Combined optical and neural network fingerprint matching

This paper presents results on direct optical matching of inked and real-time fingerprint images. Direct optical correlations and hybrid optical neural network correlation are used in the matching system for inked fingerprints. Preliminary results on optical matching of real-time fingerprints use optical correlation. The test samples used in the inked image experiments are the fingerprint taken from NIST database SD-9. These images, in both binary and gray level forms, are stored in a VanderLugt correlator. Tests of typical cross correlations and auto correlation sensitivity for both binary and 8 bit gray images are presented. When global correlations are tested on a second inked image results are found to be strongly influenced by plastic distortion of the finger. When the correlations are used to generate features that are localized to parts of each fingerprint and combined using a neural network classification network and separate class-by-class matching networks, 84.3 percent matching accuracy is obtained on a test set of 100,000 image pairs. Initial results with real- time images suggest that the difficulties resulting from finger deformation can be avoided by combining many different distorted images when the hologram is constructed in the correlator. Testing this process will require analysis of 10-20 second sequences of digital video.

[1]  Charles L. Wilson,et al.  Training Dynamics and Neural Network Performance , 1997, Neural Networks.

[2]  J. Horner,et al.  Optical processing for security and anticounterfeiting , 1996, Conference Proceedings LEOS'96 9th Annual Meeting IEEE Lasers and Electro-Optics Society.

[3]  Bahram Javidi,et al.  Position‐invariant two‐dimensional image correlation using a one‐dimensional space integrating optical processor: application to security verification , 1996 .

[4]  Bahram Javidi,et al.  Experimental comparison of binary joint transform correlators used for fingerprint identification , 1996 .

[5]  L. Guibert,et al.  Fingerprint recognition using a partially rotation invariant composite filter in a FLC joint transform correlator , 1996 .

[6]  Jean-Pierre Huignard,et al.  Performance of a photorefractive joint transform correlator for fingerprint identification , 1995 .

[7]  Charles L. Wilson,et al.  Binary decision clustering for neural-network-based optical character recognition , 1994, Pattern Recognit..

[8]  Craig I. Watson,et al.  Neural Network Fingerprint Classification , 1994 .

[9]  Craig I. Watson,et al.  Massively Parallel Neural Network Fingerprint Classification System | NIST , 1992 .

[10]  F T Gamble,et al.  Real-time fingerprint verification system. , 1992, Applied optics.

[11]  J L Horner,et al.  Two-bit correlation. , 1985, Applied optics.

[12]  J. Goodman,et al.  A technique for optically convolving two functions. , 1966, Applied optics.

[13]  A. B. Vander Lugt,et al.  Signal detection by complex spatial filtering , 1964, IEEE Trans. Inf. Theory.