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 10, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Object-level image segmentation using low level cues.

Hongyuan Zhu1, Jianmin Zheng, Jianfei Cai

  • 1BeingThere Centre, Institute for Media Innovation, Nanyang Technological University, Singapore. hzhu1@e.ntu.edu.sg

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|June 21, 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 author

Prognostic prediction model for rectal cancer based on CMS subtype indicators and SHAP-based interpretable analysis.

Abdominal radiology (New York)·2026
Same author

A retrospective study on post-traumatic stress disorder in fathers of preterm infants in the NICU and the effectiveness of kangaroo care intervention.

Frontiers in psychiatry·2026
Same author

Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning.

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

Contrasting effects of rice-crayfish co-culture on insect herbivores at field and landscape scales.

Pest management science·2026
Same author

Studies on Zinc Metabolism Related to Ischemia-reperfusion Injury: A Bibliometric and Visualized Analysis.

Biological trace element research·2026
Same author

Counterfactual Risk Minimization for Out-of-Distribution Generalization.

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
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 presents a novel image segmentation method using pixel feature vectors. The approach effectively identifies object-level regions by integrating low-level cues, outperforming existing techniques.

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Automatic image segmentation into meaningful regions is challenging.
  • Existing methods often require high-level knowledge or extensive training.
  • Low-level image features are explored for object-level segmentation.

Purpose of the Study:

  • To develop an automatic image segmentation algorithm using low-level cues.
  • To integrate spectral, color, and spatial information for pixel representation.
  • To propose a method for automatically determining the number of segments.

Main Methods:

  • Constructing pixel feature vectors integrating spectral attributes, Gaussian mixture models, and geodesic distance.
  • Formulating a Potts variational model in the feature space for segmentation.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Related Experiment Videos

Last Updated: May 10, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

  • Developing a heuristic approach for automatic segment number selection.

    • Main Results:

    • The proposed method produces coherent regions in color and position.
    • Segmentation results comply with global object structures.
    • The algorithm maintains smooth and accurate object boundaries.
    • Demonstrated effectiveness against state-of-the-art methods on the Berkeley benchmark dataset.

    Conclusions:

    • Low-level feature integration enables effective object-level image segmentation.
    • The variational approach in feature space offers a robust segmentation solution.
    • The method achieves competitive performance with automatic segment selection.