PERANCANGAN APLIKASI MOBILE PROTOTIPE LOKER PINTAR BERBASIS PENGENALAN WAJAH MENGGUNAKAN ALGORITMA LBPH UNTUK MENINGKATKAN KEAMANAN PENGGUNA

Rafiano Daniswara, . (2025) PERANCANGAN APLIKASI MOBILE PROTOTIPE LOKER PINTAR BERBASIS PENGENALAN WAJAH MENGGUNAKAN ALGORITMA LBPH UNTUK MENINGKATKAN KEAMANAN PENGGUNA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (100kB)
[img] Text
AWAL.pdf
Download (987kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (144kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (246kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (89kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (178kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (101kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (22MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (1MB)

Abstract

Security in storage systems is becoming increasingly important, especially in public environments such as mosques. This research aims to design and develop a prototype mobile application for Android that supports a smart locker system using facial recognition for user verification. The algorithm used is Local Binary Pattern Histogram (LBPH) due to its efficiency and accuracy in recognizing faces, even under poor lighting conditions. The system was developed in two main stages: an initial prototype built using Visual Studio Code and a refined version deployed as an Android application using Android Studio. The system is also integrated with MediaPipe Face Detection to identify facial landmarks and a blink-based liveness detection feature to prevent face spoofing. User face datasets are stored in Supabase Storage, and locker status metadata is managed via the Supabase REST API. The system allows users to register by scanning their face and entering their name, then unlock or lock the locker only if the detected face matches the stored data. Test results show that for optimal face recognition performance, the dataset should avoid having too many labels, and each label should not contain an excessively large number of classes.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511011] [Pembimbing: Indra Permana Solihin] [Penguji 1: Henki Bayu Seta] [Penguji 2: Radinal Setyadinsa]
Uncontrolled Keywords: LBPH, Face Recognition, MediaPipe, Android, Liveness Detection, Supabase, Smart Locker
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: RAFIANO DANISWARA
Date Deposited: 14 Aug 2025 02:19
Last Modified: 15 Aug 2025 00:46
URI: http://repository.upnvj.ac.id/id/eprint/37441

Actions (login required)

View Item View Item