Information-theoretic bounds on target recognition performance based on degraded image data

Avinash Jain, Pierre Moulin, Michael I. Miller, Kannan Ramchandran

Research output: Contribution to journalArticlepeer-review


This paper derives bounds on the performance of statistical object recognition systems, wherein an image of a target is observed by a remote sensor. Detection and recognition problems are modeled as composite hypothesis testing problems involving nuisance parameters. We develop information-theoretic performance bounds on target recognition based on statistical models for sensors and data, and examine conditions under which these bounds are tight. In particular, we examine the validity of asymptotic approximations to probability of error in such imaging problems. Problems involving Gaussian, Poisson, and multiplicative noise, and random pixel deletions are considered, as well as least-favorable Gaussian clutter. A sixth application involving compressed sensor image data is considered in some detail. This study provides a systematic and computationally attractive framework for analytically characterizing target recognition performance under complicated, non-Gaussian models and optimizing system parameters.

Original languageEnglish (US)
Pages (from-to)1153-1166
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number9
StatePublished - Sep 2002


  • Automatic target recognition
  • Data compression
  • Imaging sensors
  • Multisensor data fusion
  • Object recognition
  • Performance metrics

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Information-theoretic bounds on target recognition performance based on degraded image data'. Together they form a unique fingerprint.

Cite this