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

    Analisis Kinerja Local Binary Pattern (LBP) dan K-Nearest Neighbor (KNN) dalam Klasifikasi Citra Daun Menjari (Palminervis)

    View/Open
    Fulltext (4.989Mb)
    Date
    2021
    Author
    Ningtyas, Alyiza Dwi
    Advisor(s)
    Nababan, Erna Budhiarti
    Effendi, Syahril
    Metadata
    Show full item record
    Abstract
    The object recognition system have been studied by many researchers, but most of them only use one method, namely the K-Nearest Neighbor (KNN) method. This method is widely used for recognition systems because it can guarantee a relatively good level of accuracy, but has a weakness against noise. One way to overcome this weakness is to use the Local Binary Pattern (LBP) feature extraction method. To see how far the performance of the combination of the two methods is, an object recognition process is also carried out using a combination of KNN and Gray Level Co-Occurrence Matrix (GLCM). The input for the processing stage is to use data in the form of images of papaya leaves and chaya leaves (palminervis). The comparison between training data and test data in this study is 2:1. The experimental results show that the level of accuracy using LBP-KNN for training data is greater than using GLCM-KNN, i.e. the difference is 12% (95% versus 83%), while for test data the difference is 18% (76% versus 58%).
     
    Sistem pengenalan suatu objek telah banyak diteliti oleh para peneliti, namun sebagian besar hanya menggunakan satu metode saja, yakni metode K-Nearest Neighbor (KNN). Metode tersebut banyak digunakan untuk sistem pengenalan dikarenakan dapat memberikan jaminan tingkat akurasi yang relatif baik, namun memiliki kelemahan terhadap suatu noise. Salah satu cara untuk mengatasi kelemahan tersebut yaitu dengan menggunakan metode ekstraksi ciri Local Binary Pattern (LBP). Untuk melihat sejauh mana kinerja kombinasi kedua metode tersebut, dilakukan juga proses pengenalan objek menggunakan kombinasi KNN dan Gray Level Co-Occurrence Matrix (GLCM). Adapun sebagai input untuk tahap pemrosesan ialah dengan menggunakan data berupa citra daun pepaya dan daun chaya (palminervis). Perbandingan antara data pelatihan dan data pengujian dalam penelitian ini yakni 2:1. Dari hasil eksperimen memperlihatkan bahwa tingkat akurasi menggunakan LBP-KNN untuk data latih lebih besar dibandingkan menggunakan GLCM-KNN, yakni selisih sebesar 12% (95% berbanding 83%), sedangkan untuk data uji dengan selisih 18% (76% berbanding 58%).

    URI
    https://repositori.usu.ac.id/handle/123456789/46152
    Collections
    • Master Theses [621]

    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