Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/20294
Title: | Implementasi Algoritma Backpropagation Untuk Pengenalan Wajah Berbasis Citra |
Other Titles: | Backpropagation Algorithm Implementation For Image-Based Face Recognition |
Authors: | Sari, Maya Dani |
metadata.dc.contributor.advisor: | Khairina, Nurul |
Keywords: | Attendance System;Data Security;Face recognition;Artificial Neural Network;Backpropagation Algorithm;Sistem Absensi;Keamanan Data;Pengenalan wajah;Jaringan Syaraf Tiruan |
Issue Date: | 29-Mar-2023 |
Publisher: | Universitas Medan Area |
Series/Report no.: | NPM;178160077 |
Abstract: | Umumnya sistem absensi karyawan pada kantor dilakukan dengan mengisi buku absen menggunakan mesin sidik jari dimana jika dilihat dari segi keamanan, sistem ini mempunyai kelemahan antara lain adalah sering mengalami human error seperti scan sidik jari sulit diterima. Hal ini dapat diakibatkan kondisi permukaan jari yang tidak normal, seperti basah, kotor, terlalu kering, ujung jari cacat dan akhirnya sistem menolak, maka dalam menyelesaikan masalah tersebut diatas memerlukan suatu metode cepat tepat dan akurat. Pada penelitian ini dilakukan pengenalan wajah berbasis citra dengan mengimplementasikan algoritma Backpropagation. Dataset citra wajah yang digunakan pada penelitian ini bersumber dari situs kaggle.com dengan jumlah wajah yang akan dilatih sebanyak 1866 citra wajah dengan berbagai ekspresi setiap wajah. Pada sistem ini ada dua tahap yang dilakukan yaitu pelatihan semua citra wajah sebagai dataset untuk memperoleh bobot setiap citra dan tahap selanjutnya dilakukan pengujian yaitu tahap pengenalan. Hasil percobaan bahwa aplikasi dapat melakukan pembacaan nilai piksel citra pelatihan dengan parameter jaringan maksimal error sebesar 0.001, learning rate sebesar 0.30 dan 0.50. Aplikasi dapat melakukan pengenalan dengan hasil terbaik pada nilai learning rate 0.50 dengan nilai akurasi pengenalan sebesar 82 %. In general, the employee attendance system at the office is done by filling out the attendance book using a fingerprint machine where from a security point of view, this system has weaknesses, among others, is that it often experiences human errors such as fingerprint scans that are difficult to accept. This can be caused by abnormal finger surface conditions, such as wet, dirty, too dry, defective finger tips and finally the system refuses, so solving the problems mentioned above requires a fast, precise and accurate method. In this study, image-based face recognition was carried out by implementing the Backpropagation algorithm. The facial image dataset used in this study was sourced from the site kaggle.com with the number of faces to be trained as many as 1866 face images with various expressions for each face. In this system there are two stages, namely training all face images as a dataset to obtain the weight of each image and the next stage is testing, namely the introduction stage. The experimental results show that the application can read the pixel value of the training image with a maximum error of 0.001 network parameters, learning rates of 0.30 and 0.50. The application can perForm the introduction with the best results at a learning rate of 0.50 with a recognition accuracy value of 82%. |
Description: | 75 Halaman |
URI: | https://repositori.uma.ac.id/handle/123456789/20294 |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
178160077 - Maya Dani Sari - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 1.19 MB | Adobe PDF | View/Open |
178160077 - Maya Dani Sari - Chapter IV.pdf Restricted Access | Chapter IV | 542.42 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.