain calculation errors and improve accuracy, showing effectiveness in obtaining full-field strain information, especially in positions with abrupt displacement changes. OPSM application in a cellular structure compression experiment validates the method's capability to suppress noise and approximate results to true values in zones with abrupt displacement changes.

OPTICS AND LASERS IN ENGINEERING (2022)

Article Engineering, Multidisciplinary

Adjusting fictitious domain parameters for fairly priced image-based modeling: Application to the regularization of Digital Image Correlation

Ali Rouwane et al.

Summary: The integration of numerical simulation and experimental measurements at the sub-cellular scale in cellular materials poses a real challenge. It involves solving the difficulties in displacement fields measurement on the experimental side and constructing reliable and specimen-specific geometric and mechanical models from digital images on the simulation side. Adjusting discretization parameters to strike a balance between accuracy and computational cost is key in the analysis.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

Article Engineering, Multidisciplinary

Free-Form Deformation Digital Image Correlation (FFD-DIC): A non-invasive spline regularization for arbitrary finite element measurements

M. Chapelier et al.

Summary: Regularizing Finite-Element Digital Image Correlation (FE-DIC) problems is essential for using fine meshes, and a new spline-based non-invasive regularization scheme based on the Free-Form Deformation (FFD) concept is proposed in this study. The method embeds the input FE mesh into a cuboid B-spline box to decouple the design space from the actual geometry, resulting in a regularized but conventional FE measured field.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2021)

Article Optics

When Deep Learning Meets Digital Image Correlation

S. Boukhtache et al.

Summary: This paper introduces the development of a CNN model (StrainNet) for retrieving displacement and strain fields from pairs of images of a flat speckled surface, and demonstrates its successful performance of measurements. Compared to DIC, StrainNet achieves competitive results in terms of metrological performance and computing time, making it a viable alternative for real-time applications.

OPTICS AND LASERS IN ENGINEERING (2021)

Review Optics

Deformation measurement in the presence of discontinuities with digital image correlation: A review

Ghulam Mubashar Hassan

Summary: Digital Image Correlation (DIC) has been successful in measuring deformation remotely, but has limitations in measuring discontinuous deformation, restricting its application to lab environment. This study systematically analyzes different methodologies to overcome the limitations of DIC and presents future research directions in this area.

OPTICS AND LASERS IN ENGINEERING (2021)

Article Biochemical Research Methods

Displacement and strain mapping for osteocytes under fluid shear stress using digital holographic microscopy and digital image correlation

Runyu Cao et al.

Summary: This study introduced a label-free displacement and strain mapping method based on DHM-DIC to evaluate the deformation of osteocytes under FSS. Experimental results showed good agreement between DHM-DIC and finite element modeling results.

BIOMEDICAL OPTICS EXPRESS (2021)

Article Engineering, Biomedical

Automated evaluation of tumor spheroid behavior in 3D culture using deep learning-based recognition

Zaozao Chen et al.

Summary: The introduction of two new indices and a convolutional neural network-based algorithm offers a more accurate method for evaluating the invasiveness of 3D tumor models.

BIOMATERIALS (2021)

Article Optics

Error analysis of surface-distribution and non-deformation of fluorescent beads for the IC-GN2 DVC algorithm

Shihai Lan et al.

Summary: The text discusses the application of the Digital volume correlation (DVC) method in biomechanical experiments, highlighting the challenges and proposed solutions to improve accuracy and reliability. The introduction of the IC-GN(2) DVC algorithm and the speckle-surface-distributed experimental method address issues like shape function mismatch and phototoxicity. Results indicate high accuracy and reliability of the proposed methods in analyzing cell deformation and migration.

OPTICS AND LASERS IN ENGINEERING (2021)

Article Multidisciplinary Sciences

Deep learning classification of lipid droplets in quantitative phase images

Luke Sheneman et al.

Summary: Researchers successfully applied supervised machine learning to automatic classification of lipid droplets in label-free, quantitative-phase images, with convolutional neural networks outperforming other methods. They found that this imaging approach combined with machine learning enables accurate classification of lipid droplets in single living cells, offering an alternative to more common imaging modalities.

PLOS ONE (2021)

Article Multidisciplinary Sciences

Deep learning-based predictive identification of neural stem cell differentiation

Yanjing Zhu et al.

