Qualitative Methods in Computer Vision

Abstract

Current object recognition systems can only recognize a limited class of objects. Objects having variable numbers of parts and only loosely constrained shapes cannot be modeled and recognized by these systems. The PI proposed the use of a data structure called the VAPOR (Variable Appearance Object Representation) model to represent objects with these kinds of variable appearances and develop a search procedure called MOSS (Model Space Search) to find instances of these models in two-dimensional image data. The VAPOR model is an idealization of the object; all instances of the model in the image are variations from ideal appearance. The variations are evaluated by the description length of the model, measured in information-theoretic bits. MOSS selects the best model for the given image data by choosing the minimal length description. It was demonstrated how the system performs in a simple domain of circles and polygons and in the complex domain of finding cloverleaf intersections in aerial images of roads.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA264335

Entities

People

  • Azriel Rosenfeld

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Bayesian Inference
  • Computer Vision
  • Computers
  • Maryland
  • Object Recognition
  • Optimization
  • Recognition
  • Statistical Algorithms
  • Target Detection
  • Theses
  • Three Dimensional
  • Two Dimensional
  • Universities

Fields of Study

  • Computer science

Readers

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

Technology Areas

  • AI & ML
  • Space
  • Space - Space Objects