User's guide to NIST biometric image software (NBIS)

Watson, Craig I.; Garris, Michael D.; Tabassi, Elham; Wilson, Charles L.; McCabe, R Michael; Janet, Stanley; Ko, Kenneth

doi:10.6028/nist.ir.7392

Cited by 154 publications

(188 citation statements)

References 8 publications

Supporting

Mentioning

184

Contrasting

Unclassified

Order By: Relevance

“…• The NIST (National Institute for Standards and Technology) Fingerprint Image Quality (NFIQ) algorithm 3 [23]: an open source tool that has become the 2 In the rest of the text, we will be using the abbreviations (D0-D3) to refer to these four respective devices. The same instance of each device were used throughout the data collection.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Interoperability between Fingerprint Biometric Systems: An Empirical Study

Mason

Gashi

Lugini

et al. 2014

2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks

View full text Add to dashboard Cite

Abstract-Fingerprints are likely the most widely used biometric in commercial as well as law enforcement applications. With the expected rapid growth of fingerprint authentication in mobile devices their importance justifies increased demands for dependability. An increasing number of new sensors, applications and a diverse user population also intensify concerns about the interoperability in fingerprint authentication. In most applications, fingerprints captured for user enrollment with one device may need to be "matched" with fingerprints captured with another device. We have performed a large-scale study with 494 participants whose fingerprints were captured with 4 different industry-standard optical fingerprint devices. We used two different image quality algorithms to evaluate fingerprint images, and then used three different matching algorithms to calculate match scores. In this paper we present a comprehensive analysis of dependability and interoperability attributes of fingerprint authentication and make empirically-supported recommendations on their deployment strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

“…, a minutiae based fingerprint matcher developed by NIST [23]; • (M3) BIO-key WEB-key Software Development Kit 5 . In the rest of the text, we will be using the abbreviations M1, M2 and M3 to refer to these three matching algorithms.…”

Section: Methodsmentioning

confidence: 99%

Interoperability between Fingerprint Biometric Systems: An Empirical Study

Mason

Gashi

Lugini

et al. 2014

2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks

View full text Add to dashboard Cite

show abstract

“…The parameters for orientation distributions are obtained using expectation maximization for the von Mises distribution [29]. The estimates of ν mk and κ mk at the (n + 1)th iteration are given by…”

Section: M-mentioning

confidence: 99%

Generative Models and Probability Evaluation for Forensic Evidence

Srihari

2011

Pattern Recognition, Machine Intelligence and Biometrics

View full text Add to dashboard Cite

Generative approaches to pattern recognition and machine learning involve two aparts: first describing the underlying probability distributions and then using such models to compute probabilities or make classificatory decisions. We consider generative models for forensic evidence where the goal is to describe the distributions using graphical models and to use such models to compute probabilistic metrics for measuring the degree of individuality of a forensic modality or of a piece of evidence. The metrics are defined as variations of the probability of random correspondence (PRC) when evidence consists of a set of measurements and correspondence is within a tolerance. Three metrics are defined, the first two of which concern the modality and the third concerns evidence: 1) PRC of two samples, 2) PRC among a random set of n samples (nPRC), and 3) PRC between a specific sample among n others (specific nPRC). Computation of these probabilities are described using graphical models which makes all the variables explicit. The metrics are evaluated for several cases-some of which are illustrative (birthdays and heights) and others concern fingerprints. For birthdays, which are discretevalued and exact, assuming uniformly distributed birthdays, while nPRC rapidly approaches unity with higher n (which is the well-known birthday paradox), specific nPRC grows much less rapidly. For human heights, which are continuous-valued scalars, a quantization is needed and results are genderspecific: assuming Gaussian distributed heights, the PRC for males is higher than for females due to lower variance. Two forms of fingerprint representation are considered: ridge flow and minutiae. Gaussian mixtures are used to model location and orientation of minutiae. With parameters estimated from standard databases (using expectation maximization), fingerprint PRCs are determined for given numbers of available and matching minutiae (which correspond to quantization), for the case of 36 available minutiae where 24 of them match, the PRC is 4.0 × 10 −34 . The methodology put forward should be value to establish the relative value of different types of forensic evidence in courtroom scenarios.

show abstract

“…If a minutia is located in a block with the highest ridge quality as indicated by NBIS [23] (i.e., quality level of 4), the 48 × 48 image patch centered at the minutia and aligned along the minutia direction is cropped.…”

Section: Minutiae Dictionary Learningmentioning

confidence: 99%