Klasifikais Citra Uang Rupiah Menggunakan Uang Asli Dan Uang Palsu Untuk Mendeteksi Keaslian Uang Sebagai Alat Transaksi Jual Beli Dengan Mengunakan Algoritma CNN (Convolutional Neural Network)

Dhany, Maulana Supriadi (2021) Klasifikais Citra Uang Rupiah Menggunakan Uang Asli Dan Uang Palsu Untuk Mendeteksi Keaslian Uang Sebagai Alat Transaksi Jual Beli Dengan Mengunakan Algoritma CNN (Convolutional Neural Network). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (1MB)
	Text Abstract .pdf Download (210kB)
	Text Abstrak .pdf Download (230kB)
	Text BAB 1.pdf Download (763kB)
	Text BAB 2.pdf Download (2MB)
	Text BAB 3.pdf Download (1MB)
	Text BAB 4.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text BAB 5.pdf Download (221kB)
	Text Daftar Pustaka.pdf Download (779kB)
	Text Lampiran.pdf Restricted to Registered users only Download (624kB) | Request a copy

Abstract

Advances in information technology have a major influnce on the development of human life. This can have a positive impact and a negative impact on people’s behavior in utilizing technlogy. Money is an item that is very much needed as a transaction tool that can be in the form of a metal chip or a piece of paper and has a different nominal, but over time,pople in indonesia is still worried aboot the circulating fake rupiaj currency, this triggers criminal acts by people, irresposible. This study was made to assist the public in distinguishing between genuine and counterfeit rupiaj currencies when transacting. The method used in this stude is Deep Learning with the Convolutional Neural Network algorithm and the model used very commonly found namely the sequential mode. CNN is a type of neural network that is commonly used in the image data processing. This study uses the CNN algorithm because this algorithm is good for classifying images and objects. The images used in this study were 802 images where the image consisted of 4 classes, namely Rp 2,000 genuine, RP 2,000 fake, RP 5,000 genuine, and RP 5,000 fake. This model uses a learning rate parameter of 0.0001, a 3x3 kernel, and 3 iterations, namely 20 ephochs, 25 epochs, and 30 epochs.in the third iteration test, the model gets an accuracy of 100 % this test uses the second iteration with 25 epochs because the average accuracy is greater that the other 2 iterations. The number of images tested was 80 images, the average results were 100 % accurate. Keywords : Classification, Money, CNN, Deep Learning, Epoch

Actions (login required)

View Item