Comparison of Neural Network and Maximum Likelihood High Resolution Image Classification for Weed Detection in Crops: Applications in Precision Agriculture

Abstract

Selective application of herbicide in agricultural cropping systems provides both economic and environmental benefits. Implementation of this technology requires knowledge of the location and density of weed species within a crop. In this study, two image classification techniques (neural networks and maximum likelihood) are compared for accuracy in weed/crop species discrimination. In the summer of 2005, high spatial resolution (1.25 mm) ground-based hyperspectral image data were acquired over field plots of three crop species (canola, peas, and wheat) seeded with weeds, either redroot pigweed or wild oat. Neural network (NN) and maximum likelihood (MLC) classifiers were applied to these image data for comparison of accuracy in species discrimination. Both techniques preformed well in classifying single weed/crop mixtures with overall accuracies ranging from 92-97% and 88-96% using NN and MLC, respectively. NN classification accuracy showed slight improvements over MLC in all cases.