KLASIFIKASI USIA BERDASARKAN CITRA WAJAH MENGGUNAKAN LOCAL BINARY PATTERN DAN K-NEAREST NEIGHBORS

Safrudin, Alfian (2020) KLASIFIKASI USIA BERDASARKAN CITRA WAJAH MENGGUNAKAN LOCAL BINARY PATTERN DAN K-NEAREST NEIGHBORS. Tugas Akhir thesis, University of Technology Yogyakarta.

[img]
Preview
Text
Naskah Publikasi-5160411032 Alfian Safrudin.pdf

Download (634kB) | Preview

Abstract

The face is one part of the human body that can be used as an object in research in the field of digital images. In facial images, humans can directly find out gender, ethnicity, age predictions and so on. Human age can be seen easily visually through the condition of a person's face. In general, humans can be divided into several vulnerable or groups where each group describes the stage of human growth. One of the age group divisions or age categories issued by the Ministry of Health of the Republic of Indonesia (2009) on its official website, depkes.go.id, is toddler (0 - 5 years), childhood (6 - 11 years), early adolescence ( 12 - 16 years), late adolescence (17-25 years), early adulthood (26 - 35 years), late adulthood (36 - 45 years), early old age (46 - 55 years), late old age ( 56 - 65 years), old age (65 - over). In the health sector, age grouping is very important, for example it is used to classify age groups that have a lot of stroke and various other diseases. In other words, the existence of age grouping / age classification, epidemiology and health demographics will be seen more clearly. This study aims to develop an artificial intelligence-based system that can identify a person's age through facial images using the Local Binary Pattern (LBP) and the K-Nearest Neighbors classification technique. In this study, researchers used the UTKFace face dataset that had been filtered again and produced 12,406 images as training data and 3,100 as data for testing. The results of this study obtained the best accuracy from the value of k = 13 and the Manhattan distance calculation method with an accuracy rate of 49.35% using a Local Binary Pattern with a radius of 16 and points 2 with a value of k = 13. Keywords: Image Processing, Age, Face, LBP, k-NN

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: 20 Dec 2020 01:50
Last Modified: 20 Dec 2020 01:50
URI: http://eprints.uty.ac.id/id/eprint/6335

Actions (login required)

View Item View Item