Predicting Face Recognition Performance in Unconstrained Environments

被引:1
|
作者
Phillips, P. Jonathon [1 ]
Yates, Amy N. [1 ]
Beveridge, J. Ross [2 ]
Givens, Geof [3 ]
机构
[1] NIST, Gaithersburg, MD 20899 USA
[2] Colorado State Univ, Dept Comp Sci, Ft Collins, CO 80523 USA
[3] Givens Stat Solut LLC, Ft Collins, CO USA
关键词
D O I
10.1109/CVPRW.2017.83
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
While face recognition algorithms perform under many different unconstrained conditions, predicting this performance is not possible when a new location is introduced. Analyzing the impostor distribution of the videos of the Point-and-Shoot Challenge (PaSC) as well as its relationship to the genuine match distribution, we show that there is large variation in the false accept rate over the impostor distribution, demonstrate there is a correlation between changes in the verification and false accept rates over factor, and using this, present a method for predicting the performance of an algorithm using only unlabeled data for a new location.
引用
收藏
页码:557 / 565
页数:9
相关论文
共 50 条
  • [1] Face Recognition in Unconstrained Environments
    Kim, Dong-Ju
    Lee, Sang-Heon
    Sohn, Myoung-Kyu
    Kim, Byungmin
    Kim, Hyunduk
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2013, : 143 - 144
  • [2] Evaluation of Face Recognition Methods in Unconstrained Environments
    Agrawal, Amrit Kumar
    Singh, Yogendra Narain
    [J]. INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATION AND CONVERGENCE (ICCC 2015), 2015, 48 : 644 - 651
  • [3] Efficient Face Recognition System for Operating in Unconstrained Environments
    Sanchez-Moreno, Alejandra Sarahi
    Olivares-Mercado, Jesus
    Hernandez-Suarez, Aldo
    Toscano-Medina, Karina
    Sanchez-Perez, Gabriel
    Benitez-Garcia, Gibran
    [J]. JOURNAL OF IMAGING, 2021, 7 (09)
  • [4] Still-to-video face recognition in unconstrained environments
    Wang, Haoyu
    Liu, Changsong
    Ding, Xiaoqing
    [J]. IMAGE PROCESSING: MACHINE VISION APPLICATIONS VIII, 2015, 9405
  • [5] Fully automatic face normalization and single sample face recognition in unconstrained environments
    Haghighat, Mohammad
    Abdel-Mottaleb, Mohamed
    Alhalabi, Wadee
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2016, 47 : 23 - 34
  • [6] Automatic face region tracking for highly accurate face recognition in unconstrained environments
    Kim, YO
    Paik, J
    Heo, J
    Koschan, A
    Abidi, B
    Abidi, M
    [J]. IEEE CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, PROCEEDINGS, 2003, : 29 - 36
  • [7] A comparative study of thermal face recognition methods in unconstrained environments
    Hermosilla, Gabriel
    Ruiz-del-Solar, Javier
    Verschae, Rodrigo
    Correa, Mauricio
    [J]. PATTERN RECOGNITION, 2012, 45 (07) : 2445 - 2459
  • [8] A Combined GLQP and DBN-DRF for Face Recognition in Unconstrained Environments
    Hu, Hongping
    Yang, Yu
    [J]. PROCEEDINGS OF THE 2017 2ND INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ARTIFICIAL INTELLIGENCE (CAAI 2017), 2017, 134 : 553 - 557
  • [9] Multiple Media Based Face Recognition in Unconstrained Environments Using Eigenfaces
    Sreelakshmi, K. R.
    Anitha, R.
    Rehitha, K. R.
    [J]. 2016 INTERNATIONAL CONFERENCE ON NEXT GENERATION INTELLIGENT SYSTEMS (ICNGIS), 2016, : 277 - 282
  • [10] Face Recognition in Unconstrained Environments A Deep Architecture on A Small Training Set
    Saffar, Mohammad Taghi
    Rekabdar, Banafsheh
    Louis, Sushil
    Nicolescu, Mircea
    [J]. 2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,