• 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.

    Implementasi Metode You Only Look Once (YOLO) Versi 5 untuk Identifikasi Keaslian Sepatu secara Realtime

    Thumbnail
    View/Open
    Cover_191402119 (578.3Kb)
    List of Tables_191402119 (35.91Kb)
    List of Figures_191402119 (165.9Kb)
    Full Text_191402119 (2.499Mb)
    Date
    2024
    Author
    Tantri, Brillian Jonathan
    Advisor(s)
    Hizriadi, Ainul
    Zendrato, Niskarto
    Metadata
    Show full item record
    Abstract
    Many prospective shoe buyers, particularly those interested in sneakers, encounter difficulties in ensuring the authenticity of the shoes they wish to purchase. Free trade has propelled the growth of the shoe industry in Indonesia, particularly for renowned imported shoe brands such as Converse, Adidas, Nike, Vans, and others. These renowned shoe brands have prompted shoe manufacturers to enhance their production in order to remain competitive in the market. Furthermore, in certain instances, these manufacturers and retailers imitate well-known shoe brands to attain greater profits. Furthermore, there have been several instances of fraud where manufacturers sell counterfeit shoes that are packaged in a manner that closely resembles the authentic product. Undoubtedly, this can result in significant losses for buyers who purchase genuine shoes at a higher price, only to ultimately receive counterfeit ones. The "You Only Look Once" (YOLO) method was employed in this study to discern between genuine and counterfeit shoes. Two types of shoes were identified in this research, namely Nike Air Force 1 and Nike Air Jordan 1. A total of 3,876 data were utilized in this study, with 3,574 data serving as training data and 302 data serving as validation data. Furthermore, 86 testing data were obtained through the use of a smartphone camera. The YOLO method has been employed to identify the authenticity of shoes. The test results indicate that the YOLO method has achieved a level of accuracy of 91.8%.
    URI
    https://repositori.usu.ac.id/handle/123456789/92073
    Collections
    • Undergraduate Theses [768]

    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