Craig I. Watson

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.

IREX III - Performance of Iris Identification Algorithms

Disclaimer Specific hardware and software products identified in this report were used in order to perform the evaluations described in this document. In no case does identification of any commercial product, trade name, or vendor, imply recommendation or endorsement by the National Institute of Standards and Technology, nor does it imply that the products and equipment identified are necessarily the best available for the purpose.

Distortion-Tolerant Filter for Elastic-Distorted Fingerprint Matching

This paper gives results for using distortion tolerant filters to improve performance of fingerprint correlation matching. Three types of distortion tolerant filters were tested: summation, weighted, and MINACE. A set of 55 fingers were used from NIST Special Database 24 to evaluate the filters. Our results show performance was improved from 49% correct, using one training fingerprint, to 100% correct, using multiple training fingerprints, and a distortion- tolerant MINACE filter, with no false alarms.

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.

Modest proposals for improving biometric recognition papers

We present practical recommendations for improving the clarity, transparency, and usefulness of many biometric papers. Several of the recommendations can be enabled by preparing a publicly available library of state of the art Receiver Operating Characteristics (ROCs). We propose such a library and invite suggestions on its details.

Recognition of live-scan fingerprints with elastic distortions using correlation filters

A special NIST database of live-scan fingerprints with elastic distortion was prepared. It is used to evaluate the effect of elastic and other distortions on correlation filters. The need for normalized and finely or coarsely rotationally aligned data is addressed, and performance gains for various cases noted.

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.

Fingerprint Matching Using Distortion Tolerant Filters

This chapter shows how using distortion-tolerant filters can significantly improve correlation fingerprint matchers. Filters are built by combining several elastic distorted variations of the fingerprint into a single matched filter. The three techniques tested for making the distortion-tolerant filters are averaging, synthetic discriminate function, and minimum average noise and correlation plane energy filters. A data set containing 200 fingers is used for evaluation. Receiver operator curves show that distortion-tolerant filters are a significant improvement compared to a single-finger filter in correlation matching.

Correlation filters for recognition of live-scan fingerprints with elastic distortions

A special NIST database of live-scan fingerprint with elastic distortion wa prepared. It is used to evaluate the effect of elastic and other distortions on correlation filters. The need for normalized and fine vs. coarse rotationally-aligned data are addressed with performance gains for various cases noted. Procedures to test and evaluate fingerprint recognition algorithms for verification and identification are defined for the first time and initial results are presented.

Performance of electrically addressed spatial light modulators

The measurement of two important performance limitations of commonly available spatial light modulations is addressed. A method for the determination of modulation transfer function and amplitude modulation from CCD captures of imaged gratings is presented. An interferometric technique is employed for estimating spatial non-uniformities and optical non-flatness of a liquid crystal panel.