<![CDATA[Each type of robusta and arabica coffee grown in different places will have significant differences in shape and taste because the coffee itself has a rich taste. Each type also has a different price depending on the grade and taste produced. So far, knowing the types of Robusta and Arabica coffee from Timor is only based on sight and knowledge, so it does not rule out the possibility of errors due to differences of opinion for each assessment, because of this a classification system for Timor coffee beans was developed. using digital image processing techniques. In classifying coffee images, an algorithm is needed that can work properly according to the characteristics of the data to be processed. The feature extraction process is carried out using the Gray Level Co Occurrence Matrix (GLCM) method, which is a texture-based feature extraction method that aims to obtain information from an image to be classified. The classification process is carried out by comparing the Distance Space in the K-Nearest Neighbors (K-NN) method. The data used in this study were 200 datasets which were divided into 150 training data and 50 test data, with the distribution of datasets using the Holdout method. The performance of K-Nearest Neighbors with the GLCM feature which gives the best results is the Euclidean Distance space with 1 Neighbors with an accuracy result of 88%.]]>
Copyrights © 2023
