IMPLEMENTATION OF LOCAL BINARY PATTERN HISTOGRAM AND K-NEAREST NEIGHBOR IN THE CLASSIFICATION OF POTATO LEAF DISEASE IMAGES

Triningsih, Wahyu (2026) IMPLEMENTATION OF LOCAL BINARY PATTERN HISTOGRAM AND K-NEAREST NEIGHBOR IN THE CLASSIFICATION OF POTATO LEAF DISEASE IMAGES. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 19081010024_Cover.pdf Download (1MB)
	Text (Bab 1) 19081010024_Bab 1.pdf Download (24kB)
	Text (Bab 2) 19081010024_Bab 2.pdf Restricted to Repository staff only until 23 July 2029. Download (252kB)
	Text (Bab 3) 19081010024_Bab 3.pdf Restricted to Repository staff only until 23 July 2029. Download (505kB)
	Text (Bab 4) 19081010024_Bab 4.pdf Restricted to Repository staff only until 23 July 2029. Download (1MB)
	Text (Bab 5) 19081010024_Bab 5.pdf Download (13kB)
	Text (Daftar Pustaka) 19081010024_Daftar Pustaka.pdf Download (71kB)
	Text (Lampiran) 19081010024_Lampiran.pdf Restricted to Repository staff only until 23 July 2029. Download (223kB)

Abstract

Potato leaf diseases can reduce the quality and quantity of crop yields, making fast and accurate identification essential. Manual identification performed by farmers still has limitations because it depends on experience and subjective visual observations. This study aims to identify potato leaf diseases using the Local Binary Pattern Histogram (LBPH) method for feature extraction and the K-Nearest Neighbor (KNN) algorithm for classification. The dataset consists of three classes, namely Early Blight, Late Blight, and Healthy, obtained from Kaggle. The research stages include image preprocessing through resizing and grayscale conversion, feature extraction using LBPH, and classification using KNN with K values of 3 and 5. Model performance was evaluated using a confusion matrix and classification accuracy. The results indicate that the LBPH method is capable of extracting texture characteristics from potato leaf images effectively, providing representative features for the KNN classifier. Based on the evaluation results of Recall 83.31%, Precision 90.52%, and F1-Score 81.02%, the KNN model with K = 3 achieved better performance than K = 5, which is 83.59%. The findings demonstrate that the combination of LBPH and KNN can be utilized to support automatic potato leaf disease identification and produce satisfactory classification performance. Keywords: Potato Leaf Disease, Local Binary Pattern Histogram, K-Nearest Neighbor, Digital Image Processing, Classification.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Al Haromainy, Muhammad Muharrom	NIDN0701069503	muhammad.muharrom.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Wahyu Triningsih

Date Deposited:

24 Jul 2026 07:44

Last Modified:

24 Jul 2026 07:44

URI:

https://repository.upnjatim.ac.id/id/eprint/57897