An Exploratory Study of Masked Face Recognition with Machine Learning Algorithms

被引:1
|
作者
Pudyel, Megh [1 ]
Atay, Mustafa [1 ]
机构
[1] Winston Salem State Univ, Dept Comp Sci, Winston Salem, NC 27110 USA
来源
SOUTHEASTCON 2023 | 2023年
关键词
masked face recognition; machine learning; ocular biometrics; synthesized mask; Covid-19; pandemic;
D O I
10.1109/SoutheastCon51012.2023.10115205
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automated face recognition is a widely adopted machine learning technology for contactless identification of people in various processes such as automated border control, secure login to electronic devices, community surveillance, tracking school attendance, workplace clock in and clock out. Using face masks have become crucial in our daily life with the recent world-wide COVID-19 pandemic. The use of face masks causes the performance of conventional face recognition technologies to degrade considerably. The effect of mask-wearing in face recognition is yet an understudied issue. In this paper, we address this issue by evaluating the performance of a number of face recognition models which are tested by identifying masked and unmasked face images. We use six conventional machine learning algorithms, which are SVC, KNN, LDA, DT, LR and NB, to find out the ones which perform best, besides the ones which poorly perform, in the presence of masked face images. Local Binary Pattern (LBP) is utilized as the feature extraction operator. We generated and used synthesized masked face images. We prepared unmasked, masked, and half-masked training datasets and evaluated the face recognition performance against both masked and unmasked images to present a broad view of this crucial problem. We believe that our study is unique in elaborating the mask-aware facial recognition with almost all possible scenarios including half_masked-to-masked and half_masked-to-unmasked besides evaluating a larger number of conventional machine learning algorithms compared the other studies in the literature.
引用
收藏
页码:877 / 882
页数:6
相关论文
共 50 条
  • [1] Masked Face Detection and Recognition System Based on Deep Learning Algorithms
    Al-Dmour, Hayat
    Tareef, Afaf
    Alkalbani, Asma Musabah
    Hammouri, Awni
    Alrahmani, Ban
    JOURNAL OF ADVANCES IN INFORMATION TECHNOLOGY, 2023, 14 (02) : 224 - 232
  • [2] Learning 3D Face Representation with Vision Transformer for Masked Face Recognition
    Wang, Yuan
    Yang, Zhen
    Zhang, Zhiqiang
    Zang, Huaijuan
    Zhu, Qiang
    Zhan, Shu
    2022 ASIA CONFERENCE ON ALGORITHMS, COMPUTING AND MACHINE LEARNING (CACML 2022), 2022, : 505 - 511
  • [3] Masked Face Recognition Using Deep Learning: A Review
    Alzu'bi, Ahmad
    Albalas, Firas
    AL-Hadhrami, Tawfik
    Younis, Lojin Bani
    Bashayreh, Amjad
    ELECTRONICS, 2021, 10 (21)
  • [4] Multi-face Recognition Systems Based on Deep and Machine Learning Algorithms
    Alane, Badreddine
    Saad, Bouguezel
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON APPLIED CYBER SECURITY (ACS) 2021, 2022, 378 : 90 - 102
  • [5] Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation
    Martinez-Diaz, Yoanna
    Mendez-Vazquez, Heydi
    Luevano, Luis S.
    Nicolas-Diaz, Miguel
    Chang, Leonardo
    Gonzalez-Mendoza, Miguel
    IEEE ACCESS, 2022, 10 : 7341 - 7353
  • [6] Masked-face recognition using deep metric learning and FaceMaskNet-21
    Rucha Golwalkar
    Ninad Mehendale
    Applied Intelligence, 2022, 52 : 13268 - 13279
  • [7] Masked-face recognition using deep metric learning and FaceMaskNet-21
    Golwalkar, Rucha
    Mehendale, Ninad
    APPLIED INTELLIGENCE, 2022, 52 (11) : 13268 - 13279
  • [8] The Effect of Wearing a Mask on Face Recognition Performance: an Exploratory Study
    Damer, Naser
    Grebe, Jonas Henry
    Chen, Cong
    Boutros, Fadi
    Kirchbuchner, Florian
    Kuijper, Arjan
    2020 INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG), 2020, P-306
  • [9] Explainable masked face recognition
    Anjali, T.
    Masilamani, V
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (10) : 31123 - 31138
  • [10] Explainable masked face recognition
    Anjali T
    Masilamani V
    Multimedia Tools and Applications, 2024, 83 : 31123 - 31138