Cahyono, Ferry (2020) Pengenalan Wajah Menggunakan Model Facenet Untuk Presensi Pegawai. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
07111850067013-Master_Thesis.pdf Download (2MB) | Preview |
Abstract
Penelitian ini membahas tentang metode yang sesuai untuk diterapkan dalam sistem presensi pegawai menggunakan wajah. Facenet adalah model yang dikembangkan Google yang mempunyai akurasi tertinggi dalam pengenalan wajah. Sementara Openface adalah pengembangan dari FaceNet yang dilatih dengan kumpulan data yang lebih kecil tetapi memiliki akurasi yang hampir sama dengan FaceNet. Hal yang dilakukan dimulai dengan mengambil gambar wajah pegawai untuk dijadikan dataset gambar. Dari dataset tersebut akan dilakukan preprosessing wajah dengan melakukan deteksi, pemotongan (cropping) dan mengubah ukuran (resize) wajah. Untuk kemudian diekstrak fitur vektor wajah ke dalam 128 dimensi menggunakan model Facenet. Dengan klasifikasi Support Vector Machine (SVM) pada dataset wajah digunakan untuk mengenali wajah pegawai akan dicatat hasil akurasi pengenalan wajah. Pengujian dilakukan dengan 2 langkah yaitu pengujian model dan pengujian sistem. Pada pengujian model dilakukan perbandingan antara Facenet dan Openface menggunakan 5 fold cross validation dan 10 fold cross validation didapatkan akurasi Facenet lebih tinggi yaitu 100% sedangkan Openface 93,3%. Pada pengujian sistem hanya dilakukan pada model yang mempunyai akurasi tertinggi yaitu Facenet dan didapatkan hasil akurasi 100% dengan menggunakan ambang batas (threshold) probabilitas pengenalan 0,25.
========================================================================================
This study discusses the appropriate method to be applied in a employee presence system using faces by comparing two deep learning architectural models, they are FaceNet and Openface. FaceNet is a model developed by Google researchers that has the highest accuracy in face recognition. While Openface is a development from FaceNet that is trained with smaller datasets but has an accuracy that is almost equal to FaceNet. This will start by taking the employee's face into an image dataset. From the dataset, the face preprocessing will be performed by detecting, cropping, and resizing the face. Then extracting facial features into 128 dimensions using the FaceNet and Openface. With the Support Vector Machine (SVM), the classification of facial features will be carried out to obtain accuracy. To validate the model, 5 and 10 fold cross-validations are used. FaceNet accuracy results that obtained are higher with perfect accuracy that is 100%, while Openface only 93.33% accuracy, but in the time of making facial features (embedding), Openface is four times faster than FaceNet. The implementation using the model with the highest accuracy (FaceNet) has the same results as the model testing that is 100% using the introduction threshold probability of 0.25
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Pengenalan wajah, facenet, openface, embedding, support vector machine |
| Subjects: | Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55101-(S2) Master Thesis |
| Depositing User: | FERRY CAHYONO |
| Date Deposited: | 06 Aug 2020 06:25 |
| Last Modified: | 17 May 2023 01:22 |
| URI: | http://repository.its.ac.id/id/eprint/76660 |
Actions (login required)
 |
View Item |