Smart Agri Disease Detection of Black Gram Plant Leaf Using the Cloud-Based Yolov8 Intelligent System

Abstract

Infectious diseases affecting plants can have a major negative impact on economic output. Phenotyping plants is an essential part of plant characterization for tracking plant development over time. The urdbean leaf crinkle virus (ULCV) causes crinkled leaf disease, a plant disease that mostly affects black gram (Vigna mungo), a significant pulse crop in India. Crinkled disease is devastating to crops and the agricultural economy as a whole, causing farmers to lose out on a lot of money and harvests. Plant diseases cost USD 220 billion annually, according to the FAO (Food & Agriculture Organization). The early and accurate diagnosis of a disease (ULCV) is crucial for any economy that relies on agriculture. computer vision and Image processing are among the many cutting-edge methods for detecting plant diseases early. Preprocessing images, segmenting those images, extracting features, and applying machine learning algorithms to diagnose diseases are all viable options. Grey Level Co-occurrence Matrix (GLCM) is used for feature extraction. One of the machine learning methods used for detection is YOLO, which is based on a Convolutional Neural Network (CNN). In other words, YOLO led to more reliable disease diagnosis.