Scopus Indexed Publications

Paper Details


Title
Deep Learning for Detection of Mango Leaf Disease: A Comparative Study Using Convolutional Neural Networks Models
Author
Munshi Omar Faruque Rabbi, Israt Jahan, Lamia Rukhsara, Tapasy Rabeya,
Email
Abstract

The intricacy of diagnosing mango leaf disease is compounded by the multiplicity of crop types, variations in agricultural disease markers, and a multitude of environmental factors. Because they are infrequently utilized for early identification of many illnesses, existing solutions frequently rely on localized data. Farmers can avoid significant financial losses by taking immediate action to solve these problems. The novel image processing-based method for detecting mango leaf disease is explained in this paper. When the Proposed Convolutional Neural Network (CNN) model was used in the study, it achieved an amazing 97.92% accuracy in this unique scenario. The capacity of the model to differentiate between various leaf states was proven by a thorough series of experiments conducted on both healthy and damaged mango leaves. This technique provides a quick and effective way to detect diseases early on by making it easier to determine whether images of mango tree leaves are healthy or infected. This new approach may significantly enhance plant disease identification and treatment. Additionally, it raises the prospect of using comparable technologies in other agricultural settings, which might improve disease control and benefit the mango sector.

Keywords
"mango leaf disease detection , convolutional neural networks (cnn) , image processing in agriculture , deep learning for plant health"
Journal or Conference Name
Proceedings - 6th International Conference on Electrical Engineering and Information and Communication Technology, ICEEICT 2024
Publication Year
2024
Indexing
scopus