A Mobile-Based Deep Learning Approach for Mango Leaf Disease Detection Using TensorFlow Lite and Flutter Framework.

ABSTRACT Mango cultivation faces significant challenges from leaf diseases such as Gall Midge and Sooty Mould, which can reduce crop yield by up to 40% if not detected early. Traditional disease identification methods rely heavily on expert knowledge and laboratory analysis, which are time- consuming, expensive, and inaccessible to small-scale farmers. This study presents a comprehensive mobile-based solution for automated mango leaf disease detection using deep learning techniques deployed on mobile devices. The system employs a Convolutional Neural Network (CNN) optimized through quantization-aware training and deployed via TensorFlow Lite within a Flutter-based cross-platform mobile application. The dataset comprises 4,962 high-resolution images across three classes: Healthy, Gall Midge, and Sooty Mould, collected from agricultural research stations and field conditions.. The Flutter application enables farmers to capture leaf images through their smartphone cameras and receive immediate disease classification results with confidence scores, detailed disease information, and treatment recommendations. The system operates entirely offline, making it accessible in remote agricultural areas with limited internet connectivity. Results demonstrate that mobile-based deep learning can provide accurate, fast, and accessible plant disease detection, contributing to early intervention, reduced crop losses, and improved agricultural productivity for mango farmers globally. Keywords: Mango Leaf Disease Detection, TensorFlow Lite, Flutter Framework, Mobile Deep Learning, CNN Quantization, Agricultural Technology, Plant Disease Classification, On- Device Inference