Traditional fingerprint identification relies on the scanning of signals generated from the physical contact of fingers to acquire data. The fingerprint images are popularly acquired by pressing or rolling one’s fingers against the sensors surface which can be from silicon, glass or the polymer. Due to sensor noise, improper placement of fingers, finger rotation, skin deformation and smearing of fingers due to pressure, the resulting fingerprint images are therefore often distorted and/or degraded in their quality. By avoiding contact with system acquisition surface, the contactless fingerprint acquisition technologies can be used to address these limitations. Contactless fingerprint sensing enables recovery of high quality fingerprint images that can represent true finger surface and such approach can alleviate skin deformations and sensor noise. In addition to these benefits, contactless 3D fingerprint systems can offer significantly improved accuracy and advanced anti-spoofing capabilities than those can be availed from contactless 2D fingerprint systems.
Currently there is no publicly available 3D fingerprint database which is acquired using colored illumination. Therefore a new two-session 2D/3D fingerprints database acquiring from 300 different clients consisting of 2760 different 3D fingerprints is developed. This database has been reconstructed from 5520 colored 2D fingerprints images and is being made available publicly to promote further research efforts in this area. As detailed in reference , database was acquired during September 2014 to February 2016 in our university and uses 16560 2D fingerprint images to reconstruct entire 3D fingerprint database.
Colored 2D fingerprints and corresponding reconstructed 3D fingerprints
The database is made available freely for the researchers from June 2016 onwards. Interested researchers should follow following steps to acquire the 'The Hong Kong Polytechnic University 3D Fingerprint Images Database Version 2.0’.
All the rights of the The Hong Kong Polytechnic University 3D Fingerprint Images Database Version 2.0 are reserved and commercial use/distribution of this database is strictly prohibited. All the technical reports and papers that report experimental results from this database should provide due acknowledgement and reference. The reference should appear as 'The Hong Kong Polytechnic University 3D Fingerprint Images Database Version 2.0. Questions regarding this database can be directed to Ajay.Kumar@polyu.edu.hk.
 Chenhao Lin, Ajay Kumar, “Tetrahedron Based Fast 3D Fingerprint Identification Using Colored LEDs Illumination”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 99, DOI: 10.1109/TPAMI.2017.2771292, Nov. 2017.
Back to Databases Page