A Comparison of Texture Feature Algorithms for Urban Settlement Classification

Texture features derived using Haralick´s Gray-Level Cooccurrence Matrix (GLCM) are by far the most popular in urban remote sensing research - but are they the best features for every application? In order to select the most appropriate texture algorithm for an automated informal settlement classification system, we performed an experiment to compare the performance of the GLCM with that of other texture features. The performance of a texture feature is measured by computing the classification accuracy achieved on a supervised set of images spread over 8 settlement classes, focusing on informal and low-cost housing. The results show that GLCMs perform very well, but that Local Binary Pattern texture features have a small advantage in this classification problem.