Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2022, Vol. 16 Issue (5) : 165332    https://doi.org/10.1007/s11704-021-0475-9
RESEARCH ARTICLE
Endowing rotation invariance for 3D finger shape and vein verification
Hongbin XU1, Weili YANG2, Qiuxia WU1(), Wenxiong KANG2()
1. School of Software Engineering, South China University of Technology, Guangzhou 510006, China
2. School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China
 Download: PDF(41164 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

Finger vein biometrics have been extensively studied for the capability to detect aliveness, and the high security as intrinsic traits. However, vein pattern distortion caused by finger rotation degrades the performance of CNN in 2D finger vein recognition, especially in a contactless mode. To address the finger posture variation problem, we propose a 3D finger vein verification system extracting axial rotation invariant feature. An efficient 3D finger vein reconstruction optimization model is proposed and several accelerating strategies are adopted to achieve real-time 3D reconstruction on an embedded platform. The main contribution in this paper is that we are the first to propose a novel 3D point-cloud-based end-to-end neural network to extract deep axial rotation invariant feature, namely 3DFVSNet. In the network, the rotation problem is transformed to a permutation problem with the help of specially designed rotation groups. Finally, to validate the performance of the proposed network more rigorously and enrich the database resources for the finger vein recognition community, we built the largest publicly available 3D finger vein dataset with different degrees of finger rotation, namely the Large-scale Finger Multi-Biometric Database-3D Pose Varied Finger Vein (SCUT LFMB-3DPVFV) Dataset. Experimental results on 3D finger vein datasets show that our 3DFVSNet holds strong robustness against axial rotation compared to other approaches.
Keywords 3D finger-vein      biometrics      point-cloud      CNN     
Corresponding Author(s): Qiuxia WU,Wenxiong KANG   
Just Accepted Date: 03 March 2021   Issue Date: 28 January 2022
 Cite this article:   
Hongbin XU,Weili YANG,Qiuxia WU, et al. Endowing rotation invariance for 3D finger shape and vein verification[J]. Front. Comput. Sci., 2022, 16(5): 165332.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-021-0475-9
https://academic.hep.com.cn/fcs/EN/Y2022/V16/I5/165332
Fig.1  Illustration of the finger posture variation problem if rotation is taken into consideration in finger vein verification
Fig.2  The framework of the proposed 3D finger vein verification system
Fig.3  3D reconstruction schematic diagram. (a) shows a finger model in our predefined 3D coordinate system; (b) extracts a cross section from the finger model (a) and spreads in a 2D plane
Fig.4  Illustration of the preprocessing procedure on 3D finger vein point cloud
Fig.5  Illustration of the rotation group on our 3D finger vein point cloud
Fig.6  A simple example of the rotation group. ? represent the convolution operator. Rotation on the input data equals to permutation in the group
Fig.7  Illustration of the network architecture. The input point cloud in the first row is rotated arbitrary to be the input point cloud in the second row. “GCN” means graph convolutional neural network. “MLP” represents multi layer perceptron and “Pool” means global pooling. The initial rotation problem is transformed into a permutation problem by the rotation group, and finally transformed to invariance by global pooling
Fig.8  An example of a simple graph convolutional layer. p represent the center point of this local region and ni,i=1,2,3,4,5 represent the k-nearest neighbors of point p.
