CropCare: Real-Time Plant Disease Detection Using CNN and TensorFlow Lite for Mobile-Based Agricultural Assistance
Author
Yashwardhan Bhosale, Prof S.N. Shelke, Shravan Sutar
Abstract
Agriculture remains a cornerstone of the global economy, yet crop productivity is significantly affected by plant diseases that often go undetected in early stages.
Traditional disease detection methods rely on manual inspection by experts, which is time-consuming, subjective, and often inaccessible to farmers in remote
regions. With the advancement of Artificial Intelligence, particularly Deep Learning, automated plant disease detection has emerged as a promising solution.
This paper presents the design and implementation of a real-time plant disease detection system using Convolutional Neural Networks (CNN) integrated with a
mobile application. The proposed system aims to assist farmers in early disease identification using smartphone-based image capture. A deep learning model is
trained on plant leaf datasets and optimized using TensorFlow Lite (TFLite) for efficient deployment on resource-constrained mobile devices.
The system follows a complete pipeline including image acquisition, preprocessing, model training, and mobile integration. Lightweight architectures are employed
to ensure real-time performance with minimal computational overhead. The trained model achieves high accuracy in classifying plant diseases such as early blight,
late blight, and healthy leaves.
The developed Android application enables users to capture leaf images and receive instant predictions along with disease information. This solution reduces
dependency on expert diagnosis and promotes precision agriculture. The system demonstrates strong performance, scalability, and usability in real-world
agricultural scenarios
Keywords
Plant Disease Detection ,Convolutional Neural Networks (CNN) , Deep Learning ,TensorFlow Lite (TFLite) ,Mobile-Based AI Systems,Precision Agriculture ,Image Classification , Agricultural Automation , Edge AI ,Real-Time Inference ,Smart Farming
Full Text:
Download Paper PDF
References
1.Jafar A, Bibi N, Naqvi RA, Sadeghi-Niaraki A and Jeong D (2024) Revolutionizing agriculture with artificial intelligence: plant disease detection methods, applications, and their
limitations. Front. Plant Sci. 15:1356260.
Ahmed S, Hasan MB, Ahmed T, Sony MRK, And Kabir MH (2022) Less Is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification. IEEE Access, 10, 68868-68884.
Nigar N, Faisal HM, Umer M, Okid O, And Lukose JM (2024) Improving Plant Disease Classification With Deep-Learning-Based Prediction Model Using Explainable Artificial Intelligence. IEEE Access, 12, 100005-100014.
Shelke SN, Yadav MP, & Salve S (2024) A Systematic Review of AI Driven Crop Disease Detection using Deep Learning: Analysis, Research Challenges and Future Trends.
Javidan SM, Banakar A, Rahnama K, Vakilian KA, Ampatzidis Y (2024) Feature engineering to identify plant diseases using image processing and artificial intelligence: A comprehensive review. Smart Agricultural Technology, 8, 100480.
Damaševičius, R., & Maskeliūnas, R. (2024). High-accuracy plant disease classification on edge computing devices using MobileNetV3- small.
