The Use of Statistical Image Classification In Assessing Antenna Pattern Measurements
Authors: Stuart Gregson, Allen Newell, Christian Feat, Frédéric Viguier
Publication: AMTA 2013
Copyright Owner: NSI-MI Technologies
Attempts to produce robust, objective, and quantitative measures of similarity between antenna pattern data sets using statistical methods have been widely reported in the open literature [1, 2]. Hitherto, such techniques have primarily been restricted to the purposes of comparing two or more images as a means in itself. However, no measurement can be considered to be completely free from error, and as such each data set inevitably contains an associated uncertainty. Therefore, in contrast to previous work, this paper discusses and extends some commonly used comparison techniques to take account of the finite, non-zero, measurement uncertainties that complicate the comparison process. Results are presented that illustrate the effectiveness of the comparison method and conclusions drawn.