Summary: The differentiation of neural stem cells into neurons is crucial for potential cell-based therapeutic strategies for CNS diseases. Using deep learning, researchers have developed a reliable model for predicting NSCs fate, demonstrating high precision in identifying differentiated cell types early in culture and applicability across various inducers.

NATURE COMMUNICATIONS (2021)

Article Mathematical & Computational Biology

A Novel Pyramid Network with Feature Fusion and Disentanglement for Object Detection

Guoyi Yu et al.

Summary: This paper proposes a novel approach to address the issues of scale variation and task misalignment in object detection: using multiflow feature fusion module and task adaptive convolution, building a feature pyramid network with feature fusion and disentanglement functionality, which can enhance performance.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2021)

Article Materials Science, Multidisciplinary

Smart Digital Image Correlation Patterns via 3D Printing

J. Yang et al.

Summary: This study introduces a new, robust, and efficient technique for printing DIC speckle dot patterns on both planar and non-planar sample surfaces using a custom-modified 3D printer in an automated fashion. By controlling the extrusion volume and spatial positioning of the print head, accurate patterns can be printed for tracking large and heterogeneous deformations in highly compliant and porous materials, as well as materials with significant 3D topographies. The technique achieves high accuracy in measuring displacements and strains in materials.

EXPERIMENTAL MECHANICS (2021)

Article Biochemistry & Molecular Biology

Interpretable deep learning uncovers cellular properties in label-free live cell images that are predictive of highly metastatic melanoma

Assaf Zaritsky et al.

Summary: The study utilized a generative neural network and supervised machine learning to classify the metastatic efficiency of melanoma cells, revealing characteristic features of metastatic cells and validating these findings with live cell observations. It demonstrates how artificial intelligence can aid in identifying cell properties predictive of complex phenotypes and integrated cell functions that may be subtle and difficult for human experts to identify in raw imagery.

CELL SYSTEMS (2021)

Article Computer Science, Information Systems

Adaptive Feature Pyramid Networks for Object Detection

Chengyang Wang et al.

Summary: An adaptive feature pyramid network is proposed in this paper to address scale variation challenges and feature fusion issues in object detection. By incorporating adaptive feature upsampling and adaptive feature fusion, the model performance is improved, as validated by experimental results.

IEEE ACCESS (2021)

Article Computer Science, Artificial Intelligence

Code-free deep learning for multi-modality medical image classification

Edward Korot et al.

Summary: The analysis compares the performance of six 'code-free deep learning' platforms in creating medical image classification models and finds that they demonstrate higher classification performance with optical coherence tomography modality. Potential use cases include research dataset curation, mobile 'edge models' for regions without internet access, and baseline models for comparing and iterating bespoke deep learning approaches.

NATURE MACHINE INTELLIGENCE (2021)

Article Computer Science, Artificial Intelligence

A versatile deep learning architecture for classification and label-free prediction of hyperspectral images

Bryce Manifold et al.

Summary: Hyperspectral imaging provides rich chemical information and the new U-within-U-Net architecture can effectively process hyperspectral information from various imaging techniques. The architecture shows great potential in advancing the use of hyperspectral imaging across different application areas.

NATURE MACHINE INTELLIGENCE (2021)

Article Mechanics

Optimal procedure for the identification of constitutive parameters from experimentally measured displacement fields

Stephane Roux et al.

INTERNATIONAL JOURNAL OF SOLIDS AND STRUCTURES (2020)

Article Biophysics

New insights on the proximal femur biomechanics using Digital Image Correlation

Yekutiel Katz et al.

JOURNAL OF BIOMECHANICS (2020)

Article Computer Science, Artificial Intelligence

Recent advances in deep learning for object detection

Xiongwei Wu et al.

NEUROCOMPUTING (2020)

Article Engineering, Multidisciplinary

An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications

E. Samaniego et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2020)

Article Computer Science, Artificial Intelligence

Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI

Chunfeng Lian et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Article Engineering, Multidisciplinary

Digital volume correlation technique for characterizing subsurface deformation behavior of a laminated composite

Sooyoung Lee et al.

COMPOSITES PART B-ENGINEERING (2020)

Review Clinical Neurology

Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

Monika A. Myszczynska et al.

NATURE REVIEWS NEUROLOGY (2020)

Article Optics

Remote surface motion measurements using defocused speckle imaging

Juuso Heikkinen et al.

OPTICS AND LASERS IN ENGINEERING (2020)

Article Multidisciplinary Sciences

Tough and tunable scaffold-hydrogel composite biomaterial for soft-to-hard musculoskeletal tissue interfaces

Raul A. Sun Han Chang et al.

