--- Start of Idrisi List message Dear Eric You are very helpful as always, thank you! A cloudy problem can become clearer when we discuss it. But, considering maxset again...what exactly is the evidence? I suppose it is the signature mean (belief) plus the signature variance (plausibility)(?). Then it must consider all the means and covariance from all signatures, for all bands. So, if maxset gives me evidence for two classes, does it mean that these two classes have covariance overlap ( probably what you call "pot")? If not, what is the procedure? I wanted to know if the fuzzy signature considers the percentage of participation of each signature in the mean...because as discussed before, the need to use a square matrix still makes me distrust it. In other words...what is going on behind the scene? Justin, thanks also for your answer, but PCA gives correlation between two bands, and I would need at least between three. The results can be quiet different. I did not put it in my question. Sorry! I cannot find a software that can do it... Beatriz R. Luz --- End of Idrisi List message IDRISI-L is an unmoderated list. As a service to list users, please post a summary of useful responses to your questions. To post a message to IDRISI-L, send it to [EMAIL PROTECTED] To subscribe to the list, send an email from the address to be subscribed to [EMAIL PROTECTED] with "subscribe" (without quotes) as the first line of the message body. To unsubscribe, do the same, only with "unsubscribe" as the first line of the message body.
