Title :
A system classification algorithm using neural networks
Author :
Mamlook, Rustom ; Thompson, Wiley E.
Author_Institution :
Dept. of Electr. & Comput. Eng., New Mexico State Univ., Las Cruces, NM, USA
Abstract :
A system classification algorithm to classify an image into targets and backgrounds is presented. The algorithm uses a double window filter in which the inner window surrounds the predicted target(s), and the outer window contains the predicted background(s). A solution to the problem of threshold selection is given. An example is given to illustrate the application of this algorithm for multi-target and multi-background classification
Keywords :
computer vision; image classification; neural nets; prediction theory; backgrounds; computer vision; double window filter; inner window; multi-background classification; multi-target classification; neural networks; outer window; predicted background; predicted target; system classification algorithm; threshold selection; Application software; Classification algorithms; Computer vision; Filters; Histograms; Military computing; Neural networks; Neurons; Pixel; Space technology;
Conference_Titel :
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-1760-2
DOI :
10.1109/MWSCAS.1993.343079
