De-identifying facial images using singular value decomposition and projections

被引:2
|
作者
Chriskos, P. [1 ]
Zoidi, O. [1 ]
Tefas, A. [1 ]
Pitas, I. [1 ,2 ]
机构
[1] Aristotle Univ Thessloniki, Dept Informat, Thessaloniki 54124, Greece
[2] Univ Bristol, Dept Elect & Elect Engn, Bristol, Avon, England
关键词
Face de-idenification; Privacy protection; Singular value decomposition; Projections on hyperspheres;
D O I
10.1007/s11042-016-4069-8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, two methods are presented that manipulate images to hinder automatic face identification. They partly degrade image quality, so that humans can identify the persons in a scene, while face identification algorithms fail to do so. The approaches used involve: a) singular value decomposition (SVD) and b) image projections on hyperspheres. Simulation experiments verify that these methods reduce the percentage of correct face identification rate by over 90 %. Additionally, the final image is not degraded beyond recognition by humans, in contrast with the majority of other de-identification methods.
引用
收藏
页码:3435 / 3468
页数:34
相关论文
共 50 条
  • [1] De-identifying facial images using singular value decomposition and projections
    P. Chriskos
    O. Zoidi
    A. Tefas
    I. Pitas
    Multimedia Tools and Applications, 2017, 76 : 3435 - 3468
  • [2] De-Identifying Facial Images Using Singular Value Decomposition
    Chriskos, P.
    Zoidi, O.
    Tefas, A.
    Pitas, I.
    2014 37TH INTERNATIONAL CONVENTION ON INFORMATION AND COMMUNICATION TECHNOLOGY, ELECTRONICS AND MICROELECTRONICS (MIPRO), 2014, : 1240 - 1245
  • [3] De-Identifying Facial Images Using Projections on Hyperspheres
    Chriskos, P.
    Zoidi, O.
    Tefas, A.
    Pitas, I
    2015 11TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOPS ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG): DE-IDENTIFICATION FOR PRIVACY PROTECTION IN MULTIMEDIA (DEID 2015), VOL 4, 2015,
  • [4] Preserving privacy by de-identifying face images
    Newton, EM
    Sweeney, L
    Malin, B
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2005, 17 (02) : 232 - 243
  • [5] De-identifying Face Image Datasets While Retaining Facial Expressions
    Leibl, Andreas
    Meissner, Andreas
    Altmann, Stefan
    Attenberger, Andreas
    Mayer, Helmut
    2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [6] Facial recognition with singular value decomposition
    Zeng, Guoliang
    ADVANCES AND INNOVATIONS IN SYSTEMS, COMPUTING SCIENCES AND SOFTWARE ENGINEERING, 2007, : 145 - 148
  • [7] De-Identifying People in Videos using Neural Art
    Brkic, Karla
    Sikiric, Ivan
    Hrkac, Tomislav
    Kalafatic, Zoran
    2016 SIXTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), 2016,
  • [8] Watermarking of still images using multiresolution singular value decomposition
    Akhbari, B
    Ghaemmaghami, S
    ISPACS 2005: PROCEEDINGS OF THE 2005 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS, 2005, : 325 - 328
  • [9] POSITION MEASURING IN IMAGES USING CORRELATION AND SINGULAR VALUE DECOMPOSITION
    KNUPFER, K
    GROSSKOPF, R
    SUDLAND, K
    TECHNISCHES MESSEN, 1990, 57 (10): : 381 - 383
  • [10] SUBBAND CODING OF IMAGES USING SINGULAR VALUE DECOMPOSITION (SVD)
    YU, TH
    MITRA, SK
    VISUAL COMMUNICATIONS AND IMAGE PROCESSING IV, PTS 1-3, 1989, 1199 : 1247 - 1257