Real Time Database Seleksi Wajah Digital Menggunakan Algoritma CAMshift

Abstract

<p class="AbstractTitle"><strong>Abstrak</strong></p><p class="BodyAbstract">Perkuliahan yang ditempuh 4-5 tahun mempengaruhi perkembangan fisik. Penelitian ini menggunakan data video digital mahasiswa. Hasil rekaman video digunakan untuk data set menentukan ciri tertentu yang dimiliki mahasiswa nantinya tersimpan dalam katalog database file digital.  Dimulai dari konversi video .mp4 menjadi format .AVI. Algoritma CAMShift menggunakan dasar warna HSV untuk pelacakan posisi wajah (tracking) dan mengenal wajah (recognition). Video durasi 1-2 detik menghasilkan 45-200 frame format PNG. Algoritma CamShift melakukan penghitungan nilai Hue data sample. Hasil seleksi area bounding box disimpan dalam database wajah. Tracking wajah menggunakan Meanshift switching Matlab–OpenGL. Penelitian bertujuan mendokumentasikan profil wajah berbentuk digital berdasarkan warna dominan kulit. Hasil uji pencocokan wajah dilakukan pada beberapa video play, keberhasilan deteksi: 100% terseleksi, 45%-60%, 80-90%, disimpulkan sekitar 50%-100% berhasil. Gerakan wajah akan tertangkap centroid bounding box, bila warna wajah dominan Hue.</p><p class="BodyAbstract"><strong>Kata kunci</strong><strong>:</strong> Algoritma Camshift; Database Wajah; Real Time; Seleksi Wajah; Warna Hue;</p><p class="BodyAbstract"> </p><p class="AbstractTitle"><strong>Abstract</strong></p><p class="BodyAbstract"><strong>[</strong><strong>Real Time for Digital Face Database Selection Using Cams</strong><strong>hift Algorithm]</strong> Education taken 4-5 years affects physical development. This study uses student digital video data. The recording results are used to identify certain characteristics possessed by a student later stored in the digital file database catalog. The stages of the study consisted of identification, recognition and matching of faces. It starts from converting .mp4 videos to .AVI format. The CAMShift algorithm uses basic HSV colors for tracking face position (tracking) and faces recognition. 1-2 seconds video produces 45-200 frames PNG file. The research aims to document the digital profile of a face based on the dominant color of the skin. The face matching test results were carried out on several video play, the success of detection: 100% selected, 45%-60%, 80-90%, concluded around 50%-100% successful. Face movements will be caught by the centroid bounding box, if the color of the face is dominant in Hue</p><p class="BodyAbstract"><strong>Keywords</strong><strong>:</strong> Camshift Algorithm, Database Faces Face Selection; Hue Color; Real Time</p>