CNN Algorithm Implementation on Coins Classification

Putra, Dimas Riswanda Pradana and , Helmi Imaduddin, S.Kom., M.Eng. (2023) CNN Algorithm Implementation on Coins Classification. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) NASKAH PUBLIKASI.pdf Download (674kB)
	PDF (Surat Pernyataan Publikasi) Surat-Pernyataan-Publikasi.pdf Restricted to Repository staff only Download (195kB) | Request a copy

Abstract

Accurate coin classification is an important task with many real-world applications. Existing methods for coin classification suffer from various problems in efficiency and accuracy. This study presents an approach for coin classification using a convolutional neural network (CNN) with customized configurations and tests its performance using a data set of images taken by crawling technique of five different coin denominations. Then the level of performance is further evaluated using training-validation graphs, confusion matrix, and classification reports. The graph shows an accuracy rate of 88% in the last validation set with minimal overfitting and total accuracy on the f1 score which reaches 91%. This research is promising CNN in coin classification can open up new opportunities for further exploration in this field. The proposed algorithm has the potential to improve the efficiency and accuracy of future coin classification systems.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Digital Image Processing, Machine Learning, CNN, Computer Vision
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science > QA751 Artificial Intelligence T Technology > TZ Technical Information
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	DIMAS RISWANDA PRADANA PUTRA
Date Deposited:	21 Feb 2023 04:49
Last Modified:	21 Feb 2023 04:49
URI:	http://eprints.ums.ac.id/id/eprint/110283

Actions (login required)

View Item