EDGE DETECTION IN PICTURES BY COMPUTER USING PLANNING,

Abstract

The paper describes a program for extracting an accurate outline of a man's head from a digital picture. The program accepts as input digital, grey scale pictures containing people standing in front of various backgrounds. The output of the program is an ordered list of the points which form the outline of the head. The edges of background objects and the interior details of the head have been suppressed. The program is successful because of an improved method for edge detection which uses heuristic planning, a technique drawn from artificial intelligence research in problem solving. A brief, edge detection using planning consists of three steps. A new digital picture is prepared from the original; the new picture is smaller and has less detail. Edges of objects are located in the reduced picture. The edges found in the reduced picture are used as a plan for finding edges in the original picture. (Author)

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1970
Accession Number
AD0708086

Entities

People

  • Michael D. Kelly

Organizations

  • Stanford University

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Change Detection
  • Computers
  • Detection
  • Gray Scale
  • Target Discrimination

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Science.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks