Using Pyramids to Detect Good Continuation

Abstract

Pictures containing lines and curves are often perceived by humans as being composed of a smaller number of more global figures. For example, a broken set of collinear line segments is perceived as a single straight line, even in the presence of other overlapping line segments. This paper presents a method of extracting such figures from images automatically in a highly parallel manner. A pyramid of successively lower-resolution images is used to transform the problem from one of global search to one of local good continuation. Using the pyramid, figures that are both sparse and obscured can successfully be extracted and the background clutter can be suppressed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1982
Accession Number
ADA124848

Entities

People

  • Azriel Rosenfeld
  • M. Shneier
  • R. Hartley
  • T. H. Hong

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Buildings And Structures
  • Computer Science
  • Computer Vision
  • Computers
  • Contracts
  • Crossings
  • Curvature
  • Detection
  • Detectors
  • Figure Of Merit
  • Gray Scale
  • Image Processing
  • Night Vision
  • Pattern Recognition
  • Recognition
  • Universities

Fields of Study

  • Computer science

Readers

  • Graph Algorithms and Convex Optimization.
  • Image Processing and Computer Vision.
  • Systems Analysis and Design