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

Graph partitioning active contours (GPAC) for image segmentation.

Baris Sumengen1, B S Manjunath

  • 1Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106, USA. sumengen@ece.ucsb.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|March 29, 2006
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

Generalizable Deepfake Detection With Phase-Based Motion Analysis.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

Artificial Intelligence for Automatic Analysis of Shunt Treatment in Presurgery and Postsurgery Computed Tomography Brain Scans of Patients With Idiopathic Normal Pressure Hydrocephalus.

Neurosurgery·2024
Same author

Automatic classification and neurotransmitter prediction of synapses in electron microscopy.

Biological imaging·2024
Same author

Erratum: Automatic classification and neurotransmitter prediction of synapses in electron microscopy - CORRIGENDUM.

Biological imaging·2024
Same author

Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus.

BME frontiers·2023
Same author

A robust approach to 3D neuron shape representation for quantification and classification.

BMC bioinformatics·2023
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

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

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

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

Achieving Text-based Person Retrieval with Any Granularity.

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

This study presents Graph Partitioning Active Contours (GPAC), a novel method for image segmentation using pixel similarities. GPAC offers an efficient and effective solution for segmenting various image types.

Area of Science:

  • Computer Vision and Image Processing
  • Computational Mathematics

Background:

  • Traditional active contour models often struggle with complex image segmentation tasks.
  • Variational segmentation methods require robust cost functions based on pixel relationships.

Purpose of the Study:

  • Introduce novel variational segmentation cost functions and active contour methods.
  • Develop a new curve evolution framework, Graph Partitioning Active Contours (GPAC), for image segmentation.

Main Methods:

  • Formulated segmentation cost functions based on pairwise pixel similarities/dissimilarities.
  • Developed the Graph Partitioning Active Contours (GPAC) framework as a solution to minimization problems.
  • Implemented efficient techniques for curve evolution using global features.

Related Experiment Videos

Main Results:

  • GPAC achieves results close to the ideal minimization of defined cost functions.
  • Demonstrated effectiveness and computational efficiency on natural, grayscale, color, and texture images.
  • Achieved promising segmentation results across diverse image datasets.

Conclusions:

  • GPAC is an effective and computationally efficient method for image segmentation.
  • The proposed cost functions and GPAC framework advance active contour methodologies.
  • GPAC shows significant potential for various image analysis applications.