Iris Center Localization Using Geodesic Distance and CNN

被引:2
|
作者
Fusek, Radovan [1 ]
Sojka, Eduard [1 ]
机构
[1] Tech Univ Ostrava, FEECS, Dept Comp Sci, 17 Listopadu 2172-15, Ostrava 70800, Czech Republic
来源
PATTERN RECOGNITION AND IMAGE ANALYSIS, IBPRIA 2019, PT II | 2019年 / 11868卷
关键词
CNN; Iris detection; Geodesic distance; Deep learning;
D O I
10.1007/978-3-030-31321-0_7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a new eye iris center localization method for remote tracking scenarios. The method combines the geodesic distance with CNN-based classification. Firstly, the geodesic distance is used for fast preliminary localization of the regions possibly containing the iris. Then a convolutional neural network is used to carry out the final decision and to refine the final position of the iris center. In the first step, the areas that do not appear to contain the eyeball are quickly filtered out, which makes the whole algorithm fast even on less powerful computers. The proposed method is evaluated and compared with the state-of-the-art methods on two publicly available datasets focused to the remote tracking scenarios (namely BioID [9] , GI4E [15]).
引用
收藏
页码:76 / 85
页数:10
相关论文
共 50 条
  • [31] Image recoloring using geodesic distance based color harmonization
    Li X.
    Zhao H.
    Nie G.
    Huang H.
    Computational Visual Media, 2015, 1 (02) : 143 - 155
  • [32] Iris Code Matching using Adaptive Hamming Distance
    Dehkordi, Arezou Banitalebi
    Abu-Bakar, Syed A. R.
    2015 IEEE INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING APPLICATIONS (ICSIPA), 2015, : 404 - 408
  • [33] Table Localization and Segmentation using GAN and CNN
    Reza, Mohammad Mohsin
    Bukhari, Syed Saqib
    Jenckel, Martin
    Dengel, Andreas
    2019 INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION WORKSHOPS (ICDARW), VOL 5, 2019, : 152 - 157
  • [34] Approximating geodesic tree distance
    Amenta, Nina
    Godwin, Matthew
    Postarnakevich, Nicolay
    St. John, Katherine
    INFORMATION PROCESSING LETTERS, 2007, 103 (02) : 61 - 65
  • [35] End-to-end Off-angle Iris Recognition Using CNN Based Iris Segmentation
    Jalilian, Ehsaneddin
    Karakaya, Mahmut
    Uhl, Andreas
    2020 INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG), 2020, P-306
  • [36] Accurate iris center localization method using facial landmark, snakuscule, circle fitting and binary connected component
    Xiao, Feng
    Huang, Kejie
    Qiu, Yue
    Shen, Haibin
    MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (19) : 25333 - 25353
  • [37] Accurate iris center localization method using facial landmark, snakuscule, circle fitting and binary connected component
    Feng Xiao
    Kejie Huang
    Yue Qiu
    Haibin Shen
    Multimedia Tools and Applications, 2018, 77 : 25333 - 25353
  • [38] Superpixels by Bilateral Geodesic Distance
    Zhou, Yuanfeng
    Pan, Xiao
    Wang, Wenping
    Yin, Yilong
    Zhang, Caiming
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2017, 27 (11) : 2281 - 2293
  • [39] ISOLLE: LLE with geodesic distance
    Varini, Claudio
    Degenhard, Andreas
    Nattkemper, Tim W.
    NEUROCOMPUTING, 2006, 69 (13-15) : 1768 - 1771
  • [40] Euclidean and Geodesic Distance Profiles
    Janusch, Ines
    Artner, Nicole M.
    Kropatsch, Walter G.
    DISCRETE GEOMETRY FOR COMPUTER IMAGERY, DGCI 2017, 2017, 10502 : 307 - 318