Aplikasi Pengenalan Pola Citra Logo Obat Medis Menggunakan K-Means Clustering

Abstract

Trends in drug abuse have occurred since 2014 such as ATS abuse or chemicals such as over-the-counter PCC. People no longer follow the rules of using drugs according to applicable regulations, but many who buy and consume drugs without a doctor's prescription. These behaviors and actions can endanger health, so people need to know the use of drugs to be more safe for consumption, one of them by paying attention to the type of logo on the drug packaging. To make it easier to find out the name of the logo type on drug packaging, it is necessary to develop an application using digital image processing. The study began with taking a drug pattern image using a smartphone camera and the results were carried out cropping the logo image in detail. Furthermore, cropping (RGB) images are converted into binary images and grayscale images to be performed a feature extraction process that is metric, eccentricity, and GLCM. The results of testing the test image data, a percentage of 91.5% with an accuracy rate of 100% types of over-the-counter drugs, hard drugs, and narcotics, while over-the-counter drug images are limited to 66%.