Hyperspectral Imaging for Early Detection of  Tomato Bacterial Wilt

Author(s)	Rohit Krishnan Kandathil, Anuush M B, Anshu Prasad Sah, Ayush Binil Nair, Shalu Murali
Country	India
Abstract	Early and accurate detection of plant diseases is essential for improving crop health and minimizing yield losses. This study explores the application of hyperspectral imaging (HSI) combined with deep learning techniques for the early stage detection of tomato bacterial wilt, a severe and fast spreading crop disease. Spectral reflectance data collected from hyperspectral scans of tomato leaves were preprocessed using Savitzky-Golay smoothing, dimensionality reduction via Principal Component Analysis (PCA), and normalized before classification using a lightweight one-dimensional Artificial Neural Network (1D-ANN). The proposed model achieved a validation accuracy of 96% and a test accuracy of 89.77%, demonstrating high precision and robustness in distinguishing healthy and infected plants, even at asymptomatic stages. These findings highlight the potential of integrating HSI and deep learning for non-invasive, real time plant disease diagnosis, contributing to the advancement of precision agriculture systems.
Keywords	Hyperspectral Imaging(HSI), Artificial Neural Networks (ANNs), UAV-based Disease Surveillance, Spectral Normalization
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 16, Issue 2, April-June 2025
Published On	2025-06-30
DOI	https://doi.org/10.71097/IJSAT.v16.i2.6663
Short DOI	https://doi.org/g9r8d4

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology