A Syntax-Directed Method of Extracting Topological Regions from a Silhouette.

Abstract

The objective of this research is to develop a preprocessing technique for decomposing pictorial data into its topological units and subunits so as to enhance any subsequent feature/primitive extraction. To enhance the later stages of perception implies that each topological unit and its subunits must be labeled in such a way as to reveal their relationship to the other topological units of the pattern. If the labeling can be standardized then the feature/primitive analysis, which is very application-oriented, can process the results of the preprocessor decomposition as desired. While the proposal for such a decomposition (called segmentation or region analysis) is not new, the concept of decomposition to reveal a pattern's intrinsic structure prior to and independent of feature/primitive analysis is new. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1977
Accession Number
ADA045944

Entities

People

  • John O. Amoss

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Air Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Computer Vision
  • Computers
  • Contrast
  • Decomposition
  • Extraction
  • Grammars
  • Information Science
  • Language
  • Operations Research
  • Pattern Recognition
  • Perception
  • Preprocessing
  • Recognition
  • Scientific Research
  • Skeleton
  • Universities

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Graph Algorithms and Convex Optimization.
  • Molecular Genetics