Classification Of Rice Plant Diseases Using K-Nearest Neighbor Algorithm Based On Hue Saturation Value Color Extraction And Gray Level Co-Occurrence Matrix Features

Saniah, Siti (2024) Classification Of Rice Plant Diseases Using K-Nearest Neighbor Algorithm Based On Hue Saturation Value Color Extraction And Gray Level Co-Occurrence Matrix Features. JTOS (JURNAL TEKNOLOGI DAN OPEN SOURCE), 7 (2). pp. 212-223. ISSN 2622-1659

Full text not available from this repository.

Abstract

This research aims to classify diseases in rice plants using the K-Nearest Neighbor (K-NN) algorithm based on HSV color and GLCM texture feature extraction. The main problem is how to identify diseases in rice automatically using digital images. Diseases such as Blight, Tungro, and Crackle often attack rice, thus requiring an accurate early detection system. Lack of understanding in recognizing disease symptoms manually often leads to handling errors. This research develops an image processing-based classification system to detect rice diseases. The methods used include RGB to HSV color space conversion, texture feature extraction using GLCM, and classification using K-NN algorithm. The dataset consists of 240 images, divided into 192 training data and 48 testing data. Testing is done by calculating accuracy at parameter values K = 1, K = 3, and K = 5 to evaluate the model. The results showed that the combination of HSV and GLCM features produced the best accuracy at K=3 with 75% accuracy. This system can help farmers detect rice diseases quickly and effectively, minimize production losses, and support agricultural sustainability. This research is expected to provide practical solutions for farmers in detecting rice diseases, so that control can be carried out more accurately and efficiently.

Jenis Item:	Artikel
Uncontrolled Keywords:	K-Nearest Neighbor, HSV, GLCM, Rice Disease, Image Processing
Subjects:	000 Generalities > 004 Data processing Computer science
Divisions:	Artikel (Jurnal, Koran, Majalah)
Pengguna yang mendeposit:	Mr Muhammad Aditya
Date Deposited:	22 Sep 2025 04:57
Last Modified:	22 Sep 2025 04:57
URI:	http://repository.uinsu.ac.id/id/eprint/25955

Actions (login required)

View Item