Visualizing Plant Disease Distribution and Evaluating Model Performance for Deep Learning Classification with YOLOv8

Area of Science:

• Agricultural Science
• Computer Vision
• Artificial Intelligence

Background:

• Plant diseases pose a significant threat to global food security, necessitating efficient detection methods.
• Traditional disease identification can be time-consuming and requires expert knowledge.
• Advancements in deep learning offer potential for automated and accurate plant disease diagnosis.

Purpose of the Study:

• To develop and evaluate a novel methodology for plant disease detection using the YOLOv8 object detection model.
• To assess the accuracy and robustness of the YOLOv8 model in classifying various plant conditions.
• To explore the suitability of YOLOv8 for real-time plant disease monitoring in agricultural settings.

Main Methods:

• Training a custom YOLOv8 model on a dataset of plant images.
• Evaluating the model's performance on a dedicated testing subset.
• Further validating the model's generalizability using a diverse set of unseen images from Google Images.

Main Results:

• The YOLOv8 model demonstrated high accuracy in detecting and classifying plant diseases.
• The model showed robust performance on both the training/testing datasets and unseen real-world images.
• YOLOv8 provided significant improvements in detection speed and precision compared to existing methods.

Conclusions:

• The proposed YOLOv8-based methodology is effective for accurate and rapid plant disease detection.
• This approach has strong potential for practical applications in early disease detection and prevention in agriculture.
• The use of YOLOv8 facilitates real-time monitoring, contributing to improved crop management and yield.