Image and Video Retrieval for National Security Applications: an Approach Based on Multiple Content Codebooks

Abstract

Content-based retrieval of images and video is examined in the context of national security applications (defense, intelligence, and law enforcement). The unique characteristics of CBR systems for these applications are developed and contrasted with those for commercial industry (entertainment, retail, publishing, etc.). The variety of visual media, the lack of internal image structure, the presence of significant raw metadata, and the presence of domain restrictions are discussed, along with other characteristics. A general CBR approach, and its implementation, that is well-suited to the unique characteristics of national security applications is described in detail. This approach is based on the concept of multiple vector quantization codebooks for content extraction, and indexed-based query that uses multiple content types simultaneously.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1997
Accession Number
AD1108115

Entities

People

  • Elizabeth S. Hughes
  • Thomas P. Bronez

Organizations

  • MITRE Corporation

Tags

Communities of Interest

  • Autonomy
  • Counter WMD
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Aircrafts
  • Algorithms
  • Computer Vision
  • Databases
  • Detection
  • Detectors
  • Equations
  • Image Processing
  • Images
  • National Security
  • Probability
  • Security
  • Statistical Analysis
  • Statistics
  • United States
  • Unmanned Aerial Vehicles
  • Video Clips

Readers

  • Database Systems and Applications
  • Government and Public Administration Law.
  • Neural Network Machine Learning.