An Object Oriented Approach to Land Cover Classification: Case Study for the State of Ohio.

The usability of Land Cover maps primarily depends on its accuracy. This book covers the development of an object oriented approach to land cover analysis and evaluate this approach along with five other classifiers for accuracy in classifying Level II land-cover categories in Ohio. These methods consist of (1) USGS National Land Cover Data; (2) the spectral angle mapper; (3) the maximum likelihood classifier; (4) the maximum likelihood classifier with texture analysis; and (5) a recently introduced hybrid artificial neural network.