Eung Gi Paek

Effect of resolution and image quality on combined optical and neural network fingerprint matching

Abstract This paper presents results on direct optical matching, using Fourier transforms and neural networks for matching fingerprints for authentication. Direct optical correlations and hybrid optical neural network correlation are used in the matching system. The test samples used in the experiments are the fingerprints taken from NIST database SD-9. These images, in both binary and gray-level forms, are stored in a VanderLugt correlator (A. VanderLugt, Signal detection by complex spatial filtering, IEEE Trans. Inform. Theory IT-10 (1964) 139–145). Tests of typical cross correlations and autocorrelation sensitivity for both binary and 8 bit gray images are presented. When Fourier transform (FT) 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, 90.9% matching accuracy is obtained on a test set of 200,000 image pairs. These results are obtained on images using 512 pixel resolution. The effect of image quality and resolution are tested using 256 and 128 pixel images, and yield accuracy of 89.3 and 88.7%. The 128-pixel images show only ridge flow and have no reliably detectable ridge endings or bifurcations and are therefore not suitable for minutia matching. This demonstrates that Fourier transform matching and neural networks can be used to match fingerprints which have too low image quality to be matched using minutia-based methods. Since more than 258,000 images were used to test each hybrid system, this is the largest test to date of FT matching for fingerprints.

Nonmechanical image rotation with an acousto-optic dove prism

We report what we believe to be the first method for nonmechanical and programmable image rotation. The method uses a pair of crossed acousto-optic beam deflectors and a polygon mirror to emulate the mechanical dove prism. It is capable of fast (of the order of microseconds) image rotation to an arbitrary angle in a programmable manner. An experimental result that proves the concept is provided.

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.

All-optical image transmission through a single-mode fiber.

All-optical transmission of two-dimensional images through a single single-mode fiber with a two-dimensional multicolor surface-emitting laser array and a volume hologram is described. A preliminary experimental result to prove the concept of the idea is demonstrated by transmitting a simple 2 x 2 image over a distance of 1 mile (1.61 km).

Transverse grating-assisted narrow-bandwidth acousto-optic tunable filter.

An experimental acousto-optic tunable filter that has a narrow spectral bandwidth (0.2 nm at 1550 nm) and a fast (10-micros) tuning capability with a continuous tuning range of approximately 50 nm is described. The tunable filter consists of an acousto-optic beam deflector with a diffraction grating whose grating vector is transverse to the direction of light propagation.

Acoustically steered and rotated true-time-delay generator based on wavelength-division multiplexing

The acoustically steered and rotated (ASTRO) true-time-delay (TTD) generator, capable of two-dimensional (2D) multiple beam generation without causing extraneous beams, is described. It is based on wavelength-division multiplexing to encode and decode various linear chirp time delays with wavelengths. An array of equally spaced light stripes with linear chirp time delays among them is formed and is subsequently rotated to a desired angle by use of our nonmechanical acousto-optic dove prism, believed to be novel. Our architecture reduces hardware complexity significantly by avoiding redundancy in conventional TTD generators. Experimental results to prove the concept of 2D multiple beam generation are shown. Also, an extension of the system for bidirectional communications is proposed. Various technical issues for practical applications are discussed.

Performance enhancement of a joint transform correlator using the directionality of a spatial light modulator

we observe that conventional electrically addressable spatial light modulators have different transfer functions along the fast (horizontal) and the slow (vertical) directions. We then propose to use the directionality of a spatial light modulator to increase the performance of a joint transform correlator. Our experimental results show that input space- bandwidth product of a joint transform correlator can be significantly increased by recording a hologram so that interference fringes run along the fast (horizontal) direction of a spatial light modulator.

Composite filter for Vanderlugt correlator

This paper examines the use of composite filters for improving the effectiveness of a Vanderlugt correlator when used for fingerprint identification. A digital simulation, which accounts for noise sources in the optical setup, is used to design and test composite matched spatial filters. Results are presented for a real time video image database containing 10 seconds of video from 200 fingers. Using the composite matched spatial filter the Vanderlugt correlator is getting 70% correct identifications with no false positives.

2D multiple beam steering with acoustically steered and rotated (ASTRO) true-time delay generator

Two-dimensional multiple beam steering in the Acoustically STeered and ROtated (ASTRO) true time delay generation architecture is described. The architecture is capable of generating 2D multiple beams without causing any extraneous beams. The system can be used as both transmitter and receiver modes simultaneously.

Acoustically steered and rotated (ASTRO) optoelectronic 2D true-time-delay generation

A new 2-D true time delay (TTD) generation system architecture for phased array antennas is described. The method uses fiber chirp gratings and acousto-optic beam deflectors. By combining free-space optics and guided optics, the device complexity in conventional TTD systems has been significantly reduced. A proof-of-concept experimental results are demonstrated.