• 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.

    Modifikasi Speed-Up Robust Feature (SURF) dengan Histogram of Oriented Gradient (HOG) pada Klasifikasi Citra Blur

    View/Open
    Fulltext (2.935Mb)
    Date
    2017
    Author
    Tanjung, Mahardika Abdi Prawira
    Advisor(s)
    Nasution, Mahyuddin K. M
    Sitompul, Opim Salim
    Metadata
    Show full item record
    Abstract
    The human eye can directly distinguish objects from images. Such as animals, plants or inanimate objects that have been directly recognized by humans. However, the computer does not have the capability of such a human eye that can instantly recognize objects in the image. Because computers only recognize binary numbers 0 and 1. Bag of visual words is a method to present the image based on local features, where an image can be taken its characteristics, so as to distinguish the objects in the image. In the process, bag of visual words has the stages of determining the characteristics of the interest points. In this study, the determination of the interest point is modified using the speed-up robust feature with histogram of oriented gradients. Performance of these modifications generate consistent accuracy by using 5-scale detection of interest points.
     
    Mata manusia dapat secara langsung membedakan objek-objek pada citra. Seperti hewan, tumbuhan ataupun benda-benda mati yang telah dikenali secara langsung oleh manusia. Namun, komputer tidak memiliki kemampuan seperti mata manusia yang dapat langsung mengenali objek pada citra tersebut. Karena komputer hanya mengenali bilangan biner yaitu 0 dan 1. Bag of visual words merupakan suatu metode untuk mempresentasikan citra berdasarkan fitur lokal, dimana sebuah citra dapat diambil karakteristiknya, sehingga dapat membedakan objek-objek pada citra. Dalam prosesnya, Bag of visual words memiliki tahapan penentuan karakteristik yaitu interest point. Dalam penelitian ini, penentuan interest point dimodifikasi menggunakan speed-up robust feature dengan histogram of oriented gradients. Kinerja modifikasi tersebut menghasilkan akurasi yang konsisten dengan menggunakan 5 skala pendeteksian interest point.

    URI
    http://repositori.usu.ac.id/handle/123456789/43203
    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