PENGENALAN CITRA SIDIK JARI MENGGUNAKAN METODE JARINGAN SARAF TIRUAN BACKPROPAGATION BERBASIS ANDROID

Irsyaad, Muh. (2020) PENGENALAN CITRA SIDIK JARI MENGGUNAKAN METODE JARINGAN SARAF TIRUAN BACKPROPAGATION BERBASIS ANDROID. Tugas Akhir thesis, University of Technology Yogyakarta.

[img]
Preview
Text
naskah publikasi-Muh. Jamaaluddin Irsyaad-5150411368.pdf

Download (1MB) | Preview

Abstract

Human fingerprint identification is a process to recognize and determine someone's fingerprint. Fingerprint identification technology is included in biometrics that uses the characteristics of natural human behavior. In fingerprint identification it is not possible to use conventional methods because of its complex form and difficult to distinguish from the naked eye. Therefore it is necessary to conduct research to create a computerized recognition system. In this study, backpropagation is used to identify the fingerprint image. The application development steps include: grayscalling, tresholding,morphology opening, median filtering, resizing and training and testing. The training process that is carried out is to determine the initial weight of the system, determine the output target as a benchmark for training to adjust output, and making corrections to weights until the calculated errors are smaller than fault tolerance. Weight improvement is done by feedbacking the output signal to the hidden layer and the input layer. The final weight obtained is stored in the database, which will then be used in the testing process. In addition, testing is carried out to determine the level of success of the introduction of data entered after passing the training stage. The software used in building this application is Java & XML as a programming language, SQLite as a database, Android Studio as a support. Fingerprint Image Recognition Using Backward Error Artificial Neural Network Method is an application that serves to facilitate the identification of a person's fingerprints through a computerized system with the results of training data accuracy of 90,42% and testing data accuracy of 71,67%. Keywords: Image Identification, Backpropagation, Fingerprint

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 27 Mar 2020 04:34
Last Modified: 27 Mar 2020 04:34
URI: http://eprints.uty.ac.id/id/eprint/4912

Actions (login required)

View Item View Item