Human Face Recognition Using Eigen Vector-Based Recognition System

Human Face Recognition Using Eigen Vector-Based Recognition System

Sadia Afrin1*, Maria Tasnim2, and Md. Rafiqul Islam3
1Department of Basic Science, Primeasia University, Dhaka, Bangladesh
2Mathematics Discipline, Khulna University, Khulna, Bangladesh
*Corresponding Author

DOI: https://doi.org/10.51244/IJRSI.2023.10612

Received: 19 June 2023; Revised: 27 June 2023; Accepted: 01 July 2023; Published: 13 July 2023

Abstract: Face recognition is an algorithm that can recognize or verify a query face among a large number of faces in the enrollment database. Face recognition is a crucial and difficult area of computer vision. This study demonstrates a system that can recognize a human face by comparing the facial structure to that of another individual or a well-known individual, which is accomplished by the use of frontal several summarizations. Many researchers have done their work on face recognition and also applied it by using different methods. We made use of an eigenvector-based recognition system as a method for recognizing faces. The face recognition system is highly accurate and is one of the most powerful surveillance tools ever made. But this face recognition technology is quite costly for developing countries like Bangladesh. In this study, we have used a face recognition system for our security purpose using an eigenvector-based face recognition system with the help of MATLAB software and a Raspberry Pi camera for security purposes which minimizes the cost, and this process we have used is quite affordable.

Keywords: Face recognition, Eigenvector, Eigenvalue, Covariance matrix.

I. Introduction

Face recognition applications are affected by a variety of factors such as illumination, facial distance, expression, age group, hair color, facial wear, and so on. In social situations, the face is the primary center of attention, and it plays an important role in expressing identity and emotion. Although face recognition is difficult, the human ability to recognize faces is remarkable that you can recognize faces. Even after years apart, faces can be recognized at a look. This ability is despite significant alterations in the visual stimuli due to distractions such as lighting, emotion, and age such as spectacles, beards, or hairstyle changes. Face recognition has fundamental importance for our simple everyday activities. It is a very high-level task and has many applications. A facial recognition system is a technology capable of matching a human face from a digital image or a video frame against a database of faces, typically employed to authenticate users through ID verification services and works by pinpointing and measuring facial features from a given facial recognition systems are employed throughout the world today by governments and private companies. The strategy taken by Dubravka Jevtic et al., (2012) aims to Face Recognition Using Eigenface Approach [1]. Their effectiveness varies, and some systems have previously been scrapped because of their ineffectiveness. K Ravi, M Kttswamy, (2014) aim at Face Recognition using PCA and Eigenface Approach [2]. Manoharan, Samuel, (2019) Study on Hermitian Graph Wavelets in Feature Detection [3]. The use of facial recognition systems has also raised controversy, with claims that the systems violate citizens’ privacy, commonly make incorrect identifications, encourage gender norms and racial profiling, and do not protect important biometric data securities. F Mahmud, M T Khatun, S T Juhori, M Akhter dan B Paul, (2015) aim to Face recognition using Principal Component Analysis and Linear Discriminant Analysis [4]. In this study, we are going to use a face recognition system using an eigenvector-based face recognition system with the help of MATLAB software and a Raspberry Pi camera for security purposes.

II. Methodology

Face Recognition
A straightforward approach to extracting the information contained in a face image is to capture the variation in a collection of face images, independent of any judgment of features, and then use this information to encode and compare individual face images. Treating a picture as a point (or vector) in a very high dimensional space, the major components of the distribution of faces, or the eigenvectors of the covariance matrix of the collection of face images.