Subset Rotation Subjects Times Samples
SCUT-3DFV-V1-ER [8] Small 203 6 1218
SCUT-3DFV-V1-HR [8] Large 203 14 2842
3DPVFV-ER Small 702 10 7020
3DPVFV-HR Large 702 14 9828
Tab.1  Instruction of the SCUT-3DFV-V1 and LFMB-3DPVFV Dataset
Methods [8] Ours
Device A1 A A B2
Implementation Matlab Matlab C++ C++
Acceleration √ √
Preprocessing 848.19 948.33 59.52 270.79
3D reconstruction 1532.09 724.65 4.75 19.94
Texture mapping 5331.14 328.04 28.49 138.5
Total 7711.42 2001.02 92.76 429.23
Tab.2  Time consumption for 3D Reconstruction pipline (ms)
Fig.9  Visualization of our 3DFVSNet’s attention towards arbitrary simulated rotation. Grad-CAM++ [41] is applied for calculating the heatmap of the input point cloud. Besides the 3D heatmap, we also provide the top view of the 3D heatmap point cloud for a clear comprehension. The black dotted arrow means the reference direction
Fig.10  Visualization of our 3DFVSNet’s attention towards arbitrary rotation in realistic situation. Grad-CAM++ [41] is applied for calculating the heatmap of the input point cloud. For each sample, 3D heatmap and its top view are presented in the first two columns. The black dotted arrow provides a reference direction and the red arrow represents the unfolding direction. Following the direction of red arrow, we unfold the point cloud and interpolate the discrete points into 2D texture map and heatmap with a resolution of 200×200 in the remaining two columns
Methods Data 3DFV-V1-ER/% 3DFV-V1-HR/%
DOCH [42] Image 8.42 25.56
Uniform LBP [43] Image 8.65 17.29
MCP [11] Image 4.32 20.75
Deepvein [20] Image 8.08 9.25
Das et al. [22] Image 6.25 8.77
Mobile CNN [8] Image 3.05 9.54
ResNet50 [44] Image 3.67 11.76
PointNet [9] Points 10.10 15.39
DensePoints [37] Points 4.11 7.73
DGCNN [36] Points 3.89 7.00
3DFVSNet Points 2.61 5.07
Tab.3  Performance comparison on SCUT-3DFV-V1
Methods Data 3DPVFV-ER/% 3DPVFV-HR/%
DOCH [42] Image 18.05 31.78
Uniform LBP [43] Image 19.09 31.17
MCP [11] Image 14.44 28.40
Deepvein [20] Image 5.56 8.71
Das et al. [22] Image 5.67 8.91
Mobile CNN [8] Image 2.97 5.38
ResNet50 [44] Image 3.23 5.97
PointNet [9] Points 4.23 8.43
DensePoints [37] Points 4.88 8.36
DGCNN [36] Points 3.60 6.30
3DFVSNet Points 2.81 4.49
Tab.4  Performance comparison on LFMB-3DPVFV
Fig.11  The ROC curves of various algorithms evaluated on dataset 3DFV-V1-ER (easy rotation)
Fig.12  The ROC curves of various algorithms evaluated on dataset 3DFV-V1-HR (hard rotation)
Fig.13  The ROC curves of various algorithms evaluated on dataset LFMB-3DPVFV-ER (easy rotation)
Fig.14  The ROC curves of various algorithms evaluated on dataset LFMB-3DPVFV-HR (hard rotation)
Benchmark Modalities EER/%
3DFV-V1-ER Shape 4.81
Shape + Texture 2.61
3DFV-V1-HR Shape 12.15
Shape + Texture 5.07
3DPVFV-ER Shape 5.84
Shape + Texture 2.81
3DPVFV-HR Shape 10.00
Shape + Texture 4.49
Tab.5  Ablation study on different modalities of 3D finger vein
Method Groups 3DFV-V1-ER/% 3DFV-V1-HR/%
3DFVSNet 360 2.61 5.07
180 3.55 7.14
90 3.70 7.20
45 3.70 7.79
PointNet [9] 1 10.10 15.39
DensePoints [37] 1 4.11 7.73
DGCNN [36] 1 3.89 7.00
Tab.6  Ablation study of different grops on SCUT-3DFV-V1
Methods Groups 3DPVFV-ER/% 3DPVFV-HR/%
3DFVSNet 360 2.81 4.49
180 2.83 4.60
90 2.85 4.70
45 2.95 4.99
PointNet [9] 1 4.23 8.43
DensePoints [37] 1 4.88 8.36
DGCNN [36] 1 3.60 6.30
Tab.7  Ablation study of different groups on SCUT-LFMB-3DPVFV
Network Input Resolution Params FLOPs CPU runtime/ms GPU runtime/ms
3DFVSNet Points 40000 × 4 1.55M 3.41G 360 12.5
10000 × 4 891M 90 3.2
PointNet [9] Points 40000 × 4 0.83M 6.07G 570 15.7
10000 × 4 1.52G 150 6.3
DGCNN [36] Points 40000 × 4 1.82M 40.39G ? ?
