Shape Segmentation Using Relaxation

Abstract

Relaxation is applied to the segmentation of closed boundary curves of shapes. The ambiguous segmentation of the boundary is represented by a directed graph structure whose nodes represent segments, where two nodes are joined by an arc if the segments are consecutive along the boundary. A probability vector is associated with each node; each component of this vector provides an estimate of the probability that the corresponding segment is a particular part of the object. Relaxation is used to eliminate impossible sequences of parts, or reduce the probabilities of unlikely ones. In experiments involving airplane shapes, this almost always results in a drastic simplification of the graph, with only good interpretations surviving.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1979
Accession Number
ADA078084

Entities

People

  • Azriel Rosenfeld
  • Shmuel Peleg
  • Wallace S. Ruthowski

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Aircrafts
  • Airplanes
  • Artificial Intelligence
  • Boundaries
  • Computer Graphics
  • Computer Science
  • Computer Vision
  • Computers
  • Figure Of Merit
  • Graphics
  • Image Processing
  • Leading Edges
  • Pattern Recognition
  • Probability
  • Recognition
  • Sequences
  • Shape

Readers

  • Calculus or Mathematical Analysis
  • Electromagnetic Wave Scattering and Antenna Radiation Engineering
  • Neural Network Machine Learning.