• 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.

    Klasifikasi Daun Mangrove Menggunakan Metode Mobilenet-Ssd Berbasis Mobile Secara Realtime

    View/Open
    Fulltext (3.230Mb)
    Date
    2021
    Author
    Siregar, Muhammad Alisiraj Fachreza
    Advisor(s)
    Rahmat, Romi Fadillah
    Purnamawati, Sarah
    Metadata
    Show full item record
    Abstract
    Mangroves are a group or individual plant species that live and form a community in the tidal and low tide areas. Mangrove forest itself consists of various types of trees and shrubs which are divided into 8 different families. Mangrove plants consist of several main parts in general plant body parts, such as stems, roots, flowers, leaves and fruit. Mangrove leaf data was taken on the mangrove beach in Perbaungan District, Serdang Bedagai Regency, which provides two types of mangroves, namely Rhizopora Mucronata and Avicennia Alba. In this study, there were 2124 mangrove leaf data. Then, the data goes through two stages of the pre-processing process, namely resizing to resize the leaf image data to 640 x 640 and labeling using the labellmg application to indicate special objects in the image and so that the image can be read by the system. The classification process uses the Mobilenet-SSD method to classify leaf image data into 2 classes, namely Rhizophora Mucronata and Avicennia Alba. The system built is able to produce an accuracy rate of 93.3%.
     
    Mangrove merupakan kumpulan atau individu dari tumbuhan yang hidup pada sebuah komunitas yang berada di daerah pasang dan surut. Hutan mangrove sendiri terdiri dari berbagai jenis pohon dan semak yang terbagi atas 8 famili yang berbeda. Tumbuhan mangrove terdiri dari beberapa bagian utama seperti pada bagian tubuh tumbuhan umumnya, seperti batang, akar, bunga, daun dan juga buah. Data daun mangrove diambil di pantai mangrove yang ada di Kecamatan Perbaungan Kabupaten Serdang Bedagai yang menyediakan dua jenis mangrove yaitu Rhizopora Mucronata dan Avicennia Alba. Pada penelitian ini, data daun mangrove berjumlah sebanyak 2124 data. Kemudian, data melalui dua tahap proses pre-processing yaitu resizing untuk mengubah ukuran data citra daun menjadi 640 x 640 dan labeling menggunakan aplikasi labellmg untuk menandakan objek khusus pada citra dan agar citra mampu dibaca oleh sistem. Proses classification menggunakan metode Mobilenet-SSD untuk mengklasifikasi data citra daun menjadi 2 Classes, yaitu Rhizophora Mucronata dan Avicennia Alba. Sistem yang dibangun mampu menghasilkan tingkat akurasi sebesar 93,3%.

    URI
    http://repositori.usu.ac.id/handle/123456789/43783
    Collections
    • Undergraduate Theses [800]

    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