Perception of Image Features in Post-Mortem Iris Recognition: Humans vs Machines

被引:1
|
作者
Trokielewicz, Mateusz [1 ]
Czajka, Adam [2 ]
Maciejewicz, Piotr [3 ]
机构
[1] Res & Acad Comp Network, Biometr & Machine Intelligence Lab, Kolska 12, PL-01045 Warsaw, Poland
[2] Univ Notre Dame, Dept Comp Sci & Engn, Notre Dame, IN 46556 USA
[3] Med Univ Warsa, Dept Ophthalmol, Lindleya 4, PL-02005 Warsaw, Poland
关键词
D O I
10.1109/btas46853.2019.9185980
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Post-mortem iris recognition can offer an additional forensic method of personal identification. However, in contrary to already well-established human examination of fingerprints, making iris recognition human-interpretable is harder, and therefore it has never been applied in forensic proceedings. There is no strong consensus among biometric experts which iris features, especially those in iris images acquired post-mortem, are the most important for human experts solving an iris recognition task. This paper explores two ways of broadening this knowledge: (a) with an eye tracker, the salient features used by humans comparing iris images on a screen are extracted, and (b) class-activation maps produced by the convolutional neural network solving the iris recognition task are analyzed. Both humans and deep learning-based solutions were examined with the same set of iris image pairs. This made it possible to compare the attention maps and conclude that (a) deep learning-based method can offer human-interpretable decisions backed by visual explanations pointing a human examiner to salient regions, and (b) in many cases humans and a machine used different features, what means that a deep learning-based method can offer a complementary support to human experts. This paper offers the first known to us human-interpretable comparison of machine-based and human-based post-mortem iris recognition, and the trained models annotating salient iris image regions.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Post-mortem Human Iris Recognition
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. 2016 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB), 2016,
  • [2] Post-mortem iris recognition with deep-learning-based image segmentation
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. IMAGE AND VISION COMPUTING, 2020, 94
  • [3] Human Iris Recognition in Post-mortem Subjects: Study and Database
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. 2016 IEEE 8TH INTERNATIONAL CONFERENCE ON BIOMETRICS THEORY, APPLICATIONS AND SYSTEMS (BTAS), 2016,
  • [4] Post-Mortem Iris Recognition Resistant to Biological Eye Decay Processes
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. 2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 2296 - 2304
  • [5] Post-Mortem Iris Recognition-A Survey and Assessment of the State of the Art
    Boyd, Aidan
    Yadav, Shivangi
    Swearingen, Thomas
    Kuehlkamp, Andrey
    Trokielewicz, Mateusz
    Benjamin, Eric
    Maciejewicz, Piotr
    Chute, Dennis
    Ross, Arun
    Flynn, Patrick
    Bowyer, Kevin
    Czajka, Adam
    [J]. IEEE ACCESS, 2020, 8 : 136570 - 136593
  • [6] Grading iris color of post-mortem human eyes
    Madigan, M.
    Cionaca, V.
    Sitiwin, E.
    Ton, H. T.
    [J]. ACTA OPHTHALMOLOGICA, 2016, 94
  • [7] Iris Recognition under Biologically Troublesome Conditions - Effects of Aging, Diseases and Post-mortem Changes
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. PROCEEDINGS OF THE 10TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 4: BIOSIGNALS, 2017, : 253 - 258
  • [8] Post-mortem Iris Decomposition and its Dynamics in Morgue Conditions
    Trokielewicz, Mateusz
    Czajka, Adam
    Maciejewicz, Piotr
    [J]. JOURNAL OF FORENSIC SCIENCES, 2020, 65 (05) : 1530 - 1538
  • [9] Post-mortem Iris Biometric Analysis in Sus scrofa domesticus
    Saripalle, Sashi K.
    McLaughlin, Adam
    Krishna, Rohit
    Ross, Arun
    Derakhshani, Reza
    [J]. 2015 IEEE 7TH INTERNATIONAL CONFERENCE ON BIOMETRICS THEORY, APPLICATIONS AND SYSTEMS (BTAS 2015), 2015,
  • [10] Data-Driven Segmentation of Post-mortem Iris Images
    Trokielewicz, Mateusz
    Czajka, Adam
    [J]. 2018 6TH INTERNATIONAL WORKSHOP ON BIOMETRICS AND FORENSICS (IWBF), 2018,