%0 Generic
%A VIRA , VERINA 
%C UNIVERSITAS LAMPUNG
%D 2023
%F eprints:74981
%I FAKULTAS MATEMATIKA DAN ILMU PENGETAHUAN ALAM
%T CLUSTERING CITRA TANAMAN OBAT MENGGUNAKAN  METODE K-MEANS
%U http://digilib.unila.ac.id/74981/
%X Tanaman obat memiliki manfaat besar dalam menyembuhkan berbagai penyakit.  Banyak masyarakat yang menggunakan tanaman obat sebagai sumber tanaman obat  keluarga (TOGA). Bagian tanaman yang dapat dimanfaatkan sebagai obat adalah  daun. Daun sulit diidentifikasi karena banyak daun yang memiliki bentuk dan  warna yang mirip. Oleh karena itu, pengolahan citra dengan K-Means Clustering  diterapkan untuk membantu mengidentifikasi daun tanaman obat. Citra akan  discaling menjadi 600 x 800 piksel. Ciri tekstur pada citra akan dihitung  menggunakan Gray Level Co-occurrence Matrix (GLCM). GLCM menghasilkan  nilai numerik yang kemudian digunakan untuk proses K-Means Clustering. KMeans  Clustering akan mengelompokkan citra berdasarkan kesamaan nilai fitur  dan centroid terdekatnya. Jumlah cluster optimal yaitu k=3 berdasarkan  perhitungan nilai SSE. Hasil penelitian 900 dataset citra daun terbagi menjadi 3  cluster dengan akurasi tertinggi 51,54% pada cluster 2 yang memprediksi daun  binahong. Proses K-Means Clustering kurang baik dikarenakan penetuan nilai  centroid berpengaruh terhadap hasil cluster. K-Means Clustering  diimplementasikan ke dalam sistem web menggunakan flask.  Kata Kunci: K-Means Clustering, Gray Level Co-occurrence Matrix (GLCM),  Tanaman Obat, Flask    Medicinal plants have significant benefits in treating various diseases. Many  communities utilize medicinal plants as a source of family herbal medicine  (TOGA). The part of the plant that is often used for medicinal purposes is the leaves.  Identifying leaves can be challenging as many of them have similar shapes and  colors. Therefore, image processing with K-Means Clustering is applied to aid in  the identification of medicinal plant leaves. The leaf images are scaled to 600 x 800  pixels. The texture features of the images are computed using the Gray Level Cooccurrence  Matrix (GLCM) method. GLCM generates numerical values that are  later used in the K-Means Clustering process. K-Means Clustering method groups  the images based on the similarity of their feature values and their closest centroids.  The optimal number of clusters is determined to be k=3 based on the calculation of  the Sum of Squared Errors (SSE). The results show that out of 900 leaf image  datasets, the K-Means Clustering divides them into 3 clusters, with the highest  accuracy of 51.54% achieved in cluster 2, which predicts the binahong leaves. KMeans  Clustering process is less effective due to the influence of centroid  initialization on the clustering results. K-Means Clustering is implemented into a  web-based system using Flask.  Keywords: K-Means Clustering, Gray Level Co-occurrence Matrix (GLCM),  Medicinal Plant, Flask