Performance Analysis of Support Vector Machine and Bayesian Classifier for Crop and Weed Classification from Digital Images

Abstract

In conventional cropping systems, removal of weed population tends to rely heavily on the application of chemical herbicides, which has had successes in attaining higher profitability. However, concerns regarding the adverse effects of excessive herbicide applications have prompted increasing interests in seeking alternative weed control approaches. Rather than the conventional method of applying herbicides uniformly across the field, an automated machine vision system that has the ability to distinguish crops and weeds in digital images to control the amount of herbicide usage can be an economically feasible alternative. This paper investigates the use of support vector machine (SVM) and Bayesian classifier as machine learning algorithm for the effective classification of crops and weeds in digital images and a performance comparison between these two methods. Young plants that did not mutually overlap were used in our study. A total of 22 features that characterize crops and weeds in images were tested to find the optimal combination of features for both methods which provides the highest classification rate. Analysis of the results reveals that SVM achieves above 98% accuracy over a set of 224 test images, where Bayesian classifier achieves an accuracy of above 95% over the same set of images.