Classification of Broad-Leaved Dock Plants Using Open Sprayer Images: A Comparative Study

Abstract

This paper presents a comprehensive analysis of a model developed for classifying images of broad-leaved dock plants and non-dock plants captured using open sprayers, specifically drones used in agricultural settings. The dataset, sourced from Kaggle, includes annotated images of both broad-leaved docks and non-dock areas. We introduce and evaluate a novel model, referred to as MC-OAFM, using performance metrics such as accuracy, precision, recall, and F1 score. The experimental results demonstrate that the proposed model achieves an accuracy of 98.9%, with precision, recall, and F1 score each at 98%. The performance of the MC-OAFM model is compared with existing models, highlighting its superior performance. The study underscores the efficacy of using advanced deep learning techniques for plant classification in agricultural domains.