Deep Learning-Based Classification of Quick Wilt Disease in Black Pepper Using Leaf Images

Abstract

Quick wilt disease, primarily caused by Phytophthora capsici, is one of the most destructive diseases affecting black pepper (Piper nigrum L.), leading to substantial yield losses and economic damage in pepper-producing regions. Early and accurate disease detection is essential for timely intervention and sustainable crop management. Conventional diagnostic methods rely on manual field inspection, which is often labor-intensive, time-consuming, and susceptible to human error. This study proposes a deep learning-based approach for the early detection of quick wilt disease in black pepper plants using leaf image analysis. A comprehensive dataset comprising healthy and infected leaf images was collected under varying environmental conditions and pre processed using image resizing, normalization, and data augmentation techniques to improve model generalization. Multiple state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNNs) and transfer learning models, were trained and evaluated to identify the most effective classifier. The proposed framework was assessed using standard performance metrics, including accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). The executed experiment produced strong leaf-classification performance for the evaluated models. The numerical results reported in this paper are taken only from the executed test evaluation. The proposed system offers an efficient, scalable, and cost-effective solution for automated disease monitoring and decision support in precision agriculture. The findings highlight the potential of deep learning and computer vision technologies to enhance black pepper disease management, reduce crop losses, and improve agricultural productivity. Future work will focus on integrating the proposed framework into mobile and edge computing platforms for real-time field deployment.