Tsinghua University Finger Vein and Finger Dorsal Texture Database（THU-FVFDT）and THUMVFV-3V Database
THU-FVFDT1 Introduction
THU-FVFDT1 contains raw finger vein and finger dorsal texture images of 220 different subjects. It was named by THU-FVFDT before 2014-06-09. The majority of the subjects are students and staff volunteers from Graduate School at Shenzhen, Tsinghua University. Images are captured in two different sessions with interval of about dozens of seconds. One session is for training and the other for testing. Four finger vein images and four finger dorsal texture images are captured simultaneously in each session. We only offer one of four images in that there is approximately no difference between them. The size of raw images is 720×576 pixels.
Database:
Publish date:
2012-12-28
THU-FVFDT2 Introduction
THU-FVFDT2 contains Regions of Interest (ROIs) of finger vein and finger dorsal texture from 610 different subjects, the first 220 ROIs of which are extracted from THU-FVFDT1. The last 390 ROIs are captured in two different sessions with interval ranging from about three days to one week. One session is for training and the other for testing. Each ROI is normalized to 200*100 pixels. The majority of the subjects are students and staff volunteers from Graduate School at Shenzhen, Tsinghua University.
Database:
Publish date:
2014-06-12
THU-FVFDT3 Introduction
THU-FVFDT3 contains 610*16 raw finger vein and finger dorsal texture images of THU-FVFDT2. The images are all grayscale in considerarion of equal value in three channels of the raw color images except capture time displayed on top left corner.
Note:
1.Three invalid images in the folder FV3_Test/597/ were updated by adding different level Gaussian noise into ‘1.bmp’ (zero mean and 0.001 variance for ‘2.bmp’, zero mean and 0.002 variance for ‘3.bmp’, zero mean and 0.004 variance for ‘4.bmp’) on Dec. 13, 2019.
2.An invalid image ‘FV3_Train/1/2.bmp’ was updated by flipping on Dec. 13, 2019.
Database:
FV3_Test.zip FV3_Train.zip FDT3_Test.zip FDT3_Train.zip
Publish date:
2014-09-05
THUMVFV-3V Introduction
THUMVFV-3V database, a multi-view finger vein database collected over two sessions with an average interval of 45.8 days, includes 660 classes with 12 samples per class. Three types of ROIs and finger masks are provided.
Database:
Publish date:
2023-06
Copyright
All rights of the THU-FVFDT Database and THUMVFV-3V Database are reserved. The database is only available for academic research and noncommercial purposes. Any commercial uses of this database are strictly prohibited.
Download:
Please download ZIP files and sign on the license agreement. Then, send the license agreement to yangelwm@163.com. The successful applicants will receive the passwords for unzipping the downloaded files.
License agreement:
Contact Information:
Wenming Yang, Associate Professor
Visual Information Processing Lab. (VIP Lab.)
Department of Electronics Engineering/Graduate School at Shenzhen Tsinghua University
Tsinghua campus, the university town of Xili, Nanshan District, Shenzhen, China
E-mail: yangelwm@163.com
Related Papers:
[1] Zhao P, Song Y, Wang S, et al. VPCFormer: A transformer-based multi-view finger vein recognition model and a new benchmark[J]. Pattern Recognition, 2023: 110170.
[2] Zhao P, Zhao S, Xue J H, et al. The neglected background cues can facilitate finger vein recognition[J]. Pattern Recognition, 2023, 136: 109199.
[3] Song Y, Zhao P, Wang S, et al. Study of 3D Finger Vein Biometrics on Imaging Device Design and Multi-view Verification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023.
[4] Song Y, Zhao P, Yang W, et al. EIFNet: An Explicit and Implicit Feature Fusion Network for Finger Vein Verification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 33(5): 2520-2532.
[5] Zhao P, Zhao S, Chen L, et al. Exploiting multiperspective driven hierarchical content-aware network for finger vein verification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(11): 7938-7950.
[6] Zhao P, Chen Z, Xue J H, et al. Single-Sample Finger Vein Recognition via Competitive and Progressive Sparse Representation[J]. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2022.
[7] Yang W, Hui C, Chen Z, et al. FV-GAN: Finger Vein Representation Using Generative Adversarial Networks[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(9): 2512-2524.
[8] Yang W, Ji W, Xue J H, et al. A hybrid finger identification pattern using Polarized depth-Weighted Binary Direction Coding[J]. Neurocomputing, 2019, 325: 260-268.
[9] Yang W, Chen Z, Qin C, et al. $\alpha $-Trimmed Weber Representation and Cross Section Asymmetrical Coding for Human Identification Using Finger Images[J]. IEEE Transactions on Information Forensics and Security, 2018, 14(1): 90-101.
[10] Yang W, Huang X, Zhou F, et al. Comparative competitive coding for personal identification by using finger vein and finger dorsal texture fusion[J]. Information sciences, 2014, 268: 20-32.
Update date:
2023-12-08