ANDROID-BASED WHITEFLY DETECTION USING DEEP LEARNING TECHNIQUES

Abstract

Whiteflies pose a significant threat to agricultural productivity worldwide, causing damage to crops and economic losses. In this study, we present an Android-based whiteflies detection system utilizing deep learning techniques, specifically leveraging the YOLOv5 algorithm. The objective is to create a robust and efficient solution capable of real-time whitefly detection in agricultural fields. The proposed system capitalizes on the powerful capabilities of YOLOv5, a state-of-the-art object detection algorithm, known for its accuracy and speed. By training the model on a comprehensive dataset of whitefly images, we optimized the network to accurately identify and localize whiteflies within the crop environment. Additionally, to ensure the practicality and accessibility of the solution, the trained YOLOv5 model was integrated into an Android application. This application provides a user-friendly interface for farmers and agricultural experts, enabling real-time deployment on mobile devices commonly used in the field.