CLASSIFICATION OF BROADLEAF AND GRASS WEEDS USING GABOR WAVELETS AND AN ARTIFICIAL NEURAL NETWORK

Abstract

A texturebased weed classification method was developed. The method consisted of a lowlevel Gaborwaveletsbased feature extraction algorithm and a highlevel neural networkbased pattern recognition algorithm. Thisclassification method was specifically developed to explore the feasibility of classifying weed images into broadleaf and grasscategories for spatially selective weed control. In this research, three species of broadleaf weeds (common cocklebur,velvetleaf, and ivyleaf morning glory) and two grasses (giant foxtail and crabgrass) that are common in Illinois were studied.After processing 40 sample images with 20 samples from each class, the results showed that the method was capable ofclassifying all the samples correctly with high computational efficiency, demonstrating its potential for practicalimplementation under realtime constraints.