Implementasi face recognition berbasis internet of things menggunakan aws iot greengrass

Guinarto, Griselda (2021) Implementasi face recognition berbasis internet of things menggunakan aws iot greengrass. Bachelor thesis, Universitas Pelita Harapan.

	Text (Title) Title.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (4MB)
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (378kB) | Preview
	Text (ToC) ToC.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (893kB)
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (591kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (6MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (306kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (464kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB)

Abstract

Teknologi biometrik telah menjadi pilihan untuk melakukan identifikasi individu dalam berbagai bidang industri. Salah satu biometrik yang kerap digunakan adalah pemindai sidik jari. Namun, di masa pandemi COVID-19, melakukan identifikasi individu tanpa adanya kontak langsung sangat dianjurkan untuk mencegah penularan virus COVID-19. Pada penelitian ini akan dilakukan perancangan sistem pengenalan wajah untuk melakukan identifikasi individu tanpa adanya kontak langsung. Perancangan sistem pengenalan wajah akan menerapkan teknologi Internet of Things (IoT) dan edge AI. Perancangan sistem pengenalan wajah akan menggunakan algoritme Viola-Jones untuk mendeteksi wajah dan Local Binary Pattern Histogram (LBPH) dalam mengenali wajah melalui pemanfaatan library OpenCV. Implementasi sistem pengenalan wajah akan diintegrasi ke Raspberry Pi menggunakan AWS IoT Greengrass dan dilengkapi dengan pengiriman notifikasi berupa email ke pengguna mengenai identitas dari wajah yang terdeteksi. Adapun peracangan dashboard yang ditujukan sebagai penyajian data secara keseluruhan mengenai identitas dari wajah yang terdeteksi. Sistem pengenalan wajah yang dirancang menunjukkan tingkat akurasi sebesar 75% dalam mengenali wajah. Sistem yang dirancang dapat mengenal wajah dengan benar pada jarak 30 cm dan 50 cm dengan pencahayaan terang atau gelap. Namun, sistem masih memiliki kesulitan untuk mendeteksi wajah yang menggunakan masker. Sistem yang telah dirancang dapat bekerja dengan baik dari proses deteksi dan identifikasi individu hingga pengiriman email ke pengguna./Biometric technology has become the option for individual identification in various industrial fields. One of the most commonly used biometrics is fingerprint scanner. However, during the COVID-19 pandemic, identifying individual without direct contact is highly recommended to prevent transmission of the COVID-19 virus. In this study, a face recognition system will be designed to identify individual without direct contact. The design of the facial recognition system will apply Internet of Things (IoT) technology and edge AI. The design of the face recognition system will use the Viola-Jones algorithm to detect faces and the Local Binary Pattern Histogram (LBPH) algorithm to recognize faces through the use of the OpenCV library. The implementation of the facial recognition system will be integrated into the Raspberry Pi using AWS IoT Greengrass and equipped with sending notifications in the form of email to user regarding the identity of the detected face. The dashboard design is intended as a presentation of the overall data regarding the identity of the detected face. The designed facial recognition system shows an accuracy rate of 75% in recognizing faces. The designed system can recognize faces correctly at a distance of 30 cm and 50 cm with bright or dark lighting. However, the system still has difficulty detecting face that wears mask. The system that has been designed can work well from the detection and identification process of individual to sending email to user.

Actions (login required)

View Item