Pengenalan Wajah Berbasis Video menggunakan Discrete Cosine Transform dan Uniform Local Binary Pattern

Zulkarnain, Syavira Tiara (2019) Pengenalan Wajah Berbasis Video menggunakan Discrete Cosine Transform dan Uniform Local Binary Pattern. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05111540000002-Undergraduate_Theses.pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Pengenalan wajah telah menjadi bidang penelitian yang aktif beberapa tahun terakhir terutama karena meningkatnya tuntutan keamanan dan potensial aplikasi. Sistem pengenalan merupakan penerapan dari visi komputer yang berguna untuk mengidentifikasi wajah seseorang melalui citra wajah. Sementara sistem pengenalan berbasis video adalah sistem pengidentifikasian wajah seseorang bukan hanya melalui satu citra melainkan memperhatikan beberapa citra yang diperoleh melalui video. Tugas akhr ini mengembangkan sistem untuk mengidentifikasi seseorang saat memasuki ruangan melalui citra wajah. Dan sistem ini terdiri dari 4 tahapan utama, yaitu tahap deteksi wajah, ekstraksi fitur,klasifikasi dan proses fusi. Uji coba menggunakan 29 video, terdiri dari 18 video untuk training dan 11 video untuk testing. Setiap video terdiri dari satu orang yang sedang memasuki ruangan. Data testing video tersebut memiliki 10 kelas yang merupakan nama orang tertentu. Uji coba pengenalan wajah berbasis video menghasilkan akurasi 100%, sementara uji coba pengenalan wajah berbasis frame menghasilkan akurasi 91,94%.
====================================================================================================================================
face recognition has become very active research area in recent years mainly due to increasing security demans and its potential commercial. Face recognition system is one application of computer vision used for identifying a person's face through an image. Meanwhile, video based face recognition system is face identifier system not only identifying from one image but also considers sequence of image extracted from video. This final project develop system to identify someone when he/she is entering a room. This system consists of four main process,such as detection process, feature extraction process, classfication, and fusion process. Testing use 29 videos, consist of 18 videos as training set and 11 videos as testing set. Each video consists of one person entering the room. Video testing data have 10 classes which is name of the person. Testing of video-based face recognition system give 100% accuracy, while testing of frame-based face recognition system give 91,94%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Pengenalan Wajah, Seeta Face Detection, Kalman Filter, Discrete Cosine Transform, Uniform Local Binary Pattern, Support Vectore Machine, Fusion
Subjects:	Q Science > Q Science (General) T Technology > T Technology (General)
Divisions:	Faculty of Information and Communication Technology > Informatics > 55201-(S1) Undergraduate Thesis
Depositing User:	Syavira Tiara Zulkarnain
Date Deposited:	23 Jul 2026 02:58
Last Modified:	23 Jul 2026 02:58
URI:	http://repository.its.ac.id/id/eprint/65402

Actions (login required)

View Item