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: May 9, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Image classification via object-aware holistic superpixel selection.

Zilei Wang, Jiashi Feng, Shuicheng Yan

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |July 19, 2013
    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 authorSame journal

    Semantic Frame Interpolation.

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

    Construction of a <sup>89</sup>Zr-Labeled Specific Antibody Fragment for the Noninvasive Detection of Mesothelin-Overexpressing Tumors.

    Molecular pharmaceutics·2026
    Same author

    Advanced Laser Technologies for Efficient Crystalline Silicon Solar Cells.

    Nano-micro letters·2026
    Same author

    DrawMotion: Generating 3D Human Motions by Freehand Drawing.

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

    Determining chronicity and frequency of histologic lung lesions in feedyard cattle mortalities.

    Journal of veterinary diagnostic investigation : official publication of the American Association of Veterinary Laboratory Diagnosticians, Inc·2026
    Same author

    MC#: Mixture Compressor for Mixture-of-Experts Large Models.

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

    Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

    Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

    This study introduces a novel object-aware holistic superpixel selection (HPS) method to improve image classification by focusing on discriminative superpixels. HPS effectively reduces background clutter, significantly boosting classification accuracy on benchmark datasets.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Pattern Recognition

    Background:

    • Image classification is challenged by cluttered backgrounds and object segmentation difficulties.
    • Existing methods often require precise object segmentation, limiting their applicability.

    Purpose of the Study:

    • To propose an object-aware holistic superpixel selection (HPS) method for enhanced image classification.
    • To alleviate background interference without requiring accurate object segmentation.

    Main Methods:

    • HPS automatically selects discriminative superpixels that match object templates for specific classes.
    • It generates class-specific matching regions and merges them into an integral object region using pixel-level intersection.
    • The final classification is performed on the derived object region instead of the entire image.

    More Related Videos

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
    07:15

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

    Published on: July 11, 2025

    Related Experiment Videos

    Last Updated: May 9, 2026

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
    03:31

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

    Published on: December 15, 2023

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
    07:15

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

    Published on: July 11, 2025

    Main Results:

    • The proposed HPS method significantly enhances image classification performance.
    • Evaluated on Oxford-IIIT PET 37, Caltech-UCSD Birds 200, Caltech 101, and PASCAL VOC 2011 datasets.
    • Consistent improvements in classification accuracy were observed across all tested datasets.

    Conclusions:

    • HPS effectively mitigates background clutter interference in image classification.
    • The method offers a robust approach to object-aware image analysis without precise segmentation.
    • HPS demonstrates remarkable potential for improving the accuracy of image classification systems.