Jove
Visualize
Contact Us

Related Experiment Video

Updated: May 23, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Area segmentation of images using edge points.

W A Perkins1

  • 1Computer Science Department, General Motors Research Laboratories, Warren, MI 48090.

IEEE Transactions on Pattern Analysis and Machine Intelligence
|April 14, 2012
PubMed
Summary

This study introduces a novel image segmentation method using an expansion-contraction technique to overcome limitations of edge-based region separation. The approach effectively segments images by closing gaps in edge points, preserving uniform regions, and successfully processing diverse scenes.

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

INSPECTOR: A Computer Vision System that Learns to Inspect Parts.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Public health implications of airborne infection: physical aspects.

Bacteriological reviews·1961
Same author

The rat virus.

The Journal of infectious diseases·1953
Same author

EPITHELIOMA OF HAND-A STUDY IN DIFFERENTIAL DIAGNOSIS BETWEEN EPITHELIOMA AND ENDOTHELIOMA.

California and western medicine·1924
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

Area of Science:

  • Computer Vision
  • Image Processing
  • Pattern Recognition

Background:

  • Traditional edge point-based region segmentation methods struggle with gaps, leading to the merging of dissimilar regions.
  • Previous techniques lacked robustness in accurately separating distinct areas within an image.

Purpose of the Study:

  • To develop an improved image segmentation method that accurately separates regions of smoothly varying intensity using edge points.
  • To address the limitations of existing edge-based segmentation techniques, particularly the issue of region merging due to small gaps.

Main Methods:

  • A novel expansion-contraction technique is employed to refine edge regions, initially expanding to close gaps.
  • The method iteratively expands edge regions from small to large, contracting after uniform regions are identified.

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

Related Experiment Videos

Last Updated: May 23, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

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

  • A key feature is the selective expansion of edge regions, preventing the merging of different uniform regions and preserving small ones.

    • Main Results:

    • The developed program successfully segments images into distinct uniform intensity regions and edge boundary regions.
    • The iterative expansion-contraction process effectively closes gaps in edge points, enhancing segmentation accuracy.
    • The method demonstrated successful segmentation across various complex scenes, including industrial parts, landscapes, and integrated circuit chips.

    Conclusions:

    • The proposed expansion-contraction method offers a robust solution for image segmentation using edge points.
    • This technique overcomes previous limitations by effectively handling gaps and preserving details in uniform regions.
    • The successful application to diverse image types highlights the versatility and effectiveness of this novel segmentation approach.