The use of the two dimensional continuous wavelet transform for classification of targets in flir imagery, 1998
Semwogerere, Denis
1990-1999
Two dimensional continuous wavelet transforms have been used to study a wide variety of physical problems especially in the analysis of images. They are used in this particular application for the detection of discontinuities, which include edges, filaments, contours and boundaries between areas of different luminosity. In this study we investigate the use of a continuous wavelet transform partial energy density as a features detector in developing an algorithm for classification of targets in forward looking infrared imagery. Our algorithm specifically uses features that result from computing the partial energy densities of targets at all relevant scales and orientations and classification of those targets using a distance based classifier. We have found in our analysis that the partial energy density can extract target features that result in an overall improvement in classification in our algorithm.
text
application/pdf
1998-05-01
thesis
Master of Science (MS)
Clark Atlanta University
Physics
Murenzi, Romain
Georgia--Atlanta
http://hdl.handle.net/20.500.12322/cau.td:1998_semwogerere_denis