Validating a Biometric Authentication System: Sample Size Requirements

@article{Dass2006ValidatingAB,
  title={Validating a Biometric Authentication System: Sample Size Requirements},
  author={Sarat Chandra Dass and Yongfang Zhu and Anil K. Jain},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2006},
  volume={28},
  pages={1902-1319}
}
Authentication systems based on biometric features (e.g., fingerprint impressions, iris scans, human face images, etc.) are increasingly gaining widespread use and popularity. Often, vendors and owners of these commercial biometric systems claim impressive performance that is estimated based on some proprietary data. In such situations, there is a need to independently validate the claimed performance levels. System performance is typically evaluated by collecting biometric templates from n… 
Investigating and Comparing Multimodal Biometric Techniques
TLDR
This technical paper will investigate and compare multimodal biometric techniques, in order to determine how much of an advantage lies in using this technology, over its unimodal equivalent.
Secure Operation of Biometric Authentication Based on User’s Viewpoint
TLDR
A secure operation model for biometric authentication that features cooperation between an Identity Provider (IDP) and hashing of biological information is proposed and results of desk simulation assuming a specific service environment demonstrated the effectiveness of the proposed model.
The poor man's biometric: Identifying cost-effective biometric system criteria for SMMEs
TLDR
A biometric selection process is defined and evaluation criteria that are relevant to their unique environments are identified, which should aid in the decision-making process in low cost environments, and recommendations such as need assessment, vendor awareness, standard conformance, independent evaluations and the reduction of system modularity are presented.
The poor man's biometric: Identifying cost-effective biometric system criteria for SMMEs
TLDR
A biometric selection process is defined and evaluation criteria that are relevant to their unique environments are identified, which should aid in the decision-making process in low cost environments, and recommendations such as need assessment, vendor awareness, standard conformance, independent evaluations and the reduction of system modularity are presented.
Biometric System and Data Analysis: Design, Evaluation, and Data Mining
TLDR
Biometric System and Data Analysis: Design, Evaluation, and Data Mining brings together aspects of statistics and machine learning to provide a comprehensive guide to evaluating, interpreting and understanding biometric data.
Multimodal Biometric Person Authentication : A Review
TLDR
An overview of some performance parameters and error rates for biometric person authentication systems is presented, and the importance of information fusion in multi-biometric approach is considered.
From Single Biometrics to Multi-Biometrics
TLDR
This chapter describes a number of definitions on biometrics, categories and fusion strategies of multi-biometrics as well as the performance evaluation on the biometric system.
Retinal Verification Using a Feature Points-Based Biometric Pattern
TLDR
An efficient method for persons authentication is showed, a deep analysis of similarity metrics performance is presented and a set of feature points representing landmarks in the retinal vessel tree of the biometric system is described.
Fingerprint-Based Recognition
TLDR
The purpose of this article is to give an overview of fingerprint-based recognition and discuss research opportunities for making these systems perform more effectively.
Probabilistic models for multi-classifier biometric authentication using quality measures
TLDR
This thesis uses probabilistic approaches at all stages of the biometric authentication processing chain, while taking into account the quality of the signal being modelled, using the theoretical framework of Bayesian networks, a family of graphical models offering important flexibility.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
Technical Testing and Evaluation of Biometric Identification Devices
TLDR
This chapter discusses the general approach to application-dependent, decision-policy independent testing and reporting of technical device performance and gives an example of one practical test.
Evaluation techniques for biometrics-based authentication systems (FRR)
TLDR
This paper systematically study and compare parametric and nonparametric (bootstrap) methods for measuring confidence intervals and gives special attention to false reject rate estimates.
Error analysis of pattern recognition systems - the subsets bootstrap
Guide to Biometrics
TLDR
This complete, technical guide details the principles, methods, technologies, and core ideas used in biometric authentication systems and defines and explains how to measure the performance of both verification and identification systems.
On-Line Fingerprint Verification
TLDR
An improved version of the minutia extraction algorithm proposed by Ratha et al. (1995), which is much faster and more reliable, is implemented for extracting features from an input fingerprint image captured with an online inkless scanner and an alignment-based elastic matching algorithm has been developed.
Using the Beta-Binomial Distribution to Assess Performance of a Biometric Identification Device
TLDR
The Beta-binomial distribution can be used to assess the variability in estimates of the false match and the false non-match rates when multiple users are tested more than once and this method accounts for the extraneous variability in this scenario and allows for the creation of confidence intervals under certain regularity conditions.
Efficient evaluation of classification and recognition systems
  • R. Micheals, T. Boult
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
TLDR
It is shown how a set of previously overlooked replicate statistics tools can be used to obtain tighter confidence intervals of evaluation estimates while simultaneously reducing the amount of data and computation required to reach such sound evaluatory conclusions.
A nonparametric statistical comparison of principal component and linear discriminant subspaces for face recognition
TLDR
This work extends FERET by considering when differences in recognition rates are statistically distinguishable subject to changes in test imagery and makes the source code for the algorithms, scoring procedures and Monte Carlo study available in the hopes others will extend this comparison to newer algorithms.
Best practices in testing and reporting performance of biometric devices.
The purpose of this document is to summarise the current understanding of the biometrics community of the best scientific practices for conducting technical performance testing towards the end of
Multivariate Statistical Methods
TLDR
This book is well intentioned for science majors, but it seems to miss the mark by being overly complicated with the unnecessary use of calculus on one hand and the recommendation of some poor statistical techniques on the other hand.
...
1
2
3
...