SUBEKI, FAJAR (2024) PENGENALAN SETENGAH WAJAH MENGGUNAKAN ARSITEKTUR XCEPTION PADA METODE CONVOLUTIONAL NEURAL NETWORK. S1 thesis, Universitas Mercu Buana Jakarta.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (HAL COVER)
01 Cover.pdf Download (455kB) |
|
Text (ABSTRAK)
02 Abstrak.pdf Download (83kB) |
|
Text (BAB I)
03 Bab 1.pdf Restricted to Registered users only Download (81kB) |
|
Text (BAB II)
04 Bab 2.pdf Restricted to Registered users only Download (209kB) |
|
Text (BAB III)
05 Bab 3.pdf Restricted to Registered users only Download (116kB) |
|
Text (BAB IV)
06 Bab 4.pdf Restricted to Registered users only Download (1MB) |
|
Text (BAB V)
07 Bab 5.pdf Restricted to Registered users only Download (33kB) |
|
Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf Restricted to Registered users only Download (95kB) |
|
Text (LAMPIRAN)
09 Lampiran.pdf Restricted to Registered users only Download (2MB) |
Abstract
Facial recognition is a method of identifying an individual by using their face. It has become a technology widely used in various applications to verify a person's identity by comparing their facial features with stored facial data. This research aims to recognize individuals based on their facial features, specifically focusing on the upper half of the face in conditions where only this portion is accessible or visible. The study utilizes the Xception architecture in the Convolutional Neural Network (CNN) method, which can extract complex features from facial data, particularly focusing on the upper half of the face, including the forehead, eyebrows, and eyes. The research is conducted using attendance data of employees, consisting of 1020 datasets of the upper half of the face from various employees and 114 datasets of faces with masks. The results of the study involve four scenarios of dataset division, demonstrating the model's ability to accurately recognize faces. The best-performing scenario achieved an accuracy of 95%, precision of 96%, recall of 96%, and an F1-score of 95%. These metrics showcase the effectiveness of the model in accurately identifying individuals based on the upper half of their faces, even in scenarios where masks are worn. Keywords: Face Recognition, Half-Face, Xception, Convolutional Neural Network (CNN) Pengenalan wajah adalah suatu cara mengidentifikasi identitas seseorang menggunakan wajahnya. Pengenalan wajah menjadi suatu teknologi yang sering digunakan di berbagai kebutuhan untuk memverifikasi identitas seseorang apakah cocok dengan data wajah yang dimiliki. Penelitian ini bertujuan untuk mengenali seseorang dengan wajah yang dimiliki di dalam kondisi hanya setengah bagian wajah yang dapat diakses atau terlihat yaitu menggunakan setengah wajah bagian atas. Penelitian ini menggunakan arsitektur Xception pada Metode Convolutional Neural Network (CNN) yang dapat mengekstraksi fitur kompleks dari data wajah khususnya pada setengah wajah bagian atas mulai dari dahi, alis dan mata. Penelitian ini dilakukan menggunakan data absensi karyawan yang berisi 1020 dataset setengah wajah bagian atas dari berbagai karyawan dan 114 dataset wajah menggunakan masker. Hasil penelitian ini menggunakan 4 (empat) skenario pembagian dataset yang dapat mampu mengenali wajah seseorang dengan akurat dengan performance measure model dari skenario terbaik yaitu accuracy 95%, precission 96%, recall 96% dan f1-score 95%. Kata kunci : Pengenalan Wajah, Setengah Wajah, Xception, Convolutional Neural Network (CNN)
Actions (login required)
 |
View Item |
