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

Leave-One-Out Kernel Optimization for Shadow Detection and Removal.

Tomas F Yago Vicente, Minh Hoai, Dimitris Samaras

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 15, 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

    Topology-Aware Segmentation Using Discrete Morse Theory.

    ... International Conference on Learning Representations·2026
    Same author

    TOPODIFFUSIONNET: A TOPOLOGY-AWARE DIFFUSION MODEL.

    ... International Conference on Learning Representations·2026
    Same author

    Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers.

    Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
    Same author

    Look Hear: Gaze Prediction for Speech-directed Human Attention.

    Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2026
    Same author

    Measuring and predicting where and when pathologists focus their visual attention while grading whole slide images of cancer.

    Medical image analysis·2025
    Same author

    Label-Efficient Deep Color Deconvolution of Brightfield Multiplex IHC Images.

    IEEE transactions on medical imaging·2025
    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 an efficient method for shadow detection and removal in images using a kernel Least-Squares Support Vector Machine (LSSVM) and Markov Random Fields (MRF). The approach accurately identifies shadow regions and enhances them through relighting, outperforming existing state-of-the-art techniques.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Machine Learning

    Background:

    • Shadow detection and removal are crucial for accurate image analysis and manipulation.
    • Existing methods often struggle with complex shadow scenarios and achieving high-quality removal.

    Purpose of the Study:

    • To develop an efficient and accurate method for detecting shadows in images.
    • To propose a novel shadow removal technique based on region relighting.
    • To outperform current state-of-the-art methods in both detection and removal tasks.

    Main Methods:

    • Image regions are labeled using a kernel Least-Squares Support Vector Machine (LSSVM) classifier.
    • Kernel and classifier parameters are optimized using leave-one-out cross-validation.
    • The detection method is enhanced by integrating a Markov Random Field (MRF) framework with contextual cues.

    Related Experiment Videos

  • Shadow removal is achieved through region relighting, matching luminance values between shadow and lit regions.

    • Main Results:

    • The proposed region classifier demonstrates superior performance compared to more complex methods on UCF and UIUC datasets.
    • The enhanced method, incorporating MRF, surpasses state-of-the-art shadow detection techniques.
    • The shadow removal approach, evaluated on a benchmark dataset, yields results superior to existing methods.

    Conclusions:

    • The developed framework provides an efficient and effective solution for shadow detection and removal.
    • The combination of LSSVM, MRF, and region relighting offers a robust approach for image shadow challenges.
    • This work advances the state-of-the-art in both shadow detection and removal applications.