Texture-Tone Study with Application to Digitized Imagery.

Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This report describes some easily computable textural features based on grey tone spatial dependencies and illustrates their application in category identification tasks of three different kinds of image data: photomicrographs of 5 kinds of sandstones, 1:20,000 panchromatic aerial photographs of 8 land use categories and ERTS (Earth Resources Technology Satellite) multispectral imagery containing 7 land use categories. The author uses two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule) and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). Another application of texture analysis is with respect to camouflage design problems and the author develops a textural transform for the feature extraction of camouflage clutter.