Performance of a photorefractive joint transform correlator for fingerprint identification

Jacques F. Rodolfo; Henri J. Rajbenbach; Jean-Pierre Huignard

doi:10.1117/12.196537

1 April 1995 Performance of a photorefractive joint transform correlator for fingerprint identification

Jacques F. Rodolfo, Henri J. Rajbenbach, Jean-Pierre Huignard

Author Affiliations +

Optical Engineering, Vol. 34, Issue 4, (April 1995). https://doi.org/10.1117/12.196537

Abstract

A photorefractive joint transform correlator is connected to a PC-based image processing board and tested for fingerprint recognition. Distortions due to rotation, scale, and partial hiding are considered: ± 4 deg in rotation, ± 7% in scale, and up to 80% hiding can be handled by the correlator. The performance of the correlator operating with a realtime fingerprint acquisition camera is then measured. The captured fingerprint is generally distorted with respect to its original counterpart stored in the PC memory. These distortions are mostly due to the positioning and pressure of the finger on the glass prism of the camera. We evaluate the recognition performance qualitatively and statistically with these distortions on a limited data bank and demonstrate 80% successful recognition rate.

Citation Download Citation

Jacques F. Rodolfo, Henri J. Rajbenbach, and Jean-Pierre Huignard "Performance of a photorefractive joint transform correlator for fingerprint identification," Optical Engineering 34(4), (1 April 1995). https://doi.org/10.1117/12.196537

Published: 1 April 1995

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