A Study on Local Binary Pattern for Automated Weed Classification Using Template Matching and Support Vector Machine

Concerns regarding the environmental and economic impacts of excessive herbicide applications in agriculture have promoted interests in seeking alternative weed control strategies. In this context, an automated machine vision system that has the ability to differentiate between broadleaf and grass weeds in digital images to optimize the selection and dosage of herbicides can enhance the profitability and lessen environmental degradation. This paper presents an efficient and effective texture-based weed classification method using local binary pattern (LBP). The objective was to evaluate the feasibility of using micro-level texture patterns to classify weed images into broadleaf and grass categories for real-time selective herbicide applications. Two well-known machine learning methods, template matching and support vector machine, are used for classification. Experiments on 200 sample field images with 100 samples from each category show that, the proposed method is capable of classifying weed images with high accuracy and computational efficiency.