Implementing K-Nearest Neighbor to Classify Wild Plant Leaf as a Medicinal Plants

Sahenda, Lalitya Nindita (2023) Implementing K-Nearest Neighbor to Classify Wild Plant Leaf as a Medicinal Plants. Matrik: Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer, 23 (1). pp. 29-38. ISSN 2476-9843

	Text 2023_Matrik_Implementing K-Nearest Neighbor to Classify Wild Plant Leaf as a Medicinal Plants.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (1MB)
	Text 2023_Matrik_Similarity_Implementing K-Nearest Neighbor to Classify Wild Plant Leaf as a Medicinal Plants - Lalitya Nindita.pdf - Additional Metadata Available under License Creative Commons Attribution Share Alike. Download (2MB)

Abstract

The public has difficulty distinguishing medicinal leaves from wild plant leaves due to the similarityin leaf shape. Therefore, this study aimed to create a system to help increase public knowledge aboutwild plant leaves that also function as medicinal plants by the KNN method. Leaves of wild plants,namely Rumput Minjangan, Sambung Rambat, Rambusa, Brotowali, and Zehneria japonica, are alsomedicinal plants in comparison. Image processing techniques used were preprocessing, image seg-mentation, and morphological feature extraction. Preprocessing consists of scaling and splitting theRGB components and using an RGB component decomposition process to find the color componentthat best describes the leaf shape and generate the blue component image. The segmentation processused a thresholding technique with a gray threshold value (T) of less than 150, which best separatesobjects and backgrounds. Some morphological feature extraction used are area, perimeter, metric,eccentricity, and aspect ratio. Based on the results of this research, the KNN method with variations inK values, namely 13, 15, and 17, obtained a system accuracy of 94.44% with a total of 90% trainingdata and 10% test data. This comparison also affected the increase in system accuracy.

Actions (login required)

View Item