• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Deteksi Keaslian Rupiah pada Uang Kertas Rupiah Tahun Emisi 2022 Menggunakan Metode You Only Look Once Versi 8

    Authenticity Detection of 2022 Emission Indonesian Rupiah Banknotes Using You Only Look Once Version 8 Method

    Thumbnail
    View/Open
    Cover (279.1Kb)
    Fulltext (1.045Mb)
    Date
    2024
    Author
    Muflihza, Tsabitah
    Advisor(s)
    Nurhasanah, Rossy
    Purnamawati, Sarah
    Metadata
    Show full item record
    Abstract
    Rupiah is a legal payment method in Indonesia and serves as a national symbol for the entire nation. One of the challenges faced in managing Rupiah currency is the circulation of counterfeit bills. Counterfeit Rupiah are currencies produced without legal permission from the state or government, with the intent to mimic official currency to deceive intended recipients. Most people cannot distinguish between genuine and counterfeit money because the 2022 emission Rupiah closely resembles fake money. Therefore, this research was conducted to enable the public to more easily detect counterfeit money in their surroundings by performing self-checks through their smartphones also implementing and analyzing the YOLO version 8 performance to detect the authenticity of Rupiah. This research focuses on detecting 2022 emission Rupiah bills, specifically the 50,000 and 100,000 denominations, which have colorchanging ink with flower images and glossy Bank Indonesia logos that alter colors depending on the viewing angle. The study implements the You Only Look Once version 8 method to create a system for detecting the authenticity of Rupiah bills. YOLOv8 demonstrates excellent performance in terms of detection accuracy and speed, while also producing lightweight models that are compatible with mobile applications. The model developed was then integrated into an Android-based mobile application. Using the YOLOv8 method to detect counterfeit and genuine 2022 emission Rupiah bills achieved a precision of 97%, recall of 97%, F1-score of 95%, and accuracy of 97%.
    URI
    https://repositori.usu.ac.id/handle/123456789/100834
    Collections
    • Undergraduate Theses [767]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV