A CNN-Based Framework for Accurate Detection of Plant Leaf Diseases

A CNN-Based Framework for Accurate Detection of Plant Leaf Diseases

Prof. Raghavendra Nagaralli 1, Sahana Manage 2, Muktha Dodwad 3, Sahana Bijaguppi 4, Lata Kambar 5

1,Assistant professor, Dept of ECE, KLS VDIT, Haliyal

2,3,4,5, Students of Dept of ECE, KLS VDIT, Haliyal,

Email: rpn@klsvdit.edu.in, sahanamanage26@gmail.com, dodwadmuktha@gmail.com, bijaguppisahana@gmail.com, latakambar70@gmail.com

Abstract   This study demonstrates how plant diseases significantly threaten global agricultural productivity and food security. This paper presents a deep learning-based mobile application that can detect plant diseases from leaf images using Convolutional Neural Networks (CNNs). The system was trained on a dataset comprising 38 classes of healthy and diseased plants leaves. The proposed solution combines image pre-processing, feature extraction using CNNs, and mobile deployment using a lightweight interface. The experimental results demonstrated high classification accuracy, low latency inference, and practical feasibility for real-world agricultural settings. The app further integrates features such as offline access, disease-specific treatment recommendations, and image-history tracking for farmer support.
Keywords: plant disease detection, deep learning, convolutional neural network (CNN), mobile application, image classification, agricultural AI, precision farming.