AbstrakWajah merupakan salah satu identitas bagi setiap individu pada sistem biometrik. Wajah merupakan ciri unik dari setiap manusia yang dapat membedakan rupa antar manusia. Berbeda dengan manusia yang dapat mengenali wajah dengan mudah dan cepat, komputer tidak secepat dan semudah manusia. Pada komputer diperlukan suatu algoritme dalam pengenalan wajah. Pada Penelitian ini, dirancang suatu sistem pengenalan wajah menggunakan kamera web dan OpenCV yang terpasang pada Raspberry Pi 3 Model B. Masukan sistem berupa video real-time yang diperoleh dari kamera web. Metode yang digunakan pada pendeteksian wajah adalah metode Viola-Jones dan dalam pengenalan wajah digunakan metode eigenface dan jarak euclidean. Terdapat 5 responden yang diambil citra wajahnya sebagai database. Hasil yang diperoleh dari sistem ini adalah nama dari setiap responden yang terdapat pada database. Berdasarkan hasil pengujian pada kondisi dalam ruangan dihasilkan rata-rata akurasi sebesar 99,8%, sedangkan pada kondisi luar ruangan dihasilkan rata-rata akurasi sebesar 93,8%. Pada pengujian citra wajah yang diberi derau salt & pepper dengan kepadatan derau 0,001 dan 0,01 didapatkan bahwa program mampu mengenali wajah dengan benar. Program mampu mengenali wajah dengan benar pada citra yang dirotasi sebesar 10 derajat.Kata kunci: Pengenalan wajah, algoritme eigenface, jarak euclidean, metode Viola Jones, OpenCV, Raspberry Pi. AbstractFacial recognition is one of the biometric systems. Face is the hallmark of every human being who can distinguish between human beings. Face recognition is widely used for identification systems on security systems and attendance machines. In this Research, designed a face recognition system using web camera and OpenCV mounted on Raspberry Pi 3 Model B. Input system of video obtained from camera. The method used on face detection is Viola-Jones method and in face recognition used eigenface and euclidean distance. Face image capture of 55 images from 5 people using web camera. The image is stored in a folder as a database. The result obtained from this system is the name of each respondent in the database. In the test also performed a system endurance test against salt & pepper and image rotation attacks. Based on the test result on indoor condition, the average value of accuracy is 99,8% and in outdoor condition, the average value of accuracy is 93,8%. Based on the image test of salt & pepper attack it was found that the program was able to correctly recognize the face at 0.001 and 0.01 noise density. Image testing against rotational attacks found that the program is only able to detect faces on rotated images of 10, 15, and 20 degrees. The program is not resistant to rotational attacks so it goes wrong recognizing the face.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.