Robust Recognition of Ship Types from an Infrared Silhouette

Abstract

Accurate identification of unknown contacts crucial in military intelligence. Automated systems that quickly and accurately determine the identity of a contact could be a benefit in backing up electronic-signals identification methods. This work reports two experimental systems for ship classification from infrared FLIR images. In an edge-histogram approach, we used the histogram of the binned distribution of observed straight edge segments of the ship image. Some simple tests had a classification success rate of 80% on silhouettes. In a more comprehensive neural network approach, we calculated scale-invariant moments of a silhouette and used them as input to a neural network. We trained the network on several thousand perspectives of a wire-frame model of the outline of each of five ship classes. We obtained 70% accuracy with detailed tested on real infrared images but performance was more robust than with the edge-histogram approach.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2004
Accession Number
ADA465758

Entities

People

  • Jessica Herman
  • Jorge Alves
  • Neil C. Rowe

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Change Detection
  • Classification
  • Computer Vision
  • Control Systems
  • Detection
  • Detectors
  • Identification
  • Image Processing
  • Images
  • Information Processing
  • Infrared Images
  • Machine Learning
  • Neural Networks
  • Pattern Recognition
  • Recognition
  • Synthetic Aperture Radar
  • Target Recognition

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Marine Hydrodynamics

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Microelectronics