10000 × 4 10.1G 5340 97.6
ResNet50 [44] Image 224 ×224 ×3 24.05M 4.11G 210 11.8
Deepvein [20] Image 128 ×128 ×1 70.63M 3.56G 220 8.7
Das et al. [22] Image 153 ×153 ×1 188.82M 19.32G 520 24.4
Tab.8  The comparison of time efficiency among our proposed 3DFVSNet and other methods
Fig.15  Fig.A1 The visualization of the reconstructed 3D model from the same finger under different posture
1 Y Zhou . Human identification using finger images. IEEE Trans Image Process, 2011, 21( 4): 2228– 2244
2 H Qin , M A El-Yacoubi . Deep representation-based feature extraction and recovering for finger-vein verification. IEEE Transactions on Information Forensics and Security, 2017, 12( 8): 1816– 1829
3 P Tome, R Raghavendra, C Busch, S Tirunagari, N Poh, B Shekar, D Gragnaniello, C Sansone, L Verdoliva, S Marcel. The 1st competition on counter measures to finger vein spoofing attacks. In: Proceedings of International Conference on Biometrics. 2015, 513– 518
4 E C Lee , K R Park . Image restoration of skin scattering and optical blurring for finger vein recognition. Optics and Lasers in Engineering, 2011, 49( 7): 816– 828
5 S Qiu , Y Liu , Y Zhou , J Huang , Y Nie . Finger-vein recognition based on dual-sliding window localization and pseudo-elliptical transformer. Expert Systems with Applications, 2016, 64 : 618– 632
6 B Prommegger , C Kauba , M Linortner , A Uhl . Longitudinal finger rotation deformation detection and correction. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2019, 1( 2): 123– 138
7 N Miura , A Nagasaka , T Miyatake . Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Machine vision and applications, 2004, 15( 4): 194– 203
8 W Kang , H Liu , W Luo , F Deng . Study of a full-view 3d finger vein verification technique. IEEE Transactions on Information Forensics and Security, 2020, 15 : 1175– 1189
9 C R Qi, H Su, K Mo, L J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2017, 652– 660
10 Z Wu, S Song, A Khosla, F Yu, L Zhang, X Tang, J Xiao. 3d shapenets: A deep representation for volumetric shapes. In: Proceedings of IEEE conference on computer vision and pattern recognition. 2015, 1912−1920
11 N Miura , A Nagasaka , T Miyatake . Extraction of finger-vein patterns using maximum curvature points in image profiles. IEICE TRANSACTIONS on Information and Systems, 2007, 90( 8): 1185– 1194
12 B Huang, Y Dai, R Li, D Tang, W Li. Finger-vein authentication based on wide line detector and pattern normalization. In: Proceedings of the 20th. International Conference on Pattern Recognition. 2010, 1269−1272
13 D Hartung , M A Olsen , H Xu , H T Nguyen , C Busch . Comprehensive analysis of spectral minutiae for vein pattern recognition. IET biometrics, 2012, 1( 1): 25– 36
14 F Liu , G Yang , Y Yin , S Wang . Singular value decomposition based minutiae matching method for finger vein recognition. Neurocomputing, 2014, 145 : 75– 89
15 W Kang , X Chen , Q Wu . The biometric recognition on contactless multi-spectrum finger images. Infrared Physics & Technology, 2015, 68 : 19– 27
16 W Yang , W Ji , J H Xue , Y Ren , Q Liao . A hybrid finger identification pattern using polarized depth-weighted binary direction coding. Neurocomputing, 2019, 325 : 260– 268
17 G Yang, X Xi, Y Yin. Finger vein recognition based on (2d)2 pca and metric learning. Journal of Biomedicine and Biotechnology, 2012, 2012
18 S A Radzi , M K Hani , R Bakhteri . Finger-vein biometric identification using convolutional neural network. Turkish Journal of Electrical Engineering & Computer Sciences, 2016, 24( 3): 1863– 1878
19 W Liu, W Li, L Sun, L Zhang, P Chen. Finger vein recognition based on deep learning. In: Proceedings of the 12th Conference on Intustrial Elatronics and applications. 2017, 205– 210
20 H Huang, S Liu, H Zheng, L Ni, Y Zhang, W Li. Deepvein: Novel finger vein verification methods based on deep convolutional neural networks. In: Proceedings of IEE Internatinal Conference on Identity, Security and Beharior Analysis. 2017, 1– 8
21 J M Song , W Kim , K R Park . Finger-vein recognition based on deep densenet using composite image. IEEE Access, 2019, 7 : 66845– 66863
22 R Das , E Piciucco , E Maiorana , P Campisi . Convolutional neural network for finger-vein-based biometric identification. IEEE Transactions on Information Forensics and Security, 2018, 14( 2): 360– 373
23 Q Chen, L Yang, G Yang, Y Yin, X Meng. Dfvr: Deformable finger vein recognition. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 2017, 1 278– 1282
24 B Prommegger, A Uhl. Rotation invariant finger vein recognition. In: Proceedings of IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS). 2019, 1– 9
