GreenLife: An Intelligent Mobile-Based Plant Disease Detection System Using TensorFlow Lite
Year: 2026
Type: preprint
Abstract: Plant diseases cause significant yield losses in agriculture, threatening food security globally. Early detection of plant diseases is crucial for timely remediation. This paper presents Greenlife, a cross-platform mobile application built with Flutter that leverages an on-device TensorFlow Lite (TFLite) deep learning model based on the InceptionV3 architecture for real-time plant disease classification. The system detects 27 disease classes across multiple crop types including Apple, Corn, Grape, Tomato, and Potato. Firebase is used for authentication, and data storage. The proposed system achieves over 95 percent average classification accuracy on the PlantVillage dataset and operates fully on-device without requiring a network connection for inference, making it suitable for rural agricultural environments with limited connectivity.
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7223471254
Cites:
Cited by:
Related to: