Title :
Using the beta-binomial distribution for the analysis of biometric identification
Author :
Gabor Á. Werner;László Hanka
Author_Institution :
Applied Biometric Institute, Ó
Abstract :
In this paper we presented a method which could be used in the testing process of biometric devices on the side of users and costumers. The failed events during the biometrical identification are more common than the literature data, however there isn´t any standard or widely accepted manual for the examinations. The conventional statistical methods use the binomial distribution to estimate the expected number of failure, but in the field of the biometrics the probability parameter can´t be constant which means that it is necessary to describe a process. Our results have shown that the probability is characterized with two parameters of the beta distribution, and these are predictable from a smaller sample of the investigated population with the maximum-likelihood method.
Keywords :
"Density functional theory","Sociology","Statistics","Approximation methods","Bayes methods","Fingerprint recognition"
Conference_Titel :
Intelligent Systems and Informatics (SISY), 2015 IEEE 13th International Symposium on
DOI :
10.1109/SISY.2015.7325381