25 X Xi , G Yang , Y Yin , X Meng . Finger vein recognition with personalized feature selection. Sensors, 2013, 13( 9): 11243– 11259
26 Y Matsuda , N Miura , A Nagasaka , H Kiyomizu , T Miyatake . Finger-vein authentication based on deformation-tolerant feature-point matching. Machine Vision and Applications, 2016, 27( 2): 237– 250
27 E C Lee , H C Lee , K R Park . Finger vein recognition using minutia-based alignment and local binary pattern-based feature extraction. International Journal of Imaging Systems and Technology, 2009, 19( 3): 179– 186
28 K R Park , Y K Jang , B J Kang . A study on touchless finger vein recognition robust to the alignment and rotation of finger. The KIPS Transactions: PartB, 2008, 15( 4): 275– 284
29 B Huang, Y Dai, R Li, D Tang, W Li. Finger-vein authentication based on wide line detector and pattern normalization. In: Proceedings of the 20th International Conference on Pattern Recognition. 2010, 1269−1272
30 L Yang , G Yang , Y Yin , X Xi . Finger vein recognition with anatomy structure analysis. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28( 8): 1892– 1905
31 Q Chen , L Yang , G Yang , Y Yin . Geometric shape analysis based finger vein deformation detection and correction. Neurocomputing, 2018, 311 : 112– 125
32 Z Ma, L Fang, J Duan, S Xie, Z Wang. Personal identification based on finger vein and contour point clouds matching. In: Proceedings of IEE International Conference on Mechatronics and Automation. 2016, 1983−1988
33 S Bunda. 3D point cloud reconstruction based on the finger vascular pattern. B.S. thesis, University of Twente, 2018
34 C R Qi, L Yi, H Su, L J Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems, 2017, 5099−5108
35 M Jiang, Y Wu, T Zhao, Z Zhao, C Lu. Pointsift: A sift-like network module for 3d point cloud semantic segmentation. arXiv preprint arXiv: 180700652, 1807
36 Y Wang , Y Sun , Z Liu , S E Sarma , M M Bronstein , J M Solomon . Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 2019, 38( 5): 1– 12
37 Y Liu, B Fan, G Meng, J Lu, S Xiang, C Pan. Densepoint: Learning densely contextual representation for efficient point cloud processing. In: Proceedings of the IEEE International Conference on Computer Vision. 2019, 5239−5248
38 T Svoboda , D Martinec , T Pajdla . A convenient multi-camera self-calibration for virtual environments. Presence: Teleoperators & virtual environments, 2005, 14( 4): 407– 422
39 T Cohen, M Welling. Group equivariant convolutional networks. In: Proceedings of International conference on machine learning. 2016, 2990−2999
40 Y Wen, K Zhang, Z Li, Y Qiao. A discriminative feature learning approach for deep face recognition. In: Proceedings of European Conference on Computer Vision. 2016, 499– 515
41 A Chattopadhyay, A Sarkar, P Howlader, V Balasubramanian. Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In: Proceedings of IEEE Winter Conference on Applications of Computer Vision. 2018, 839– 847
42 Y Lu, M Tu, H Wang, J Zhao, W Kang. Finger vein recognition based on double-orientation coding histogram. In: Proceedings of the 14th Chinese Conference on Biometric Recognition. 2019, 20– 27
43 T Ojala , M Pietikainen , T Maenpaa . Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 2002, 24( 7): 971– 987
44 K He, X Zhang, S Ren, J Sun. Deep residual learning for image recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition. 2016, 770– 778
[1] Yajing GUO, Xiujuan LEI, Lian LIU, Yi PAN. circ2CBA: prediction of circRNA-RBP binding sites combining deep learning and attention mechanism[J]. Front. Comput. Sci., 2023, 17(5): 175904-.
[2] Guoshuai ZHOU, Xiuxia TIAN, Aoying ZHOU. Image copy-move forgery passive detection based on improved PCNN and self-selected sub-images[J]. Front. Comput. Sci., 2022, 16(4): 164705-.
[3] Juntao CHEN, Quan ZOU, Jing LI. DeepM6ASeq-EL: prediction of human N6-methyladenosine (m 6A) sites with LSTM and ensemble learning[J]. Front. Comput. Sci., 2022, 16(2): 162302-.
[4] Feifei ZHANG,Yongbin YU,Qirong MAO,Jianping GOU,Yongzhao ZHAN. Pose-robust feature learning for facial expression recognition[J]. Front. Comput. Sci., 2016, 10(5): 832-844.
[5] Peng JIANG,Qiaoyan WEN,Wenmin LI,Zhengping JIN,Hua ZHANG. An anonymous and efficient remote biometrics user authentication scheme in a multi server environment[J]. Front. Comput. Sci., 2015, 9(1): 142-156.
[6] Hunny MEHROTRA, Banshidhar MAJHI. Local feature based retrieval approach for iris biometrics[J]. Front. Comput. Sci., 2013, 7(5): 767-781.
[7] Tang Yuanyan. Status of pattern recognition with wavelet analysis[J]. Front. Comput. Sci., 2008, 2(3): 268-294.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed