Finger-vein Recognition using Deep Fully Convolutional Neural Semantic Segmentation Networks: The Impact of Training Data

被引:0
|
作者
Jalilian, Ehsaneddin [1 ]
Uhl, Andreas [1 ]
机构
[1] Univ Salzburg, Dept Comp Sci, Jakob Haringer Str 2, Salzburg, Austria
来源
2018 10TH IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS) | 2018年
关键词
D O I
暂无
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
We propose a novel approach for finger-vein recognition, focused on direct extraction of actual finger-vein patterns from NIR finger images without any specific pre- or post-processing, using semantic segmentation convolutional neural networks (CNNs). We utilize three network architectures and besides identifying efficient training and configuration settings for these networks, using manually annotated training data, we present a training model based on automatically generated labels to improve the networks' performance. Based on our experimental results, the proposed model can achieve superior performance over traditional finger-vein recognition algorithms. As further contribution, we also release human annotated ground-truth vein pixel labels (required for training the networks) for a subset of two well known finger-vein databases used in this work, and a corresponding tool for further annotations.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Adaptive Gabor Convolutional Neural Networks for Finger-Vein Recognition
    Zhang, Yakun
    Li, Weijun
    Zhang, Liping
    Lu, Yaxuan
    2019 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE BIG DATA AND INTELLIGENT SYSTEMS (HPBD&IS), 2019, : 219 - 222
  • [2] Finger vein recognition based on Deep Convolutional Neural Networks
    Weng, Lecheng
    Li, Xiaoqiang
    Wang, Wenfeng
    2020 13TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2020), 2020, : 266 - 269
  • [3] Finger-vein recognition using a novel enhancement method with convolutional neural network
    Bilal, Anas
    Sun, Guangmin
    Mazhar, Sarah
    JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS, 2021, 44 (05) : 407 - 417
  • [4] Finger-vein biometric identification using convolutional neural network
    Ahmad Radzi, Syafeeza
    Khalil-Hani, Mohamed
    Bakhteri, Rabia
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2016, 24 (03) : 1863 - 1878
  • [5] FULLY AUTOMATIC SEMANTIC SEGMENTATION OF KNEE PLAIN RADIOGRAPHS USING CONVOLUTIONAL DEEP NEURAL NETWORKS
    Tiulpin, A.
    Thevenot, J.
    Saarakkala, S.
    OSTEOARTHRITIS AND CARTILAGE, 2018, 26 : S446 - S446
  • [6] Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors
    Hong, Hyung Gil
    Lee, Min Beom
    Park, Kang Ryoung
    SENSORS, 2017, 17 (06)
  • [7] Convolutional Neural Network Based Deep Feature Learning for Finger-vein Identification
    Singh, Manjit
    Singla, Sunil Kumar
    PROCEEDINGS OF 2019 2ND INTERNATIONAL CONFERENCE ON ELECTRONICS AND ELECTRICAL ENGINEERING TECHNOLOGY (EEET 2019), 2019, : 104 - 107
  • [8] Semantic image segmentation for sea ice parameters recognition using deep convolutional neural networks
    Zhang, Chengqian
    Chen, Xiaodong
    Ji, Shunying
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2022, 112
  • [9] Brain Tumor Segmentation Using Deep Fully Convolutional Neural Networks
    Kim, Geena
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2017, 2018, 10670 : 344 - 357
  • [10] Finger-Vein Recognition Based on Deep DenseNet Using Composite image
    Song, Jong Min
    Kim, Wan
    Park, Kang Ryoung
    IEEE ACCESS, 2019, 7 : 66845 - 66863