A Max-Min Measure for Image Texture Analysis

Abstract

A new technique for image texture analysis is described which uses the relative frequency of local extremes in grey level as the principal measure. This method is invariant to multiplicative gain changes (such as caused by changes in illumination level or film processing) and is invariant to image resolution and sampling rate if the image is not undersampled. The algorithm described is computationally simple and can be implemented in hardware for realtime analysis. Comparisons are made between this new method and the spatial dependence method of texture analysis using 49 samples of each of eight textures. The new method seems just as accurate and considerably faster. Copyright © 1977 by The Institute of Electrical and Electronics Engineers, Inc.