An approach to form recognition based on non-linear projections, search and optimization

Victor L. Brailovsky*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

With the help of the family of non-linear projections and fitness functions introduced here, and using a standard evolutionary programming procedure, a broad class of parametric geometric primitives may be discovered in an image. The generalization of the notion of Mahalanobis distance proposed here permits this approach to be extended to non-parametric primitives. The suggested approach is highly robust.

Original languageEnglish
Pages (from-to)1099-1107
Number of pages9
JournalPattern Recognition Letters
Volume18
Issue number11-13
DOIs
StatePublished - Nov 1997

Keywords

  • Evolutionary programming
  • Fitness function
  • Generalized Mahalanobis distance
  • Non-linear projections

Fingerprint

Dive into the research topics of 'An approach to form recognition based on non-linear projections, search and optimization'. Together they form a unique fingerprint.

Cite this