Penerapan K-Means Clustering Pada Pengolahan Citra Jam Digital, Analog dan Monograph dengan Matlab

Dinantia, Triend
Ramadhanu, Agung

Jurnal Sains dan Teknologi
Vol. 5 No. 3 (2025): September-Desember

Manual grouping of clock types is time-consuming and prone to errors, necessitating an automatic method to accuratelyclassify digital, analog, and chronograph clocks. This study aims to implement the K-Means Clustering method ingrouping clock types using image processing techniques with Matlab. The applied method involves image processing withcolor space conversion from RGB to LAB, texture feature extraction using Gray-Level Co-occurrence Matrix (GLCM),and grouping using K-Means Clustering algorithm. Analysis was performed by calculating silhouette coefficient andDavies-Bouldin Index to evaluate cluster quality. Results show three clusters formed: analog clocks, digital clocks, andchronograph clocks with 99% accuracy, where 30 out of 30 image data were correctly identified. K-Means Clusteringmethod is proven effective and accurate in determining clock categories.