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

    Implementasi Content Based Video Retrieval Menggunakan Metode Block Truncation Algorithm

    View/Open
    Fulltext (7.030Mb)
    Date
    2020
    Author
    Ananda, Meisy Putri
    Advisor(s)
    Sihombing, Poltak
    Efendi, Syahril
    Metadata
    Show full item record
    Abstract
    Content-Based Video Retrieval (CBVR) is a method of capturing video documents that are used to find video information based on video content, not only based on the name or description of the video. Content-Based Video Retrieval has three stages of processing, including the preprocessing stage, feature extraction, and feature matching. In the pre-processing stage, the video is segmented into frames and then selected several keyframes that can represent the video. In the extraction and feature matching stages the Block Truncation Algorithm is used as a method of extracting and matching features based on color. The parameters used to measure the quality of Content Based Video Retrieval system results are the values of Recall, Precision, and Running Time. Based on the test results using 25 videos divided into five categories, the average value of Recall is 44%, Precision’s average value is 89%%, and Running Time is 87,37 seconds.
     
    Content Based Video Retrieval (CBVR) merupakan sebuah metode temu kembali dokumen video yang digunakan untuk mencari informasi video berdasarkan konten yang terkandung dalam video tersebut sehingga tidak hanya mengandalkan nama atau deskripsi dari video. Content Based Video Retrieval memiliki tiga tahap pemrosesan, yaitu tahap praproses, ekstraksi fitur, dan pencocokan fitur. Pada tahap praproses dilakukan segmentasi video menjadi frame-frame untuk kemudian dipilih beberapa keyframe yang dapat mewakili video. Kemudian pada tahap ekstraksi dan pencocokan fitur digunakan Block Truncation Algorithm sebagai metode ekstraksi dan pencocokan fitur berdasarkan warna. Pencocokan fitur dilakukan dengan mengukur jarak query masukkan dengan data yang ada. Parameter yang digunakan untuk mengukur kualitas hasil sistem Content Based Video Retrieval adalah nilai dari Recall, Precision, dan Running Time. Berdasarkan hasil pengujian menggunakan 25 video yang terbagi atas lima ketgori diperoleh nilai rata-rata Recall sebesar 44%, nilai rata-rata Precision adalah 89%, dan Running Time adalah 87,37 detik.

    URI
    http://repositori.usu.ac.id/handle/123456789/25901
    Collections
    • Undergraduate Theses [1273]

    Repositori Institusi Universitas Sumatera Utara - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    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 - 2025

    Universitas Sumatera Utara

    Perpustakaan

    Resource Guide

    Katalog Perpustakaan

    Journal Elektronik Berlangganan

    Buku Elektronik Berlangganan

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV