Mengklasifikasi Mata Uang Lima Ribu Rupiah dan Dua Ribu Rupiah dengan Menggunakan Algoritma CNN

Currency classification is one of the challenges in the field of digital image processing and computer vision which can be applied in various applications, such as ATM machines, automatic money exchange machines, and mobile banking applications. This research aims to develop a classification model that is able to differentiate between 5000 thousand rupiah and 2000 thousand rupiah currency using the Convolutional Neural Network (CNN) algorithm. CNN was chosen because of its ability to recognize complex visual patterns and specific features from images. The dataset used in this research consists of 10 currency images of 5000 thousand rupiah and 10 images of 2000 thousand rupiah taken in lighting conditions and viewing angles vary and are classified into 2 classes. The data is then processed and normalized to increase model accuracy. The proposed CNN model, namely the Squential Model, consists of several convolution layers, pooling layers, and fully connected layers which are optimized to detect visual differences between the two types of currency.