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

Intrinsic Manifold SLIC: A Simple and Efficient Method for Computing Content-Sensitive Superpixels.

Yong-Jin Liu, Minjing Yu, Bing-Jun Li

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |March 31, 2017
    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

    BNIP3 is a key driver of breast cancer progression and a novel glycolysis-regulating biomarker.

    Scientific reports·2025
    Same author

    A Multimodal Dataset for Mixed Emotion Recognition.

    Scientific data·2024
    Same author

    PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation.

    IEEE transactions on visualization and computer graphics·2024
    Same author

    Bile acids inhibit ferroptosis sensitivity through activating farnesoid X receptor in gastric cancer cells.

    World journal of gastroenterology·2024
    Same author

    Bcl-2 interacting protein 3 (BNIP3) promotes tumor growth in breast cancer under hypoxic conditions through an autophagy-dependent pathway.

    Bioengineered·2022
    Same author

    3D-CariGAN: An End-to-End Solution to 3D Caricature Generation From Normal Face Photos.

    IEEE transactions on visualization and computer graphics·2021
    Same journal

    Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Learning Shape Anchors for Holistic Indoor Scene Understanding.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces Intrinsic Manifold SLIC (IMSLIC), a novel method for creating content-sensitive superpixels. IMSLIC adapts superpixel size based on image content density, outperforming existing methods in segmentation accuracy and boundary adherence.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Computational Geometry

    Background:

    • Superpixels are fundamental image regions for feature extraction.
    • Simple Linear Iterative Clustering (SLIC) is a popular method for uniform superpixel generation.
    • Existing methods lack content-awareness in superpixel generation.

    Purpose of the Study:

    • To extend SLIC for content-sensitive superpixel computation.
    • To develop a method that generates small superpixels in dense regions and large ones in sparse regions.
    • To improve image segmentation accuracy and boundary adherence.

    Main Methods:

    • Mapping images to a 2D manifold where area represents content density.
    • Proposing Intrinsic Manifold SLIC (IMSLIC) for geodesic centroidal Voronoi tessellation (GCVT) on the manifold.

    Related Experiment Videos

  • Characterizing content sensitivity by measuring Voronoi cell areas on the manifold.

    • Main Results:

    • IMSLIC generates content-sensitive superpixels efficiently and guarantees simple connectivity.
    • Outperforms eleven methods on BSDS500 and seven on NYUV2 datasets in compactness, boundary adherence, and segmentation accuracy.
    • Achieves superior foreground segmentation in contour closure applications on WHD and WSD datasets.

    Conclusions:

    • IMSLIC offers a significant advancement in content-sensitive superpixel generation.
    • The method provides a cost-effective and accurate approach to image segmentation.
    • IMSLIC demonstrates superior performance across various image analysis tasks.