Region Extraction Using Convergent Evidence.

Abstract

Scenes consisting of spatially compact regions which contrast with their surrounds can be segmented by extracting connected components of above-threshold values whose borders match the positions of edges. Edge/border coincidence thus defines a kind of optimal thresholding, since for any object we can choose the threshold which maximizes the coincidence. This illustrates how the redundancy of different information sources aids segmentation. (Author)

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1978
Accession Number
ADA061591

Entities

People

  • D. L. Milgram

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Computational Processes
  • Computer Science
  • Computer Vision
  • Computing-Related Activities
  • Contrast
  • Extraction
  • Machine Perception
  • Mental Processes
  • Redundancy
  • Segmented

Fields of Study

  • Physics

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Computer Vision.