2D face pose normalisation using a 3D morphable model

被引：3
|
作者：
Tena, J. R. [1 ]
Smith, R. S. [1 ]
Hamouz, A. [1 ]
Kittler, J. [1 ]
Hilton, A. [1 ]
Illingworth, J. [1 ]
机构：
[1] Univ Surrey, Ctr Vision Speech & Siganl Proc, Guildford GU2 7NH, Surrey, England
来源：
2007 IEEE CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE | 2007年
关键词：
D O I：
10.1109/AVSS.2007.4425285
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
The ever growing need for improved security, surveillance and identity protection, calls for the creation of evermore reliable and robust face recognition technology that is scalable and can be deployed in all kinds of environments without compromising its effectiveness. In this paper we study the impact that pose correction has on the performance of 2D face recognition. To measure the effect, we use a state of the art 2D recognition algorithm. The pose correction is performed by means of 3D morphable model. Our results on the non frontal XM2VTS database showed that pose correction can improve recognition rates up to 30%.
引用
收藏
页码：51 / 56
页数：6
相关论文
共 50 条
  • [1] Face pose estimation and synthesis by 2D morphable model
    Yingchun, Li
    Guangda, Su
    COMPUTATIONAL INTELLIGENCE AND SECURITY, 2007, 4456 : 1001 - 1008
  • [2] Pose variant face recognition based on 3D morphable model
    Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, Beijing 100022, China
    Beijing Gongye Daxue Xuebao J. Beijing Univ. Technol., 2007, 3 (320-325):
  • [3] Face pose estimate and multi-pose synthesize by 2D morphable model
    Li, Yingchun
    Su, Guangda
    2006 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY, PTS 1 AND 2, PROCEEDINGS, 2006, : 1857 - 1860
  • [4] Sphere Face Model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training
    Jiang, Diqiong
    Jin, Yiwei
    Zhang, Fang-Lue
    Zhu, Zhe
    Zhang, Yun
    Tong, Ruofeng
    Tang, Min
    COMPUTATIONAL VISUAL MEDIA, 2023, 9 (02) : 279 - 296
  • [5] Sphere Face Model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training
    Diqiong Jiang
    Yiwei Jin
    Fang-Lue Zhang
    Zhe Zhu
    Yun Zhang
    Ruofeng Tong
    Min Tang
    Computational Visual Media, 2023, 9 : 279 - 296
  • [6] Pose Invariant Face Recognition with 3D Morphable Model and Neural Network
    Choi, Hyun-Chul
    Kim, Sam-Yong
    Oh, Sang-Hoon
    Oh, Se-Young
    Cho, Sun-Young
    2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 4131 - +
  • [7] 3D Morphable Face Model for Face Animation
    Ye, Dan
    Fuh, Chiou-Shann
    INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2020, 20 (01)
  • [8] Face Recognition Using a Unified 3D Morphable Model
    Hu, Guosheng
    Yan, Fei
    Chan, Chi-Ho
    Deng, Weihong
    Christmas, William
    Kittler, Josef
    Robertson, Neil M.
    COMPUTER VISION - ECCV 2016, PT VIII, 2016, 9912 : 73 - 89
  • [9] Nonlinear 3D Face Morphable Model
    Luan Tran
    Liu, Xiaoming
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 7346 - 7355
  • [10] Robust Head Pose Estimation Using a 3D Morphable Model
    Cai, Ying
    Yang, Menglong
    Li, Ziqiang
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2015, 2015
12345