Rafi Dwi Nugraha
Universitas Pembangunan Nasional "Veteran" Jawa Timur

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Severity Level Classification of Bacterial Leaf Blight Disease (Xanthomonas oryzae) in Rice Plants (Oryza sativa L.) Based on VARI Image Processing Rafi Dwi Nugraha; Hery Nirwanto; Sri Wiyatiningsih
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol. 15 No. 2 (2026): April 2026
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtepl.v15i2.652-662

Abstract

Bacterial leaf blight (BLB) caused by Xanthomonas oryzae is one of the main diseases threatening rice productivity in Indonesia. This study aims to classify the severity of BLB in rice plants more effectively using drone-based image processing technology with the VARI (Visible Atmospherically Resistant Index) vegetation index approach. The study was conducted in Wonoayu Subdistrict, Sidoarjo Regency, covering an area of 17 hectares using a DJI Phantom 4 Pro drone equipped with an RGB camera for image acquisition. The data was then analysed through pre-processing, segmentation using the K-Means Clustering method and edge detection, and classification using the Convolutional Neural Network (CNN) algorithm. The results showed that the CNN classification model was able to identify five levels of attack (healthy, mild, moderate, severe, and dead) with an accuracy of 82.25%, and the classification map was able to distinguish the spatial distribution of the disease in agricultural land. This model also showed better performance than conventional monitoring methods. The use of VARI-based image processing from drones has proven effective as an early disease detection method, providing precise solutions for rice plant health management.