As part of cooperative research between Jackson State University and the U.S. Bureau of Mines, a combination of image processing and geographic information system software has been developed to classify lineaments (linear features) derived from remote sensing data. Lineament analysis has proven to be a valuable tool for prediction of potentially hazardous geologic conditions in underground coal mines. The purpose of the current research effort is to partially automate the process of deriving lineaments from remote sensing data (e.g., satellite images) and determine whether such lineaments represent geological or manmade features on the earth's surface. The first phase of processing with the new software extracts all linear features from an image file produced through the U.S. Geological Survey's mini image processing system package. The second phase uses arc macro language programs to input the extracted lineaments into arc/info and compute the degree to which each lineament is manmade or geological, or that a lineament's origin cannot be determined from the available data. Digital line graphs, digital elevation models, and other user-supplied data sets are used in this comparison process to define the characteristics of each lineament.