Farm Care Using ML

EasyChair Preprint 12549

Abstract

Timely and accurate detection of plant diseases is essential for crop health and food safety in modern agriculture. This paper presents an advanced plant disease detection application that uses Convolutional Neural Networks (CNN) for image analysis, TensorFlow for deep learning, FastAPI for backend support, and React.js/React Native for front-end user-friendly interfaces occur.The main functionality of the application is based on the CNN model trained on the trained plant images, which enables accurate detection and classification of plant diseases TensorFlow facilitates training and efficient simulation, and ensures execution real-time image processing.FastAPI acts as the backbone of the application, managing data processing, instance statistics, and user authentication. Its speed and scalability make it ideally suited for handling easy user requests and simultaneous transactions.On the front end, React.js is used for web interactions, while React Native is used for mobile devices to ensure a consistent user experience across platforms. Users can easily use their smartphones to take pictures of sick plants, upload photos to the web, or select photos from their device’s gallery

Keyphrases: CNN, Classification., Fast API, Plant Disease, Potato Plant, Tomato diseases, machine learning

@booklet{EasyChair:12549,
  author    = {Raghu Nadh Reddy Gali and Rana Pratap Makineni and Srija Gonela and Pradeepthi Dirisala},
  title     = {Farm Care Using ML},
  howpublished = {EasyChair Preprint 12549},
  year      = {EasyChair, 2024}}