RICE LEAF DETECTION SYSTEM USING DEEP LEARNING WITH CONVOLUTIONAL NEURAL NETWORK MODEL

SURYADI, ADI (2026) RICE LEAF DETECTION SYSTEM USING DEEP LEARNING WITH CONVOLUTIONAL NEURAL NETWORK MODEL. Tugas Akhir thesis, University of Technology Yogyakarta.

Text 5220411008_ADI SURYADI_ABSTRAK.pdf Download (134kB)

Abstract

ABSTRACT Early detection of rice leaf diseases is essential for maintaining agricultural productivity, as rice is a major commodity in Indonesia. However, many convolutional neural network (CNN) studies still rely on laboratory datasets that do not adequately represent field conditions. This study aims to develop a CNN-based system for classifying rice leaf diseases using field imagery. The research employs an R&D approach following the waterfall model, including needs analysis, preprocessing (resizing and augmentation), design, web implementation, and black-box testing. The results demonstrate that the system achieves 94.27% accuracy, 0.93 precision, 0.90 recall, and 0.91 F1-score. The best performance was observed in the blast and blight classes, while the largest classification error occurred in the tungro class due to its visual similarity to blast in the early stages. The system supports automatic diagnosis through image uploads and exhibits stable learning performance. This research delivers an accurate, field-data-based detection system ready for deployment in agricultural environments.

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General) > T201 Patents. Trademarks
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	05 May 2026 03:50
Last Modified:	05 May 2026 03:50
URI:	http://eprints.uty.ac.id/id/eprint/19781

Actions (login required)

View Item