Target recognition in a cluttered scene using mathematical morphology

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.