3D Fingerprint Reconstruction

JR Function

Contractor

Contact Information

Description

Fingerprints are important biometric cues. Compared to conventional fingerprint sensors the use of contact-free stereoscopic image acquisition of the front-most finger segment has a set of advantages: Finger deformation is avoided, the entire relevant area for biometric use is covered, some technical aspects like sensor maintenance and cleaning are facilitated, and access to a three-dimensional reconstruction of the covered area is possible.

JR developed a photogrammetric workflow for nail-to-nail fingerprint reconstruction: A calibrated sensor setup with typically 5 cameras and dedicated illumination acquires adjacent stereo pairs. Using the silhouettes of the segmented finger a raw cylindrical model is generated. After preprocessing (shading correction, dust removal, lens distortion correction), each individual camera texture is projected onto the model. Image-to-image matching on these pseudo ortho images and dense 3D reconstruction obtains a textured cylindrical digital surface model with radial distances around the major axis and a grid size in the range of 25–50 µm. The model allows for objective fingerprint unwrapping and novel fingerprint matching algorithms since 3D relations between fingerprint features are available as additional cues. Moreover, covering the entire region with relevant fingerprint texture is particularly important for establishing a comprehensive forensic database.

The workflow is ready for industrial exploitation.

Project Duration

2003-2004

Main Partners

• TBS Touchless Biometric Systems    http://www.tbsinc.com/

Funding

• TBS Touchless Biometric Systems   http://www.tbsinc.com/
• JOANNEUM RESEARCH   http://www.joanneum.at

Figure 1: Textured Finger Model

Figure 2: Unwrapped Fingerprint, shading corrected

Presentation

• Presentation at the 8th ISPRS Conference on Optical 3-D Measurement Techniques, July 9-12, 2007, Zurich, Switzerland

Videos

• finger_scan__1.mov
• finger_scan_2.mpg

References

http://www.wipo.int/pctdb/en/wo.jsp?wo=2006021165

http://v3.espacenet.com/publicationDetails/biblio?CC=EP&NR=1693781&KC=&FT=E

http://www.patent-de.com/20070809/DE112004003011A5.html

Paar, G, Perucha, Md, Bauer, A, and Nauschnegg, B (2008).
Photogrammetric Fingerpring Unwrapping
Journal of Applied Geodesy, 2:13 - 20.

Parziale, G and Bischof, H (2004).
Image reconstruction and on-the-fly minutiae extraction of fingerprints acquired with sweep sensors
In: 28th Workshop of the Austrian Association of Pattern Recognition (OAGM/AAPR) Hagenberg, June 17-18, 2004, Austria., pp. 173-179.

Parziale, G and Niel, A (2004).
A Fingerprint Matching Using Minutiae Triangulation
In: Proc. of International Conference on Biometric Authentication (ICBA) Hong Kong, 15-17, July 2004, vol. 3072, pp. 241-248, Springer Verlag. LNCS.

Parziale, G and Niel, A (2004).
Fingerprint Matching Algorithm based on Minutiae Triangulation
In: Proceedings of 9th Computer Vision Winter Workshop, CVWW’04, Piran, Slovenia, 2004, vol. 3072/2004(ISBN 978-3-540-22146-3), pp. 241-248, Springer Verlag Berlin/Heidelberg. Lecture Notes in Computer Science - Biometric Authentification.