3D matching techniques using OCT fingerprint point clouds

Henrique S. Gutierrez da Costa; Luciano Silva; Olga R. P. Bellon; Audrey K. Bowden; Raphael K. Czovny

doi:10.1117/12.2253107

16 February 2017 3D matching techniques using OCT fingerprint point clouds

Henrique S. Gutierrez da Costa, Luciano Silva, Olga R. P. Bellon, Audrey K. Bowden, Raphael K. Czovny

Proceedings Volume 10068, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XV; 100680O (2017) https://doi.org/10.1117/12.2253107
Event: SPIE BiOS, 2017, San Francisco, California, United States

Abstract

Optical Coherence Tomography (OCT) makes viable acquisition of 3D fingerprints from both dermis and epidermis skin layers and their interfaces, exposing features that can be explored to improve biometric identification such as the curvatures and distinctive 3D regions. Scanned images from eleven volunteers allowed the construction of the first OCT 3D fingerprint database, to our knowledge, containing epidermal and dermal fingerprints. 3D dermal fingerprints can be used to overcome cases of Failure to Enroll (FTE) due to poor ridge image quality and skin alterations, cases that affect 2D matching performance. We evaluate three matching techniques, including the well-established Iterative Closest Points algorithm (ICP), Surface Interpenetration Measure (SIM) and the well-known KH Curvature Maps, all assessed using a 3D OCT fingerprint database, the first one for this purpose. Two of these techniques are based on registration techniques and one on curvatures. These were evaluated, compared and the fusion of matching scores assessed. We applied a sequence of steps to extract regions of interest named (ROI) minutiae clouds, representing small regions around distinctive minutia, usually located at ridges/valleys endings or bifurcations. The obtained ROI is acquired from the epidermis and dermis-epidermis interface by OCT imaging. A comparative analysis of identification accuracy was explored using different scenarios and the obtained results shows improvements for biometric identification. A comparison against 2D fingerprint matching algorithms is also presented to assess the improvements.

Conference Presentation

Citation Download Citation

Henrique S. Gutierrez da Costa, Luciano Silva, Olga R. P. Bellon, Audrey K. Bowden, and Raphael K. Czovny "3D matching techniques using OCT fingerprint point clouds", Proc. SPIE 10068, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XV, 100680O (16 February 2017); https://doi.org/10.1117/12.2253107

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available