香港理工大学2D_3D_掌纹数据集(The Hong Kong Polytechnic University (PolyU) 2D_3D_Palmprint
Databa)
现代言情小说推荐
神州十二号数据介绍：自愧弗如
Palmprint has proved to be one of the most unique and stable biometric characteristics. Almost all the current palmprint recognition techniques capture the two dimensional (2D) image of the palm surface and u it for feature extraction and matching. Although 2D palmprint recognition can achieve high accuracy, the 2D palmprint images are relatively easy to be counterfeited and much three dimensional (3D) depth information is lost in the imaging process. 3D Palmprint is a good choice to overcome the flaws.
关键词：
香港理工大学,2D,3D，掌纹,UGC/CRC,
PloyU,2D,3D,palmprint,UGC/CRC,ear
数据格式：
IMAGE
数据详细介绍：
The Hong Kong Polytechnic University (PolyU)
2D_3D_Palmprint Databa
Overview:
Palmprint has proved to be one of the most unique and stable biometric characteristics. Almost all the current palmprint recognition techniques capture the two dimensional (2D) image of the palm surface and u it for feature extraction and matching. Although 2D palmprint recognition can achieve high accuracy, the 2D palmprint images are relatively easy to be counterfeited and much three dimensional (3D) depth information is lost in the imaging process. 3D Palmprint is a good choice to overcome the flaws.
The Biometric Rearch Centre (UGC/CRC) at The Hong Kong Polytechnic University has developed a real time 3D palmprint capture device, and has ud it to construct a large-scale 3D palmprint databa. To advance rearch and to provide rearchers working in the area of 3D palm
print recognition a platform to compare the effectiveness of 3D palmprint recognition algorithms, we intend to publish our 3D palmprint databa, making it freely available for academic, noncommercial us.
(a) The outlook of the 3D palmprint image acquisition device; (b) The device is being ud to collect 3D palmprint image samples.
Description of the PolyU 3D Palmprint Databa:
The PolyU 3D Palmprint Databa contains 8000 samples collected from 400 different palms. Twenty samples from each of the palms were collected in two parated ssions, where 10 samples were captured in each ssion, respectively. The average time interval between the two ssions is one month. Each sample contains a 3D ROI (region of interest) and its corresponding 2D ROI. Each 3D ROI is recorded by a binary file which contains 128*128 float values denoting the depth infromation of the palmprint to a reference plane, where each 2D ROI is recorded by a BMP format image file. The 3D ROIs are stored in the folder, "Sub3D", and labeled as "Sub3D_I_M_N.dat" or
"Sub3D_II_M_N.dat", where "I" indicates the first ssion, "II" indicates the cond ssion, "M" is the unique palm identifier (range from 1 to 550, some numbers are abnt), and "N" is the index of each palm (range from 0 to 9).
The 2D ROIs are stored in the folder "Sub2D", and labeled as
"Sub2D_I_M_N.bmp" or "Sub2D_II_M_N.bmp" which are one-to-one corresponding to their 3D ROIs.
Related Publication:
1. W. Li, D. Zhang, L. Zhang, G. Lu, and J. Yan, "Three Dimensional
Palmprint Recognition with Joint Line and Orientation Features", IEEE
Transactions on Systems, Man, and Cybernetics, Part C, In Press.
2. W. Li, L. Zhang, D. Zhang, G. Lu, and J. Yan, “Efficient Joint 2D and
3D Palmprint Matching with Alignment Refinement”, in: Proc. CVPR
2010.
3. D. Zhang, G. Lu, W. Li, L. Zhang, and N. Luo, "Palmprint Recognition
Using 3-D Information", IEEE Transactions on Systems, Man, and
Cybernetics, Part C: Applications and Reviews, Volume 39, Issue 5, pp.
505 - 519, Sept. 2009.尖刀网络营销
4. W. Li, D. Zhang, and L. Zhang, "Three Dimensional Palmprint
Recognition", IEEE International Conference on Systems, Man, and
Cybernetics, 2009.
5. D. Zhang, G. Lu, W. Li, L. Zhang, and N. Luo, "Three Dimensional
Palmprint Recognition using Structured Light Imaging", 2nd IEEE如何安装空调
International Conference on Biometrics: Theory, Applications and
Systems, BTAS 2008, pp. 1-6.
The Announcement of the Copyright
All rights of the PolyU 3D Palmprint Databa are rerved. The databa is only available for rearch and noncommercial purpos. Commercial distribution or any act related to commercial u of this databa is strictly prohibited. A clear acknowledgement should be made for any public w
ork bad on the PolyU 3D Palmprint Databa. A citation to "PolyU 3D Palmprint Databa, p.polyu.edu.hk/~biometrics/2D_3D_Palmprint.htm”
and our related works must also be added in the references. A soft copy of any relead or public documents that u the PolyU 3D Palmprint Databa must be forwarded to: cslzhang@comp.polyu.edu.hk
Downloading Steps:
This PolyU 3D Palmprint Databa is made publicly available and can be obtained from this website. It is totally free for academic, noncommercial purpos. Any person or organization that wishes to u the databa must agree to the terms of the agreement and fill in the agreement forms. Then, nd the application form to cslzhang@comp.polyu.edu.hk. The successful applicants will receive their login accounts and passwords to download the databa. Moreover, to facilitate checking the 3D palmprint ROI visually, we developed a tool, which is available here. C and Matlab code for reading the 3D palmprint ROI is available here.
2D+3D Palmprint ROI.zip
陆机文赋
If you want to u our 2D palmprint databa (IEEE PAMI 2003), you can
go here.
Application Form
Contact Information:疫情下的英雄
Lei ZHANG, Associate Professor
Biometric Rearch Centre (UGC/CRC)
The Hong Kong Polytechnic University
Hung Hom, Kowloon, Hong Kong
E-mail: cslzhang@comp.polyu.edu.hk
数据预览：
