Integration of PCA and Euclidean Distance Methods for Human Face Recognition Image Processing

Authors

DOI:

https://doi.org/10.25139/ijair.v7i1.10439

Keywords:

Image Processing, Face Recognition, Principal Component Analysis, Euclidean Distance

Abstract

The purpose of this study is to combine the PCA method and Euclidean Distance weighting to detect faces in images for face recognition, and to determine the level of accuracy in face recognition. This study begins with detecting the face part in the image. The original RGB image is converted into the YCbCr colour model, and then skin colour pixel segmentation is performed on the components according to the specified threshold. The results of the segmentation image are subjected to morphological opening (erosion) to remove noise. Furthermore, labelling and cropping of the image, identified as a face, are carried out. After the face part is detected, the next process involves feature extraction using PCA (principal component analysis), which reduces a 2-dimensional image type to 1 dimension, normalizes the image, calculates the matrix, determines the eigenvalues and eigenvectors, and calculates the image weight. Then, the Euclidean distance method is used for classification by finding the minimum distance between the weight of the test image and the weight of the training image. In this study, the PCA method used reduces the facial features, which originally had a matrix size of 34 × 20400, to a matrix size of 34 × 200. The matrix is a selected component because it has a significant influence on the database. The level of accuracy of facial recognition in this study was 95%, as it was able to identify faces even when the faces had expressions. The primary objective of this study is to detect the similarity between a person's face and that of the same person, as well as similar individuals.

Downloads

Download data is not yet available.

References

D. I. Mawarni, et al, "Digital Image Processing Method to Determine the Distribution of Air Bubble Diameter Size in Microbubble Generator," Journal of Information System Management (JOISM), vol. 4, no. 2, pp. 132-136, 2023.

D.A. Sardi," Effectiveness Of Using Biometric Technology In Identifying Criminals", Kohesi: Jurnal Multidisiplin Saintek, vol. 3, no. 2, pp. 1-16, 2024.

S. Subiyanto, et al, "Face Recognition System with PCA-GA Algorithm for Smart Home Door Security Using Rasberry Pi," Journal of Computer Technology and Systems., vol. 8, no. 3, pp. 210–216, 2020.

H. Zhi and S. Liu, "Face Recognition Based on Genetic Algorithm," J. Vis. Commun. Image Represent., vol. 58, pp. 495–502, 2019, doi: 10.1016/j.jvcir.2018.12.012

A. Nurhopipah and A. Harjoko, "Motion Detection and Face Recognition for CCTV Surveillance System," Indones. J. Comput. Cybern. Syst., vol. 12, no. 2, pp. 107–118, 2018.

E. P. Purwandari, A. Erlansari, A. Wijanarko, and E. A. Adrian, "Face Sketch Recognition Using Principal Component Analysis as a Forensic Application," Journal of Computer Technology and Systems, vol. 8, no. 3, pp. 178–184, 2020.

I. D. Wijaya, N. Usman, and M. A. Barata, “Implementasi Raspberry Pi untuk Rancang Bangun Sistem Keamanan Pintu Ruangan Server dengan Pengenalan Wajah Menggunakan Metode Triangle Face,” J. Inform. Polinema, vol. 4, no. 1, pp. 9–15, 2017.

S. Al-Aidid and D. S. Pamungkas, “Sistem Pengenalan Wajah dengan Algoritma Haar Cascade dan Local Binary Pattern Histogram,” J. Rekayasa Elektr., vol. 14, no. 1, pp. 62–67, 2018,

Sunardi, et al, "Face Recognition Using Machine Learning Algorithm Based on Raspberry Pi 4b", International Journal of Artificial Intelligence Research, vol. 6, no. 1, 2022.

S. Abidin, “Deteksi Wajah Menggunakan Metode Haar Cascade Classifier Berbasis Webcam pada Matlab,” J. Teknol. Elekterika, vol. 15, no. 1, pp. 21–27, 2018.

R. Purwati and G. Ariyanto, “Pengenalan Wajah Manusia Berbasis Algoritma Local Binary Pattern,” Emit. J. Tek. Elektro, vol. 17, no. 2, pp. 29–38, 2017.

Fahrizal, et al, “Implementasi Machine Learning pada Sistem PETS Identification Menggunakan Python Berbasis Ubuntu,” J. Inf. Syst. Informatics Comput., vol. 4, no. 1, pp. 86–91, 2020.

I. I. Setiawan, A. Jaenul, and D. Priyokusumo, “Prototipe Sistem Keamanan Rumah Menggunakan Face Recognition Berbasis Raspberry Pi 4,” SNITT- Politek. Negeri Balikpapan 2020, pp. 496–501, 2020

Downloads

Published

2025-07-18

How to Cite

Indriyono, B. V., Ramadhan, S. W. ., Hutagaol, N. ., & Pratama, Z. . (2025). Integration of PCA and Euclidean Distance Methods for Human Face Recognition Image Processing . International Journal of Artificial Intelligence & Robotics (IJAIR), 7(1), 35–44. https://doi.org/10.25139/ijair.v7i1.10439

Issue

Vol. 7 No. 1 (2025): May 2025

Section

Articles

License

Authors who publish with International Journal of Artificial Intelligence & Robotics (IJAIR) agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal. 

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.