Multilayer Perceptron Classifier Combination for Identification of Materials on Noisy Soil Science Multispectral Images

Abstract

Classifier combination experiments using the multilayer perceptron (MLP) were carried out using noisy soil science multispectral images, which were obtained using a tomograph scanner. Using few units in the MLP hidden layer, images were classified using a single classifier. Later we used classifier combining techniques as bagging, decision templates (DT) and Dempster-Shafer (DS), in order to improve the performance of the single classifiers and also stabilize the performance of the multilayer perceptron. The classification results were evaluated using cross-validation. The results showed stabilization of Multilayer Perceptron and improved results were achieved with fewer units in the MLP hidden layer.