ABSTRACT
The basic strategy in supervised classification is to sample areas of known cover types to determine representative spectral values of each cover type. Supervised classification has several potential advantages over unsupervised classification. There are several potential disadvantages with supervised classification when compared to unsupervised classification. Training fields are commonly transferred from aerial photographs to base maps and then digitized from maps using a digitizing tablet. A better classifier under high covariance conditions is the maximum likelihood classifier. The classified image is produced by using the likelihood functions and comparing the smartweed and cattail likelihood values for each pixel. All pixels with values less than 25 are predicted to be smartweed, and all pixels with values greater than 25 are predicted to be cattail.
