Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal MULTINETICS
Tarigan, Ita Augustina
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Prototipe Pendeteksi dan Pengenalan Wajah Berbasis Web Menggunakan Algoritma Local Binary Pattern Histogram untuk Absensi Tarigan, Ita Augustina; Kurniawan, Asep
MULTINETICS Vol. 8 No. 1 (2022): MULTINETICS Mei (2022)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v8i1.4591

Abstract

Abstract-Face Detection and Recognition Prototype for Attendance is a prototype used to perform attendance by using a face as an object. The attendance system, which usually uses fingerprints as an object, has become less effective given the Covid-19 pandemic in Indonesia. Attendance tools that have been contaminated by fingers will become a container for the spread of Covid-19. The design of this attendance system aims to break the chain of spread of COVID-19 by conducting attendance without being directly contaminated with attendance devices. In this study, facial detection and recognition analysis was carried out with the Local Binary Pattern Histogram (LBPH) algorithm feature approach for web-based attendance, where software development used the prototype method. LBPH is an algorithm combination between Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). LBP is a well-known method of recognizing an object by distinguishing the object from the background. Face images taken in real time using a webcam will be compared and matched using histograms that have been extracted with facial images that already exist in the database. The results of the facial recognition process in this system are very dependent on lighting, facial angles and the use of accessories on the face. The face attendance system is able to detect faces well up to 100% accuracy and recognize faces that have been detected up to 60% accuracy.
Co-Authors Asep Kurniawan