Deep face recognition: A survey

被引:377
|
作者
Wang, Mei [1 ]
Deng, Weihong [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China
基金
国家重点研发计划;
关键词
Deep face recognition; Deep learning; Face processing; Face recognition database; Loss function; Deep network architecture; CONVOLUTIONAL NEURAL-NETWORK; 3D; REPRESENTATION; DATABASE; VERIFICATION; EIGENFACES; ALIGNMENT; FUSION; MODEL; 2D;
D O I
10.1016/j.neucom.2020.10.081
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction. This emerging technique has reshaped the research landscape of face recognition (FR) since 2014, launched by the breakthroughs of DeepFace and DeepID. Since then, deep learning technique, characterized by the hierarchical architecture to stitch together pixels into invariant face representation, has dramatically improved the state-of-the-art performance and fostered successful real-world applications. In this survey, we provide a comprehensive review of the recent developments on deep FR, covering broad topics on algorithm designs, databases, protocols, and application scenes. First, we summarize different network architectures and loss functions proposed in the rapid evolution of the deep FR methods. Second, the related face processing methods are categorized into two classes: "one-to-many augmentation" and "many-to-one normalization". Then, we summarize and compare the commonly used databases for both model training and evaluation. Third, we review miscellaneous scenes in deep FR, such as cross-factor, heterogenous, multiple-media and industrial scenes. Finally, the technical challenges and several promising directions are highlighted. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页码:215 / 244
页数:30
相关论文
共 50 条
  • [11] A survey: Face recognition techniques
    Sharif, Muhammad
    Mohsin, Sajjad
    Javed, Muhammad Younas
    Research Journal of Applied Sciences, Engineering and Technology, 2012, 4 (23) : 4979 - 4990
  • [12] Face recognition: A literature survey
    Zhao, W
    Chellappa, R
    Phillips, PJ
    Rosenfeld, A
    ACM COMPUTING SURVEYS, 2003, 35 (04) : 399 - 459
  • [13] The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances
    Du, Hang
    Shi, Hailin
    Zeng, Dan
    Zhang, Xiao-Ping
    Mei, Tao
    ACM COMPUTING SURVEYS, 2022, 54 (10S)
  • [14] Face Recognition Systems: A Survey
    Kortli, Yassin
    Jridi, Maher
    Al Falou, Ayman
    Atri, Mohamed
    SENSORS, 2020, 20 (02)
  • [15] A Survey of Face Recognition Techniques
    Jafri, Rabia
    Arabnia, Hamid R.
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2009, 5 (02): : 41 - 68
  • [16] A survey on disguise face recognition
    Darshan, L. M.
    Nagasundara, K. B.
    JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS, 2024, 47 (05) : 528 - 543
  • [17] Partial Face Recognition: A Survey
    Shafin, Mohammad
    Hansda, Rojina
    Pallavi, Ekta
    Kumar, Deo
    Bhattacharyya, Sumanta
    Kumar, Sanjeev
    PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON ADVANCED INFORMATICS FOR COMPUTING RESEARCH (ICAICR '19), 2019,
  • [18] A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face
    Lian, Hailun
    Lu, Cheng
    Li, Sunan
    Zhao, Yan
    Tang, Chuangao
    Zong, Yuan
    ENTROPY, 2023, 25 (10)
  • [19] The contribution of different face parts to deep face recognition
    Lestriandoko, Nova Hadi
    Veldhuis, Raymond
    Spreeuwers, Luuk
    FRONTIERS IN COMPUTER SCIENCE, 2022, 4
  • [20] Face Attributes as Cues for Deep Face Recognition Understanding
    Diniz, Matheus Alves
    Schwartz, William Robson
    2020 15TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2020), 2020, : 307 - 313