Textural Features for Image Classification

TLDR

Texture is a key characteristic used to identify objects or regions in images, whether photomicrographs, aerial photographs, or satellite images. This paper presents easily computable gray‑tone spatial‑dependency textural features and demonstrates their use in classifying photomicrographs of five sandstone types, 1:20 000 panchromatic aerial photographs of eight land‑use categories, and ERTS multispectral imagery of seven land‑use categories. The authors applied two decision‑rule families—piecewise linear convex polyhedra and min‑max rectangular parallelpiped classifiers—trained on half of each dataset and evaluated on the remaining half. The classifiers achieved 89 % accuracy on sandstone photomicrographs, 82 % on aerial photographs, and 83 % on satellite imagery, indicating that the proposed textural features are broadly applicable to diverse image‑classification tasks.

Abstract

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 paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use 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). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.