A Trainable Texture Anomaly Detector Using the Adaptive Cluster Expansion (ACE) Method.

Abstract

We derive an adaptive hierarchical maximum entropy estimate of probability density functions, whose mathematical structure suggest the name 'adaptive cluster expansion' (ACE). We apply ACE to the problem of locating statistically anomalous regions in otherwise homogeneous textured images, which we demonstrate using several images of Brodatz textures.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 05, 1990
Accession Number
ADA235346

Entities

People

  • Stephen P. Luttrell

Organizations

  • Royal Signals and Radar Establishment

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Coding
  • Computational Science
  • Computer Programming
  • Decoding
  • Detection
  • Detectors
  • Image Processing
  • Models
  • Neural Networks
  • Notation
  • Probabilistic Models
  • Probability
  • Sampling
  • Statistics
  • Trees (Data Structures)
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Aerial Delivery - Logistics and Supply Chain Management.
  • Computer Vision.
  • Neural Network Machine Learning.