Affine Invariant Object Recognition by Voting Match Techniques

Abstract

This thesis begins with a general survey of different model based systems for object recognition. The advantage and disadvantage of those systems are discussed. A system is then selected for study because of its effective Affine invariant matching characteristic. This system involves two separate phases, the modeling and the recognition. One is done off line and the other is done on line. A Hashing technique is implemented to achieve fast accessing and voting. Different test data sets are used in experiments to illustrate the recognition capabilities of this system. This demonstrates the capabilities of partial match, recognizing objects under similarity transformation of applied to the models and the results of noise perturbation. The test results are discussed, and related experiences and recommendations are presented. Theses.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1988
Accession Number
ADA218965

Entities

People

  • Tao-i Hsu

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Biomedical
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Databases
  • Detectors
  • Electrical Engineering
  • Engineering
  • Feature Extraction
  • Geometric Forms
  • Geometry
  • Image Processing
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Three Dimensional
  • Two Dimensional

Readers

  • Graph Algorithms and Convex Optimization.
  • Neural Network Machine Learning.
  • Systems Analysis and Design