Hi, I'm trying to perform some wetland supervised classification, and I am getting quite a bit of spectral confusion, with overlapping and incorrect classes. I am using ERDAS 2014 and Landsat 8 imagery. When evaluating the training classes, some of the bands show quite distinct and separate histograms, while in other bands the histograms interfere with each other. Is there a way to only use some of the bands to classify certain training sites?
The only way I have seen so far is to create a subset image without certain bands. However, that requires a whole new training signature file to be made. Is there a quicker way? Thanks