Natural Texture Classification: A Neural Network Models Benchmark

In this paper a natural texture classification study was developed employing neural network models. The objective of this study was to assess the accuracy of each model for the classifying natural texture problem. Multi-layer Perceptron (MLP) network, Hopfield network, Self-organizing feature map (SOFM) network and a Radial Basis Function (RBF) network were the models studied, analyzed using the Neurosolutions version 5.0 (trial version) software and Weka version 3.4 software, in this work. A file, with more than 700 records of natural texture characteristics, which were obtained by the analysis of digital photographs of real landscapes, was used for the experiments. These natural textures were divided in 9 classes: water, ground-sand, grass, stones, sky, tree, mountain, snow and flowers. The experimental results showed that Multilayer Perceptron network was the best neural network model in the natural texture classification.