Global and local fuzzy energy-based active contours for image segmentation

Kuo Kai Shyu, Van Truong Pham, Thi Thao Tran, Po Lei Lee

Research output: Contribution to journalArticlepeer-review

33 Scopus citations

Abstract

This paper proposes a novel active contour model for image segmentation based on techniques of curve evolution. The paper introduces an energy functional including a local fuzzy energy and a global fuzzy energy to attract the active contour and stop it on the object boundaries. The local term allows the method to deal with intensity inhomogeneity in images. The global term, aside from driving the contour toward the desired objects, is used to avoid unsatisfying results led by unsuitable initial contour position, a common limitation of models using local information solely. In addition, instead of solving the Euler-Lagrange equation, the paper directly calculates the alterations of the fuzzy energy. By this way, the contour converges quickly to the object boundary. Experimental results on both 2D and 3D images validate the effectiveness of the model when working with intensity inhomogeneous images.

Original languageEnglish
Pages (from-to)1559-1578
Number of pages20
JournalNonlinear Dynamics
Volume67
Issue number2
DOIs
StatePublished - Jan 2012

Keywords

  • Active contour
  • Curve evolution
  • Fuzzy energy
  • Global and local minimization
  • Image segmentation
  • Level set method

Fingerprint

Dive into the research topics of 'Global and local fuzzy energy-based active contours for image segmentation'. Together they form a unique fingerprint.

Cite this