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: Nov 9, 2025

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1000

Angular-Driven Feedback Restoration Networks for Imperfect Sketch Recognition.

Jia Wan, Kaihao Zhang, Hongdong Li

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 15, 2021
    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

    High-performance electrochemical sensing of 2-aminophenol enabled by a boron-doped diamond electrode.

    RSC advances·2026
    Same author

    Genomic characterization of a large-scale chikungunya outbreak in China.

    The Journal of infection·2026
    Same author

    Amniotic membrane transplantation combined with cryotherapy vs. lamellar keratoplasty for medically refractory peripheral ulcerative keratitis: a retrospective cohort study.

    Frontiers in medicine·2026
    Same author

    From Single Atom to Five-Atom Cluster Catalysts on Boron-Doped Diamond: Interface Engineering and Dynamic Active Sites Exploration for Acidic OER.

    The journal of physical chemistry letters·2026
    Same author

    Research progress of high-entropy catalysts in electrochemical oxidation of organic small molecules.

    Chemical communications (Cambridge, England)·2026
    Same author

    Control of Circularly Polarized Luminescence in Cholesteric Luminescent Liquid Crystals: From FRET to Exciton Coupling.

    Angewandte Chemie (International ed. in English)·2026
    Same journal

    Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BayeTopo: Bayesian-based Topology-guided Learning for Vascular Imaging Segmentation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a new method for recognizing imperfect hand-drawn sketches. The angular-driven feedback restoration network (ADFRNet) enhances sketch quality, improving recognition accuracy for incomplete or damaged drawings.

    Area of Science:

    • Computer Vision
    • Machine Learning

    Background:

    • Automatic sketch recognition is crucial in computer vision.
    • Existing deep learning models struggle with incomplete or damaged sketches.
    • There is a need for robust sketch recognition systems that handle real-world imperfections.

    Purpose of the Study:

    • To develop a method for improving the recognition of imperfect hand-drawn sketches.
    • To address the limitations of current models in handling incomplete or destroyed sketch data.
    • To enhance the accuracy and robustness of sketch recognition systems.

    Main Methods:

    • Development of two new datasets featuring scrawled and incomplete sketches.
    • Proposal of an angular-driven feedback restoration network (ADFRNet).
    • Implementation of a novel "feedback restoration loop" and an angular-based loss function.

    More Related Videos

    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
    06:45

    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

    Published on: October 28, 2022

    1.9K

    Related Experiment Videos

    Last Updated: Nov 9, 2025

    Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
    07:46

    Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

    Published on: August 9, 2024

    1000
    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
    06:45

    Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

    Published on: October 28, 2022

    1.9K

    Main Results:

    • The proposed ADFRNet effectively detects and refines imperfect sketch regions.
    • The feedback restoration loop improves sketch quality without significant memory overhead.
    • The angular-based loss function aids in sketch refinement and discriminator learning.
    • Experiments show superior performance over state-of-the-art methods on imperfect sketch datasets.

    Conclusions:

    • The ADFRNet significantly improves the quality of imperfect sketch images.
    • The proposed method achieves superior performance in sketch recognition tasks involving imperfect data.
    • This work offers a promising direction for robust sketch recognition in practical applications.