• 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.

    Hybrid Algoritma Adaboost dengan Metode Color Space Transformation and Lighting Compensation untuk Mendeteksi Wajah Berdasarkan Emosi

    View/Open
    Fulltext (2.449Mb)
    Date
    2021
    Author
    Linhar, Ade
    Advisor(s)
    Tulus
    Zarlis, Muhammad
    Metadata
    Show full item record
    Abstract
    In this study, facial recognition was performed using the Adaboost hybrid algorithm with the method of color space transformation and lighting compensation (CST-LC) to detect faces based on emotions. This study aims to improve facial recognition in the research. Face detection was carried out based on a combination of the skin color segmentation algorithm with the AdaBoost algorithm. The experimental results show that the value of the initial processing parameters using the CST-LC method is an average of PSNR 7.586 and MSE 50.86 and the results of face detection using a dataset with an accuracy value of 87.74 %. The value of the accuracy results in this study is still better than the contribution research above, which is 65.3% where the overall face detection performance in this study is 25.57% better than the research contribution above.
     
    Pada penelitian ini dilakukan pengenalan wajah dengan hybrid algoritma Adaboost dengan metode color space transformation dan lighting compensation (CST-LC) untuk mendeteksi wajah berdasarkan emosi. Penelitian ini bertujuan untuk melakukan perbaikan pengenalan wajah yang ada pada penelitian sebelumnya yang dilakukan deteksi wajah berdasarkan kombinasi algoritma segmentasi warna kulit dengan algoritma AdaBoost. Hasil percobaan bahwa nilai parameter pengolahan awal dengan metode CST-LC sebesar rata-rata PSNR 7,586 dan MSE 50,86 dan hasil pendeteksian wajah dengan menggunakan dataset dengan nilai akurasi sebesar 87,74 %. Nilai hasil akurasi pada penelitian ini masih lebih baik daripada penelitian kontribusi di atas yaitu sebesar 65,3 % dimana performansi pendeteksian wajah pada penelitian ini secara keseluruhannya lebih baik sebesar 25,57 % dari penelitian kontribusi di atas.

    URI
    https://repositori.usu.ac.id/handle/123456789/47373
    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