Segmentation Using Multispectral Adaptive Contours

Abstract

Funds are requested to pursue extension of the active contour model for image segmentation to images with multispectral measurements of target and background. The popular level set approach will be compared with the older "snakes" approach both theoretically and experimentally. The several different possible ways to make use of multispectral information about targets and clutter will be analyzed and experimentally compared.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 29, 2004
Accession Number
ADA424462

Entities

People

  • Wesley E. Snyder

Organizations

  • North Carolina State University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Boundaries
  • Computer Vision
  • Curvature
  • Detectors
  • Equations
  • Gaussian Distributions
  • Geometry
  • Hot Spots
  • Image Processing
  • Image Segmentation
  • Inspection
  • Multispectral
  • Probability
  • Statistics
  • Topology
  • Two Dimensional
  • Visual Inspection

Fields of Study

  • Physics

Readers

  • Computer Vision.
  • Systems Analysis and Design