Perancangan Aplikasi Sistem Pengenalan Wajah Dengan Metode Convolutional Neural Network (CNN) Untuk Pencatatan Kehadiran Karyawan = Design of Face Recognition System Application Based on Convolutional Neural Network (CNN) Method for Employee Attendance Recording System

Efanntyo, Efanntyo (2022) Perancangan Aplikasi Sistem Pengenalan Wajah Dengan Metode Convolutional Neural Network (CNN) Untuk Pencatatan Kehadiran Karyawan = Design of Face Recognition System Application Based on Convolutional Neural Network (CNN) Method for Employee Attendance Recording System. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (766kB) | Preview
[thumbnail of Abstract]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (800kB) | Preview
[thumbnail of ToC]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB) | Preview
[thumbnail of Chapter1]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB) | Preview
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (4MB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[thumbnail of Chapter6] Text (Chapter6)
Chapter6.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (303kB)
[thumbnail of Bibliography]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (621kB) | Preview
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (12MB)

Abstract

Dalam situasi menghadapi pandemi novel coronavirus (COVID-19), pemakaian masker wajah dan menjaga jarak antar sesama menjadi suatu kewajiban dalam beraktivitas. Hal ini diperkuat dengan saran yang diberikan oleh badan dunia yang berkecimpung untuk urusan kesehatan, yaitu WHO (World Health Organization), agar penggunaan masker dilakukan secara kontinu selama beraktivitas dengan menjaga jarak antar individu minimal 1 meter. Dengan mengacu pada hal tersebut, terjadi perubahan yang mencakup juga sistem pencatatan kehadiran (presensi) secara khusus karyawan perusahaan X. Bila sebelumnya sistem presensi perusahaan X menggunakan sidik jari (fingerprint) kini beralih ke sistem presensi berbasis pengenalan wajah (face recognition) dengan memanfaatkan salah satu pendekatan dalam deep learning, yaitu metode Convolutional Neural Network (CNN) untuk identifikasi wajah seseorang. Keunggulan sistem ini adalah memungkinkan orang bisa menjaga jarak saat melakukan presensi. Berdasarkan hasil observasi sistem presensi yang berjalan dan hasil studi kepustakaan dilakukan perancangan dan pengembangan aplikasi pencatatan kehadiran berbasis pengenalan wajah mengikuti RAD (Rapid Application Development). Bahasa pemrograman yang digunakan adalah bahasa Python dengan mengimplementasikan SSD (Single Shot Detection) dan fitur ekstraksi ResNet. Evaluasi pengukuran dilakukan pada jarak yang telah ditentukan antara wajah dan kamera dan diukur pada pencahayaan ruangan 200 lux dengan akurasi rata-rata 67%. Aplikasi ini juga memiliki fitur untuk mengirimkan email notifikasi kepada setiap karyawan yang berhalangan hadir pada hari kerja yang telah dijadwalkan. / In a situation facing the novel coronavirus (COVID-19) pandemic, wearing a face mask and keeping a distance between each other is an obligation in activities. This is reinforced by the advice given by the world organization involved in health affairs, namely the World Health Organization (WHO), so that the use of masks is carried out continuously during activities by maintaining a distance between individuals of at least 1 meter. Refering to that, the changes have occurred which include an attendance recording system (presence) specifically for employees of company X. Previously, the attendance system of company X used fingerprints but now changed to a face recognition-based attendance system by utilizing one approach in deep learning, namely the Convolutional Neural Network (CNN) method to recognized a person's face. The advantage of this system is that supports people to keep their distance when doing attendance. Based on the observation results on the current attendance system and literature studies, it is designed and developed an application based on facial recognition following RAD (Rapid Application Development). The programming language used is Python by implementing SSD (Single Shot Detection) and ResNet extraction features. Measurement evaluation was carried out at a predetermined distance between the face and the camera and measured at room lighting 200 lux with an average accuracy of 67%. This application also has a feature to send notification emails to every employee who is unable to attend on the scheduled working day.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Efanntyo, Efanntyo
NIM01035190015
efantyo@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Mitra, Aditya Rama
NIDN0305096901
aditya.mitra@uph.edu
Uncontrolled Keywords: Pengenalan wajah; Deep learning; Convolutional Neural Network; Python; SSD; ResNet
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Electrical Engineering
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Electrical Engineering
Depositing User: Users 9264 not found.
Date Deposited: 25 Feb 2022 01:52
Last Modified: 25 Feb 2022 01:52
URI: http://repository.uph.edu/id/eprint/46754

Actions (login required)

View Item
View Item