• 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.

    Penerapan Metode Deteksi Objek Faster R-Cnn dalam Digitalisasi Surat Batak

    View/Open
    Fulltext (3.999Mb)
    Date
    2022
    Author
    Sibuea, Tirza Priskila Kinanti
    Advisor(s)
    Muchtar, Muhammad Anggia
    Purnamawati, Sarah
    Metadata
    Show full item record
    Abstract
    The concept of digitization can be utilized in various things, including cultural sector. It intends to facilitate and help the works of community without consuming a lot of time and less of effort with the help of technology. The digitizing system of Batak manuscript helps users in converting the content of Batak manuscript on one image (*.jpg) into a digital document (*.docx) automatically. Application of Faster R-CNN as an object detection algorithm supports the system in recognizing and identifying objects in the form of Batak manuscripts contained in the input image. The system development consists of several stages—pre-processing, processing, and post-processing—and including data training process. The testing process of this application resulting an average accuracy of 90.2%.
     
    Konsep digitalisasi dapat dimanfaatkan pada berbagai sektor, termasuk kebudayaan. Hal ini bertujuan membantu masyarakat dalam memudahkan aktivitas atau pekerjaan secara efektif dan optimal tanpa memakan banyak waktu serta usaha dengan bantuan teknologi. Sistem digitalisasi surat Batak membantu pengguna dalam mendapatkan hasil konversi digital dari isi citra dokumen surat Batak (*.jpg) dalam bentuk *.docx secara otomatis. Penggunaan metode deteksi objek Faster R-CNN membantu sistem dalam mengenali dan mengidentifikasi objek yang berupa aksara Batak yang terkandung dalam citra input. Pembangunan sistem dilakukan dengan melakukan tahapan berupa pre-processing, processing, post-processing serta melibatkan proses pelatihan data. Berdasarkan hasil pengujian sistem, penerapan metode deteksi objek Faster R-CNN dalam digitalisasi surat Batak menghasilkan rata-rata akurasi sebesar 90.2%.

    URI
    https://repositori.usu.ac.id/handle/123456789/48592
    Collections
    • Undergraduate Theses [796]

    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