Monotone Equivariant Segmentation Techniques.

Abstract

An earlier model for nonhierarchial clustering is extended so that it encompasses the original image segmentation problem. A theoreticl discussion within this model is provided for certain segmentation techniques. The discussion is also carried out within the framework of a Bernouli process. The techniques are illustrated on real and simulated data. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1982
Accession Number
ADA121418

Entities

People

  • M. F. Janowitz

Organizations

  • University of Massachusetts Amherst

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Classification
  • Clustering
  • Computer Vision
  • Construction
  • Data Sets
  • Dispersions
  • Frequency
  • Image Segmentation
  • Insensitive Explosives
  • Materials
  • New York
  • Noise
  • Normal Distribution
  • Probability
  • Residuals

Fields of Study

  • Mathematics

Readers

  • Computational Modeling and Simulation
  • Medical Imaging.
  • Statistical inference.