• Version
• Download 4
• File Size 356.56 KB
• File Count 1
• Create Date 7 March 2025
• Last Updated 7 March 2025

AI-Powered Plant Disease Detection and Treatment

 

Authors:

Ettedi Ranadeesh, S.V. Hemanth, Ch. Saikiran Reddy, C. Manoj Kumar, D. Vinay

 

Abstract— Early diagnosis of plant diseases is essential to maximizing crop health and productivity. In order to solve this problem, this project presents a cutting-edge Android application that was created in Kotlin and uses deep learning methods. The Convolutional Neural Network (CNN) at the center of the program is trained on an extensive dataset of plant photographs and is intended to reliably identify a wide variety of agricultural illnesses from user-submitted images. Users may easily take or submit images of plants to the app, which makes it easier to identify diseases in real time. When an illness is identified, it offers tailored treatment suggestions along with practical advice and preventative techniques. By allowing customers to rapidly purchase suggested medications and therapies, the integrated "buy" button simplifies the procedure. The app also includes tools for tracking trends in plant health over time, which enables users to identify reoccurring problems and enhance their farming techniques. The software ensures anonymity and is easy to use, even for non-techies, thanks to its user-friendly layout and strong data security features. Farmers and gardeners may make more informed decisions, minimize crop loss, and increase agricultural output with the help of this program, which provides real-time analysis, actionable insights, and convenient access to necessary items.

Modern deep learning and mobile technologies are used in this research to meet the urgent requirement for prompt plant disease detection. Using a Convolutional Neural Network (CNN) that has been trained on a large and varied collection of plant photos, the Android app is able to recognize a wide variety of plant diseases, even those that have a similar appearance. In remote locations with poor connectivity, the CNN model is particularly well suited since it is designed to work seamlessly on mobile devices, guaranteeing high-speed analysis without requiring a continuous internet connection.

 

Keywords: 

Deep Learning, Android Application, Kotlin, Convolution Neural Network(CNN), Real-Time Analysis, Personalized Treatment, Integrated ECommerce, User-Friendly Interface, Plant Health Management, Agricultural Productivity, Medication Purchase, Diagnostic Accuracy

Download