Face Identification Based on K-Nearest Neighbor

Face identification has been widely applied this time, such as security on gadgets, smart home security, and others. Face dominates as a biometric which is most increase in the next few years. Face is used for biometric identification which is considered successful among several other types of biome...

Full description

Saved in:
Bibliographic Details
Main Authors: Ni Kadek Ayu Wirdiani, Praba Hridayami, Ni Putu Ayu Widiari, Komang Diva Rismawan, Putu Bagus Candradinata, I Putu Deva Jayantha
Format: Article
Language:English
Published: Universitas Negeri Semarang 2019-11-01
Series:Scientific Journal of Informatics
Subjects:
Online Access:https://journal.unnes.ac.id/nju/index.php/sji/article/view/19503
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167732354416640
author Ni Kadek Ayu Wirdiani
Praba Hridayami
Ni Putu Ayu Widiari
Komang Diva Rismawan
Putu Bagus Candradinata
I Putu Deva Jayantha
author_facet Ni Kadek Ayu Wirdiani
Praba Hridayami
Ni Putu Ayu Widiari
Komang Diva Rismawan
Putu Bagus Candradinata
I Putu Deva Jayantha
author_sort Ni Kadek Ayu Wirdiani
collection DOAJ
description Face identification has been widely applied this time, such as security on gadgets, smart home security, and others. Face dominates as a biometric which is most increase in the next few years. Face is used for biometric identification which is considered successful among several other types of biometrics and accurate results. Face recognition utilizes facial features for security purposes. The classification method in this paper is K-nearest Neighbor (KNN). The K-Nearest Neighbor algorithm uses neighborhood classification as the predictive value of a good instance value. K-NN includes an instance-based learning group. This paper developed face identification using Principal Component Analysis (PCA) or eigenface extraction methods. The stages of face identification research using the KNN method are pre-processing in the input image. Preprocessing used in this research are contrass stretching, grayscale, and segmentation used haar cascade. This research is registered 30 people, each person had 3 images used for training and 2 images used for testing. The results obtained from several trials of k values are as follows. Experiments with a value of k=1 get the best accuracy, namely 81%, k=2 get 53% accuracy, and k=3 get 45% accuracy.
format Article
id doaj-art-df732f290fd04cd193b92cb4b10587ac
institution OA Journals
issn 2407-7658
language English
publishDate 2019-11-01
publisher Universitas Negeri Semarang
record_format Article
series Scientific Journal of Informatics
spelling doaj-art-df732f290fd04cd193b92cb4b10587ac2025-08-20T02:21:09ZengUniversitas Negeri SemarangScientific Journal of Informatics2407-76582019-11-016215015910.15294/sji.v6i2.195039268Face Identification Based on K-Nearest NeighborNi Kadek Ayu Wirdiani0Praba Hridayami1Ni Putu Ayu Widiari2Komang Diva Rismawan3Putu Bagus CandradinataI Putu Deva JayanthaUdayana UniversityUdayana UniversityUdayana UniversityUdayana UniversityFace identification has been widely applied this time, such as security on gadgets, smart home security, and others. Face dominates as a biometric which is most increase in the next few years. Face is used for biometric identification which is considered successful among several other types of biometrics and accurate results. Face recognition utilizes facial features for security purposes. The classification method in this paper is K-nearest Neighbor (KNN). The K-Nearest Neighbor algorithm uses neighborhood classification as the predictive value of a good instance value. K-NN includes an instance-based learning group. This paper developed face identification using Principal Component Analysis (PCA) or eigenface extraction methods. The stages of face identification research using the KNN method are pre-processing in the input image. Preprocessing used in this research are contrass stretching, grayscale, and segmentation used haar cascade. This research is registered 30 people, each person had 3 images used for training and 2 images used for testing. The results obtained from several trials of k values are as follows. Experiments with a value of k=1 get the best accuracy, namely 81%, k=2 get 53% accuracy, and k=3 get 45% accuracy.https://journal.unnes.ac.id/nju/index.php/sji/article/view/19503convolutional neural network, k-nearest neighbor, principal component analysis, haar cascade
spellingShingle Ni Kadek Ayu Wirdiani
Praba Hridayami
Ni Putu Ayu Widiari
Komang Diva Rismawan
Putu Bagus Candradinata
I Putu Deva Jayantha
Face Identification Based on K-Nearest Neighbor
Scientific Journal of Informatics
convolutional neural network, k-nearest neighbor, principal component analysis, haar cascade
title Face Identification Based on K-Nearest Neighbor
title_full Face Identification Based on K-Nearest Neighbor
title_fullStr Face Identification Based on K-Nearest Neighbor
title_full_unstemmed Face Identification Based on K-Nearest Neighbor
title_short Face Identification Based on K-Nearest Neighbor
title_sort face identification based on k nearest neighbor
topic convolutional neural network, k-nearest neighbor, principal component analysis, haar cascade
url https://journal.unnes.ac.id/nju/index.php/sji/article/view/19503
work_keys_str_mv AT nikadekayuwirdiani faceidentificationbasedonknearestneighbor
AT prabahridayami faceidentificationbasedonknearestneighbor
AT niputuayuwidiari faceidentificationbasedonknearestneighbor
AT komangdivarismawan faceidentificationbasedonknearestneighbor
AT putubaguscandradinata faceidentificationbasedonknearestneighbor
AT iputudevajayantha faceidentificationbasedonknearestneighbor