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 Videos

Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor.

Shoudong Han1, Wenbing Tao, Desheng Wang

  • 1Institute of Systems Engineering, Huazhong University of Science and Technology, Wuhan 430074, China. shoudonghan@gmail.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|June 19, 2009
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

Foliar application of licorice-wolfberry derived nanomaterials enhances soybean heat tolerance through maintaining reactive oxygen species homeostasis.

Frontiers in plant science·2026
Same author

Effects of microbial inoculants and planting density on soybean summer-sown growth, nutrients accumulation and yield in Southern Xinjiang.

Frontiers in plant science·2026
Same author

Preparation and Performance Study of Three-Layer Composite Filter Media for Channel-Type Ultra-Low Penetration Air Filters.

Nanomaterials (Basel, Switzerland)·2026
Same author

Metabolomic signatures of hepatic steatosis reveal heterogeneity in cardiometabolic risk and responses to lifestyle interventions in type 2 diabetes: a post hoc analysis.

Cardiovascular diabetology·2026
Same author

Causal machine learning analysis identifies subpopulations most likely to benefit from healthy lifestyles for cognitive outcomes.

General psychiatry·2026
Same author

Development and validation of an online predictive model for biochemical recurrence after radical prostatectomy in elderly patients.

Frontiers in oncology·2026
Same journal

Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

This study introduces an improved interactive image segmentation method by combining color and multiscale nonlinear structure tensor texture (MSNST) features. The enhanced GrabCut algorithm achieves superior segmentation accuracy and efficiency for natural images.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Image segmentation is crucial for computer vision tasks.
  • Traditional methods struggle with scale differences and texture variations.
  • Integrating diverse features can enhance segmentation performance.

Purpose of the Study:

  • To develop an interactive color image segmentation method.
  • To improve segmentation accuracy and efficiency for textured images.
  • To overcome limitations of the original GrabCut algorithm.

Main Methods:

  • Integration of color features with multiscale nonlinear structure tensor texture (MSNST) features.
  • Extension of Gaussian Mixture Model (GMM) to MSNST for energy function description.

Related Experiment Videos

  • Utilizing symmetric KL divergence and Conjugate norm with Locality Preserving Projections (LPP).
  • Implementation of an adaptive fusing strategy and an iteration convergence criterion.

    • Main Results:

    • Superior image segmentation performance compared to the original GrabCut method.
    • Effective handling of scale differences in textured images.
    • Reduced iteration time with satisfied segmentation accuracy.
    • Robust segmentation through adaptive feature fusion.

    Conclusions:

    • The proposed method significantly enhances interactive image segmentation.
    • Combining color and advanced texture features (MSNST) leads to improved results.
    • The method offers a more efficient and accurate solution for segmenting natural images.