An AI-Powered Mobile Application for Crop Disease Detection Using MobileNetV2 and Flutter

Read full text Summarise with VIRAT
Authors: K. Dinakaran, Ponmozhi K
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Agriculture forms the basis of the Indian economy. However, crop disease has been a major problem in reducing crop yields. Small and marginal farmers cannot get expert advice in time. In this paper, we propose a mobile application known as SmartAgri Doctor, implemented using Flutter and TensorFlow Lite, to detect crop diseases in real time. The proposed system works on the concept of transfer learning with MobileNet V2 and the Plant Village dataset to detect diseases in crops like tomato, rice, brinjal, and sugarcane. TensorFlow Lite's model is quite light, and the proposed system runs in full offline mode. Once the disease has been identified, recommendations are provided for both organic and chemical treatments depending upon the severity of the disease. The results show that the validation accuracy of the proposed system is around 93.5%. It runs in real time and can be executed in normal Android devices. The proposed system provides a scalable, accessible, and sustainable solution for smart agriculture.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Water Quality Monitoring Technologies

Publication details

Journal / source
Iconic Research and Engineering Journals
Volume
9
Issue
9
Publication date
30 March 2026
Language
EN