Jurnal Tekinkom (Teknik Informasi dan Komputer)
Vol 5 No 1 (2022)

IDENTIFIKASI PENGENALAN WAJAH UNTUK SISTEM PRESENSI MENGGUNAKAN METODE KNN (K-NEAREST NEIGHBOR)

Dwi Rizki Yulianti (Telkom University)
Iwan Iwut Triastomoro (Universitas Telkom)
Sofia Sa’idah (Universitas Telkom)



Article Info

Publish Date
30 Jun 2022

Abstract

Attendance is an activity that is so important and cannot be separated from a teaching and learning activity to calculate and see student attendance. In this Final Project, research on the automatic attendance system is carried out through facial recognition identification (face recognition) using a webcam as a system input, then the resulting image capture results from each image will be processed through feature extraction using the LBPH (Local Binary Pattern Histogram) method and classification with the KNN (K-Nearest Neighbor) method and the help of OpenCV library-based Python software. The research in this Final Project obtained an average accuracy value in facial recognition using LBPH (Local Binary Pattern Histogram) of 93.9%, with an average FAR value of 4.66% and an average FRR value of 1.33%. For the classification of KNN (K-Nearest Neighbor) using Euclidean Distance when k = 1 obtained an accuracy of 100% with a computation time of 34 ms, at the time of k = 3 an accuracy of 98% with a computation time of 37 ms was obtained and at the time of k = 5 an accuracy of 88% with a computation time of 42 ms.

Copyrights © 2022






Journal Info

Abbrev

Tekinkom

Publisher

Subject

Computer Science & IT

Description

Jurnal TEKINKOM merupakan jurnal yang dimaksudkan sebagai media terbitan kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai isu Ilmu - ilmu komputer dan sistem informasi, seperti : Pemrograman Jaringan, Jaringan Komputer, Teknik Komputer, Ilmu Komputer/Informatika, Sistem ...