Optimization based classifiers for road extraction

We investigate the performance of a linear programming-based decision tree in creating gray scale images for road extraction from AVIRIS images. We apply our method for classification of pixels from a digital image of an area near Williamsburg, Virginia, using the distance from discriminant lines as a measure to create a gray scale image. Our method effectively captures information from a large number of bands of the original image and can be a useful input to other techniques which can use only a single band