Foveal automatic target recognition using a multiresolution neural network

Susan S. Young, Peter D. Scott, Cesar Bandera

Research output: Contribution to journalArticlepeer-review

17 Scopus citations


This paper presents a method for detecting and classifying a target from its foveal (graded resolution) imagery using a multiresolution neural network. Target identification decisions are based on minimizing an energy function. This energy function is evaluated by comparing a candidate blob with a library of target models at several levels of resolution simultaneously available in the current foveal image. For this purpose, a concurrent (top-down-and-bottom-up) matching procedure is implemented via a novel multilayer Hopfield neural network. The associated energy function supports not only interactions between cells at the same resolution level, but also between sets of nodes at distinct resolution levels. This permits features at different resolution levels to corroborate or refute one another contributing to efficient evaluation of potential matches. Gaze control, refoveation to more salient regions of the available image space, is implemented as a search for high resolution features which will disambiguate the candidate blob. Tests using real two-dimensional (2-D) objects and their simulated foveal imagery are provided.

Original languageEnglish (US)
Pages (from-to)1122-1135
Number of pages14
JournalIEEE Transactions on Image Processing
Issue number8
StatePublished - 1998
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design


  • Automatic target recognition
  • Foveal images
  • Multiresolution images
  • Neural network


Dive into the research topics of 'Foveal automatic target recognition using a multiresolution neural network'. Together they form a unique fingerprint.

Cite this