<![CDATA[This study aimed to classify the nominal value of Rupiah banknotes using image processing and classification methods. The research design was conducted by collecting a dataset of Rupiah banknotes consisting of 30 classes, each with 100 images. This research uses image preprocessing by using Canny Segmentation to create the edges of objects and clarify image details. The Hu Moments method, which describes the pixel distribution and shape of objects, was used to extract special features from images. Furthermore, classification modeling was carried out with Decision Tree and Random Forest to classify banknotes based on extracted characteristics. Model evaluation was carried out by measuring accuracy, precision, recall and f1-score performance and using cross-validation with k-fold = 5. The results showed that the Random Forest method was able to classify Rupiah banknotes well. In performance evaluation, the Random Forest method achieved an accuracy of 0.93 and good precision, recall, and f1-score scores for several banknote classes. The Decision Tree method also achieved good results, with an accuracy of 0.86. The results of the classification evaluation showed that the Random Forest method was better than the Decision Tree in classifying the banknotes.]]>
Copyrights © 2024
