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: Apr 28, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.6K

Learning-based hierarchical graph for unsupervised matting and foreground estimation.

Chen-Yu Tseng, Sheng-Jyh Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 4, 2014
    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

    Fast Blind Image Deblurring Based on Cross Partial Derivative.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    Hierarchical Image Segmentation Based on Iterative Contraction and Merging.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2017
    Same author

    Famprofazone use can be misinterpreted as methamphetamine abuse.

    Journal of analytical toxicology·2010
    Same author

    Representing images using points on image surfaces.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2005
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

    GoP-based Quality Enhancement on Video Compression.

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

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

    This study introduces a novel hierarchical graph for unsupervised matting, simplifying image processing. The method effectively extracts foreground objects by progressively condensing image data into layers, improving accuracy.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Machine Learning

    Background:

    • Automatic foreground object extraction from natural images is a complex problem.
    • Existing methods often focus on binary foreground/background segmentation.
    • Unsupervised matting requires sophisticated techniques for accurate results.

    Purpose of the Study:

    • To present a learning-based hierarchical graph for unsupervised matting.
    • To develop a framework that progressively condenses image data for efficient processing.
    • To enable multilayer foreground estimation beyond binary partitioning.

    Main Methods:

    • A hierarchical framework progressively condenses image data from pixels to cells, components, and matting layers.
    • Graph-based contraction reduces computational load by condensing pixels into cells.

    More Related Videos

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.3K

    Related Experiment Videos

    Last Updated: Apr 28, 2026

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    8.6K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.3K
  • Spectral clustering on a learned graph maps cells to matting components, utilizing multiscale information for improved affinity learning.

    • Main Results:

    • The proposed hierarchical scheme successfully assembles matting components into multilayer foreground interpretations.
    • Multiscale information integration enhances spectral clustering performance.
    • Experimental results demonstrate superior consistency and accuracy compared to state-of-the-art techniques.

    Conclusions:

    • The learning-based hierarchical graph provides an effective approach for unsupervised matting.
    • The multilayer foreground estimation offers richer interpretations than binary partitioning.
    • The method achieves state-of-the-art performance in automatic foreground object extraction.