Elsevier

Pattern Recognition

Volume 29, Issue 1, January 1996, Pages 27-49
Pattern Recognition

Target recognition in a cluttered scene using mathematical morphologu

https://doi.org/10.1016/0031-3203(95)00065-8Get rights and content

Abstract

This paper deals with the problem of locating targets within a cluttered gray-level digital image. The proposed new method is derived from principles in mathematical morphology. Basic morphological operations combined with some statistical techniques are used to generate a target recognition error function whose surface is minimized to estimate the probable location of a target. An automatic training procedure accompanies the new algorithm. The training provides the means by which the algorithm may automatically learn to deal with subtle differences in a target's appearance. A novel decomposition technique that provides some size invariance is also presented.

References (21)

There are more references available in the full text version of this article.

Cited by (6)

  • Image Analysis and Computer Vision: 1996

    1997, Computer Vision and Image Understanding
  • Lock-in imaging based on modulated white light

    2014, Guangdian Gongcheng/Opto-Electronic Engineering
  • Motion analysis and morphological approach for optical aerial conflict alarm in traffic alert and collision avoidance system (TCAS)

    2006, ITST 2006 - 2006 6th International Conference on ITS Telecommunications, Proceedings
View full text