Klasifikasi Penyakit Daun Jagung dengan Ekstraksi Fitur Local Binary Pattern dan Fuzzy Color Histogram Menggunakan Algoritma Random Forest

Defanka, Galan Ahmad (2026) Klasifikasi Penyakit Daun Jagung dengan Ekstraksi Fitur Local Binary Pattern dan Fuzzy Color Histogram Menggunakan Algoritma Random Forest. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) Cover.pdf Download (637kB)
	Text (Bab 1) Text (Bab 1).pdf Download (106kB)
	Text (Bab 2) Text (Bab 2).pdf Restricted to Repository staff only until 23 January 2029. Download (738kB)
	Text (Bab 3) Text (Bab 3).pdf Restricted to Repository staff only until 23 January 2029. Download (1MB)
	Text (Bab 4) Text (Bab 4).pdf Restricted to Repository staff only until 23 January 2029. Download (2MB)
	Text (Bab 5) Text (Bab 5).pdf Download (31kB)
	Text (Daftar Pustaka) Text (Daftar Pustaka).pdf Download (99kB)
	Text (Lampiran) Text (Lampiran).pdf Restricted to Repository staff only until 23 January 2029. Download (224kB)

Abstract

Efforts to increase corn production in support of national food self-sufficiency face various challenges, one of which is disease attacks on corn plants that can reduce both the quality and quantity of crop yields. The identification of corn leaf diseases, which still relies on conventional visual observation methods, has limitations in terms of speed, accuracy, and dependence on observer expertise, making it less effective for early monitoring. Therefore, early monitoring of corn plant health is crucial to maintain crop productivity. The classification of corn leaf diseases is one of the main approaches to support such plant health monitoring. In this study, a corn leaf disease classification system based on image processing and machine learning was developed to identify four leaf conditions, namely leaf spot, leaf blight, leaf rust, and healthy leaves. The dataset used consisted of 1,200 corn leaf images, with 300 images for each class, which were then expanded to 3,600 images through data augmentation. The data processing stages included image preprocessing, segmentation, feature extraction, as well as training and testing of the classification model. Leaf texture characteristics were extracted using the Local Binary Pattern (LBP) method, while color characteristics were represented using the Fuzzy Color Histogram (FCH). All extracted features were used as input for the Random Forest algorithm to perform corn leaf disease classification. The experimental results show that the Random Forest algorithm achieved good classification performance with an accuracy of 95.83%. These results indicate that the combination of LBP texture features and FCH color features is effective in distinguishing corn leaf diseases and has the potential to support automatic and accurate detection of corn plant diseases.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Junaidi, Achmad	19781110 2025211 048	achmadjunaidi.if@upnjatim.ac.id
Thesis advisor	Maulana, Hendra	19831223 2025211 040	Hendra.maulana.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Galan Ahmad Defanka

Date Deposited:

23 Jan 2026 06:46

Last Modified:

23 Jan 2026 06:46

URI:

https://repository.upnjatim.ac.id/id/eprint/49006