Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 5, 2026

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
06:21

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

Published on: September 20, 2024

1.5K

Interpretable DIC measurement neural network based on IC-GN algorithm framework.

Lianpo Wang, Yantao Zhang

    Optics Express
    |May 4, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Spatial frequency domain information aggregation network for radar image despeckling.

    Scientific reports·2026
    Same author

    Exosomal miR-147-3p regulates the growth of mouse bronchial epithelial cells and asthma progression via targeting RUNX3: a pilot study.

    General physiology and biophysics·2026
    Same author

    Unraveling the anti-neuroinflammatory mechanisms of Cervus cucumis polypeptide injection in Alzheimer's disease: insights from network pharmacology, molecular docking, molecular dynamics simulation, and experimental validation.

    Frontiers in aging neuroscience·2026
    Same author

    cGAS-STING/HMGB1-mediated senescence induced by LRRK2 accelerates cartilage degeneration in osteoarthritis.

    Cell death & disease·2026
    Same author

    The emerging landscape of lncRNAs in gastric cancer immunity: From immune escape to ferroptosis and metabolic reprogramming.

    Biochemical and biophysical research communications·2026
    Same author

    Basic calcium phosphate crystals aggravate senescence-related osteoarthritis through GPX4-NRF2-mediated ferroptosis.

    Cell calcium·2026

    This study introduces a novel deep learning approach for digital image correlation (DIC), enhancing measurement efficiency and accuracy. The new method combines the strengths of traditional and deep learning techniques for precise deformation analysis.

    Area of Science:

    • * Optical Measurement and Non-Destructive Testing
    • * Computational Mechanics and Material Science
    • * Artificial Intelligence in Engineering

    Background:

    • * Digital Image Correlation (DIC) is a precise, non-contact optical technique for measuring surface displacement and deformation.
    • * Traditional DIC algorithms (e.g., inverse composition-Gaussian Newton) offer accuracy but suffer from low efficiency and parameter selection challenges.
    • * Deep Learning-based DIC (DL-DIC) improves efficiency but currently lacks the accuracy and interpretability of traditional methods for industrial application.

    Purpose of the Study:

    • * To develop a hybrid DL-DIC algorithm that integrates the interpretability and accuracy of traditional DIC with the efficiency of deep learning.
    • * To overcome the limitations of existing DL-DIC methods, specifically their lower accuracy and lack of industrial applicability.

    Related Experiment Videos

    Last Updated: May 5, 2026

    Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
    06:21

    Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

    Published on: September 20, 2024

    1.5K
  • * To achieve high-precision deformation measurement through an interpretable and efficient framework.

    • Main Methods:

    • * Integration of deep learning within the traditional inverse composition-Gaussian Newton (IC-GN) DIC framework.
    • * Utilizing deep learning to determine the incremental shape function, replacing the conventional Gaussian Newton method.
    • * Employing a recursive network structure for iterative optimization of the shape function, enhancing deformation measurement precision.

    Main Results:

    • * Simulated experiments demonstrated over 10% reduction in Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) compared to traditional DIC.
    • * Real-world tensile tests showed over 20% reduction in RMSE and MAE compared to existing DL-DIC methods.
    • * The proposed method achieves high accuracy and interpretability while maintaining high efficiency and simple parameter selection.

    Conclusions:

    • * The hybrid DL-DIC approach successfully combines the high accuracy and interpretability of IC-GN with the efficiency of DL-DIC.
    • * This method offers a viable solution for high-precision, efficient, and interpretable deformation measurement.
    • * The developed algorithm shows significant potential for industrial applications where both accuracy and efficiency are critical.