DEVELOPING A MOBILE APPLICATION FOR IDENTIFYING DISEASES ON TOMATO LEAVES.

Abstract

In this thesis, we propose a method for detecting diseases on tomato leaves using deep learning, focusing on the YOLOv10-nano model due to its lightweight structure and high accuracy. A dataset of 12,008 images, consisting five classes which includes four diseases: Early blight, late blight, leaf mold, yellow leaf curl virus, along with one class representing healthy tomato leaves. The dataset was then utilized and divided into 70% for training, 20% for validation, and 10 % for testing. The YOLOv10-nano model achieved a mAP of 0.936, outweigh other models and demonstrating its suitability for real-time mobile applications. The resulting mobile application offers two key features: image-based recognition and live detection, providing a user-friendly tool for identifying tomato leaf diseases.