Home / Current Issue / Paper 1713011
AgriAid: Android-based Crop Disease Detection and Advisory System
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Mobile App Development
Abstract
Agriculture faces mounting threats from plant diseases that significantly reduce yields and incomes for smallholder farmers. AgriAid is an Android-based application that provides offline, on-device crop leaf disease diagnosis using multiple optimized TensorFlow Lite (TFLite) models. The application supports several crops and executes real-time inference on resource-constrained devices, delivering high accuracy and low latency under varied field conditions. This paper presents the system design, model integration approach, implementation details, and empirical performance metrics obtained through extensive testing.
Keywords
Crop disease detection; TensorFlow Lite; offline inference; mobile agriculture; Android application.
References
[1] Sladojevic S., Arsenovic M., Anderla A., Culibrk D., and Stefanovic D.,“Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,”Proc. of IEEE International Conference on Information Technology (IT), 2020.DOI: 10.1109/IT48899.2020.9073732
[2] Ahamed M.S.F., and Hossain M.,“Plant Disease Detection Using Image Processing and CNN,”Proc. of IEEE International Conference on Artificial Intelligence and Smart Systems (ICAIS), 2021.DOI: 10.1109/ICAIS50930.2021.9395960
[3] Zhang S., Wu S., and Zhang X.,“Leaf Disease Detection Based on Improved Deep Learning Model,”IEEE Access, Vol. 8, 2020, pp. 1–12.DOI: 10.1109/ACCESS.2020.2981886
[4] Nguyen N.T.B., and Nguyen H.T.,“Mobile-Based Application for Plant Disease Diagnosis Using Deep Learning,”Proc. of IEEE International Conference on Computer Science and Software Engineering (CSSE), 2021.DOI: 10.1109/CSSE51882.2021.9375940
[5] Pramod H.C., and Shetty A.S.,“A Survey on Plant Disease Detection Using Deep Learning Techniques,”Proc. of IEEE International Conference on Inventive Computation Technologies (ICICT), 2020.DOI: 10.1109/ICICT48043.2020.9112460
[6] Khanday M.H., Rafiq Q., and Sofi S.,“Detection of Leaf Disease Using Machine Learning and Mobile Vision,”Proc. of IEEE Innovative Research in Science, Engineering and Technology (NCIRSET), 2021.DOI: 10.1109/NCIRSET54393.2021.9664842
How to cite this paper
@article{1713011,
author = {Mohd Ayman Khan, Muhammad Umar Maniyar, Md Zulquar Nain, Tasaduque Ullah, Mrs. Mumtaj K P},
title = {AgriAid: Android-based Crop Disease Detection and Advisory System},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {1490-1493},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1713011.pdf},
abstract = {Agriculture faces mounting threats from plant diseases that significantly reduce yields and incomes for smallholder farmers. AgriAid is an Android-based application that provides offline, on-device crop leaf disease diagnosis using multiple optimized TensorFlow Lite (TFLite) models. The application supports several crops and executes real-time inference on resource-constrained devices, delivering high accuracy and low latency under varied field conditions. This paper presents the system design, model integration approach, implementation details, and empirical performance metrics obtained through extensive testing.},
keywords = {Crop disease detection; TensorFlow Lite; offline inference; mobile agriculture; Android application.},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1713011}
}