Implementation of Principal Component Analysis on Masked and Non-masked Face Recognition

Implementation of Principal Component Analysis on Masked and Non-masked Face Recognition

Table of Contents


This paper represents an implementation of Principal Component Analysis (PCA) on masked and non-masked face recognition. Security is an essential term in our today’s life. In various Biometric technology, face recognition is widely used to secure any system because it is better than any other traditional technique like PIN, password, fingerprint, etc. and most reliable to identify or verify a person efficiently. In recent years, face recognition is a very challenging task because of different occlusion or masks like the existence of sunglasses, scarves, hats, and different types of make-up or disguise ingredients. The accuracy rate of face recognition is influenced by these types of masks. Many algorithms have been developed recently for non-masked face recognition which is widely used and gives better performance. Still, in the field of masked face recognition, few contributions have been done. Therefore, in this work, a statistical procedure has been selected which is applied in non-masked face recognition and also applies in the masked face recognition technique. PCA is a more effective and successful statistical technique and widely used. For this reason in this work, the PCA algorithm has been chosen. Finally, a comparative study also was done here for a better understanding.

  • Author Keywords

    • Face recognition,
    • PCA algorithm,
    • Eigenface,
    • Eigenvalue,
    • Masked face
  • IEEE Keywords

    • Face,
    • Face recognition,
    • Principal component analysis,
    • Image recognition,
    • Feature extraction,
    • Covariance matrices,
    • Training

Face recognition is one of the most promising fields of computer vision. Recognize a face and verifying a person automatically from images, known as face recognition systems [1]. Face recognition plays an important role in our regular life. In a passport checking, ATM, credit card, voter verification, smart door, criminal or terrorist investigation, and many other purposes face recognition is widely used to authenticate a person automatically and accurately. For those reasons, face recognition is the most popular than any other Biometric techniques.

In all automated personal identification systems, face recognition has gained much attention as a unique Biometric recognition technique. For protecting the assets of many industries in the world are now trying to implement this authentication technique in their organizations. Throughout the world, many of the governments also interested to secure public places such as railway stations, airports and bus stations, etc. by using a face recognition system. However for poor recognition rate, in real-time recognizing remain unsuccessful. The recognition rate depends on the quality of the image. Recognition rate decreases for noisy and low-quality images. That’s why pre-processing is needed for a better recognition rate. Some pre-processing techniques like cropping, resizing, sharpening, de-noising, normalizing, enhancing are used in the face recognition process [2]. Recently many algorithms have been developed for reliable face recognition. Different techniques depend on different methods and they have different recognition accuracy. All of these algorithms, Principal Component Analysis (PCA) give a better accuracy rate in normal or non-masked face recognition [3]-[5].

In present days masked face recognition is more important. Mainly terrorists and criminals covered their faces with a mask for disguise. Besides this, sunglasses, hats, a color festoon, etc. also act as a mask. Using different types of masks or occlusions key features to identify a person are decreasing. Lower numbers of facial features in the masked face cause difficulties than other normal face recognition techniques [6]. Consequently, the accuracy rate of recognition is decreasing. That’s why the masked face is being one of the major concerns factors in the field of face recognition. Figure 1 shows some of the masked faces.

For face recognition, at first, we need to detect the face from the image. After detecting the face, we can recognize the person.

It is easy for humans to detect a face but harder for a system to detect a face. For this reason at first, we need to train the system to detect face portions from images. Here we use the Viola-Jones algorithm to detect face from an image. Viola-Jones algorithm detects face using a machine learning approach from any digital image [7]. After detecting a face from an input image, then we use the PCA algorithm for feature extraction from the image, which is used for training. This work also presents a statistical difference of accuracy between masked face recognition and non-masked face recognition using the most successful algorithm Principal Component Analysis. All the results are shown in both graphically and tabulated form. The paper is organized as follows: Section 2 presents our face detection and face recognition methodology. Section 2 describes the face recognition process. Section 3 signifies the dataset. Section 4 shows experimental results and section 5 draws conclusions.


This paper analyzed non-masked face recognition and masked face recognition accuracy using Principal Component Analysis (PCA) to recognize a person. It is proved that a face without a mask gives a better recognition rate in PCA based face recognition system. But when a person is wearing a mask, facial recognition gives a poor recognition rate. It is found that extracting feature from a masked face is less than a non-masked face. Because of missing features for wearing masks which decrease the recognition rate. Finally, we conclude that traditional statistical algorithm Principal Component Analysis (PCA) is better for normal face recognition but not for masked face recognition. So in the future, our concern to improve the accuracy of masked face recognition using other sophisticated machine learning methods.

About KSRA

The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.

KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.

Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.

The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.

FULL Paper PDF file:

Implementation of Principal Component Analysis on Masked and Non-masked Face Recognition



M. S. Ejaz, M. R. Islam, M. Sifatullah and A. Sarker




Implementation of Principal Component Analysis on Masked and Non-masked Face Recognition

Publish in

2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh, 2019, pp.1-5,



PDF reference and original file: Click here







+ posts

Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.

Website | + posts

Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.

Website | + posts

Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.