Accession Number:

ADA235346

Title:

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

Descriptive Note:

Memorandum rept.,

Corporate Author:

ROYAL SIGNALS AND RADAR ESTABLISHMENT MALVERN (UNITED KINGDOM)

Personal Author(s):

• Luttrell, Stephen P.

Report Date:

1990-11-05

Pagination or Media Count:

44.0

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.

Descriptors:

• *MATHEMATICAL MODELS
• DETECTORS
• TRAINING
• PROBABILITY DENSITY FUNCTIONS
• REGIONS
• UNITED KINGDOM
• IMAGES
• ADAPTIVE SYSTEMS
• EXPANSION
• TEXTURE
• HOMOGENEITY
• ANOMALIES
• CLUSTERING

Subject Categories:

• Active and Passive Radar Detection and Equipment

Distribution Statement:

APPROVED FOR PUBLIC RELEASE