SCIENCE ADVANCES (2020)

Article Construction & Building Technology

Flexural deformation characterization of glass panel in curtain walls based on digital image correlation technique

Yuan Yuan et al.

CONSTRUCTION AND BUILDING MATERIALS (2020)

Article Physics, Multidisciplinary

Active wetting of epithelial tissues

Carlos Perez-Gonzalez et al.

NATURE PHYSICS (2019)

Article Materials Science, Multidisciplinary

Full-field Ultrahigh-speed Quantification of Dynamic Shear Ruptures Using Digital Image Correlation

V. Rubino et al.

EXPERIMENTAL MECHANICS (2019)

Article Materials Science, Multidisciplinary

Mapping the nonlinear crack tip deformation field in soft elastomer with a particle tracking method

Yuan Qi et al.

JOURNAL OF THE MECHANICS AND PHYSICS OF SOLIDS (2019)

Review Chemistry, Analytical

Mechanical characterization of single cells based on microfluidic techniques

Jianyong Huang et al.

TRAC-TRENDS IN ANALYTICAL CHEMISTRY (2019)

Article Engineering, Multidisciplinary

The investigation of mechanical properties of a structural adhesive via digital image correlation (DIC) technic

Elanur Celebi Kavdir et al.

COMPOSITES PART B-ENGINEERING (2019)

Article Materials Science, Multidisciplinary

Combining Image Compression with Digital Image Correlation

J. Yang et al.

EXPERIMENTAL MECHANICS (2019)

Article Materials Science, Multidisciplinary

A q-Factor-Based Digital Image Correlation Algorithm (qDIC) for Resolving Finite Deformations with Degenerate Speckle Patterns

A. K. Landauer et al.

EXPERIMENTAL MECHANICS (2018)

Article Computer Science, Information Systems

Recurrent Spatial Pyramid CNN for Optical Flow Estimation

Ping Hu et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2018)

Article Engineering, Multidisciplinary

Three-dimensional digital image correlation with improved efficiency and accuracy

Fu Q. Zhong et al.

MEASUREMENT (2018)

Article Optics

A flexible heterogeneous real-time digital image correlation system

Tianyi Wan et al.

OPTICS AND LASERS IN ENGINEERING (2018)

Article Optics

A morphing-based scheme for large deformation analysis with stereo-DIC

Katia Genovese et al.

OPTICS AND LASERS IN ENGINEERING (2018)

Article Engineering, Multidisciplinary

A domain coupling method for finite element digital image correlation with mechanical regularization: Application to multiscale measurements and parallel computing

Robin Bouclier et al.

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING (2017)

Article Optics

Digital image correlation based on a fast convolution strategy

Yuan Yuan et al.

OPTICS AND LASERS IN ENGINEERING (2017)

Article Mechanics

Application of Digital Image Correlation to composite reinforcements testing

Marcin Tekieli et al.

COMPOSITE STRUCTURES (2017)

Article Engineering, Mechanical

Comparison of different filtering strategies to reduce noise in strain measurement with digital image correlation

Jacopo Baldoni et al.

JOURNAL OF STRAIN ANALYSIS FOR ENGINEERING DESIGN (2016)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Optics

Speeding up digital image correlation computation using the integral image technique

Lebin Jiang et al.

OPTICS AND LASERS IN ENGINEERING (2015)

Article Optics

Path-independent digital image correlation with high accuracy, speed and robustness

Zhenyu Jiang et al.

OPTICS AND LASERS IN ENGINEERING (2015)

Article Optics

High accuracy digital image correlation powered by GPU-based parallel computing

Lingqi Zhang et al.

OPTICS AND LASERS IN ENGINEERING (2015)

Article Materials Science, Multidisciplinary

Digital Image Correlation with Self-Adaptive Gaussian Windows

J. Huang et al.

EXPERIMENTAL MECHANICS (2013)

Article Engineering, Mechanical

Mesh-based digital image correlation method using higher order isoparametric elements

Shaopeng Ma et al.

JOURNAL OF STRAIN ANALYSIS FOR ENGINEERING DESIGN (2012)

Article Computer Science, Artificial Intelligence

Correlation analysis on GPU systems using NVIDIA's CUDA

Daniel Gembris et al.

JOURNAL OF REAL-TIME IMAGE PROCESSING (2011)