Determining training data requirements for template based normalized cross correlation

Peter Knee, Lee Montagnino, Shawn Halversen, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper, we investigate the effect of increasingly sparse training data sets on target classification performance using a template-based classifier. An often used method of template creation employs averaging of multiple target training chips for a predefined coverage swath. The inclusion of too many training chips results in a blurring of the predominant scatterers while averaging of too few training chips results in poor edge resolution. We use the public MSTAR data set to show that using all appropriate images for each template may not result in the best ATR performance. We successfully demonstrate the ability to reduce training data collection requirements by requiring fewer training chips per template.

Original languageEnglish (US)
Title of host publicationAutomatic Target Recognition XIX
StatePublished - Sep 8 2009
EventAutomatic Target Recognition XIX - Orlando, FL, United States
Duration: Apr 13 2009Apr 14 2009

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X


OtherAutomatic Target Recognition XIX
Country/TerritoryUnited States
CityOrlando, FL


  • Normalized cross correlation
  • Template generation
  • Training requirements

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Determining training data requirements for template based normalized cross correlation'. Together they form a unique fingerprint.

Cite this