Mathematical Foundations for Object Recognition and Image Analysis

Abstract

Substantial work was done on the method of deformable templates for object detection, recognition, and interpretation. New measures of deformation were introduced, and these yielded new and more efficient algorithms for template matching. Experiments were carried out for target tracking in radar imagery and for anatomical labeling in a variety of medical imaging applications. A new detection and tracking algorithm was developed. The algorithm uses ideas from classical filtering, but in the context of a nonlinear model and modern computational tools. Experiments were performed on challenging imagery obtained by filming several fish swimming in a large fish tank containing an elaborate array of objects.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2000
Accession Number
ADA387097

Entities

People

  • Stuart Geman

Organizations

  • Brown University

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Applied Mathematics
  • Behavioral Sciences
  • Character Recognition
  • Computational Linguistics
  • Computer Vision
  • Detection
  • Diagnostic Imaging
  • Digital Signal Processing
  • Language
  • Linguistics
  • Mathematics
  • Object Recognition
  • Recognition
  • Signal Processing
  • Stochastic Processes

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Image Processing and Computer Vision.
  • Theoretical Analysis.