30000

Histogram stretching does not change the DNs of an image, merely how the image is displayed. Vegetation indices will be calculated from the DN values of the bands themselves, not how it is displayed, so it is fine to use NDVI or any other vegetation index while using linear stretching. You can confirm this for yourself by inquiring a certain pixel, then changing the histogram to various stretches. The file pixel values for each band will stay the same, while the look up table values will changed based on the stretching.

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