• Jitendra Sharma
• Narendra Patel
• Mohammad Abrar
• Samandh Prajapat

Plant diseases cause significant crop losses annually, affecting food security and farmer livelihoods worldwide. Early detection and diagnosis of plant diseases are crucial for effective treatment and prevention of yield loss. This research addresses the critical challenge of timely plant disease identification by proposing a mobile application named "AgroLab." Existing systems often require specialized knowledge or equipment, limiting accessibility for small-scale farmers. Our solution leverages Flutter for cross-platform mobile development and TensorFlow for machine learning-based disease detection. The application employs transfer learning techniques with convolutional neural networks to identify diseases in various crops by analyzing leaf images. AgroLab enables farmers to quickly scan plant leaves, receive instant disease diagnoses, and access treatment recommendations. The app aims to improve crop management practices, reduce pesticide overuse, and increase agricultural productivity. Additionally, the system prioritizes offline functionality, multilingual support, and user-friendly design to ensure accessibility across diverse farming communities.

Mobile App, Plant Disease Detection, Flutter, TensorFlow, Machine Learning.

"AgroLab: A Mobile Application for Leaf Disease Detection Using Flutter and TensorFlow", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.318-322, June-2025, Available :http://www.jetir.org/papers/JETIRGW06052.pdf

"AgroLab: A Mobile Application for Leaf Disease Detection Using Flutter and TensorFlow", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. pp318-322, June-2025, Available at : http://www.jetir.org/papers/JETIRGW06052.pdf