DMCA
High confidence visual recognition of persons by a test of statistical independence (1993)
| Venue: | IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
| Citations: | 621 - 8 self |
BibTeX
@ARTICLE{Daugman93highconfidence,
author = {John G. Daugman},
title = {High confidence visual recognition of persons by a test of statistical independence},
journal = {IEEE TRANS. ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE},
year = {1993},
volume = {15},
number = {11}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence. The most unique phenotypic feature visible in a person’s face is the detailed texture of each eye’s iris: An estimate of its statistical complexity in a sample of the human population reveals variation corresponding to several hundred independent degrees-of-freedom. Morphogenetic randomness in the texture expressed phenotypically in the iris trabecular meshwork ensures that a test of statistical independence on two coded patterns originating from different eyes is passed almost certainly, whereas the same test is failed almost certainly when the compared codes originate from the same eye. The visible texture of a person’s iris in a real-time video image is encoded into a compact sequence of multi-scale quadrature 2-D Gabor wavelet coefficients, whose most-significant bits comprise a 256-byte “iris code. ” Statistical decision theory generates identification decisions from Exclusive-OR comparisons of complete iris codes at the rate of 4000 per second, including calculation of decision confidence levels. The distributions observed empirically in such comparisons imply a theoretical “cross-over ” error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates. In the typical recognition case, given the mean observed degree of iris code agreement, the decision confidence levels correspond formally to a conditional false accept probability of one in about l0^31.
Keyphrases
statistical independence high confidence visual recognition statistical decision theory decision confidence level biometric identification person iris texture analysis exclusive-or comparison personal identity conditional false accept probability index term image analysis detailed texture typical recognition case 256-byte iris code independent degrees-of-freedom unique phenotypic feature most-significant bit visible texture theoretical cross-over error rate statistical complexity statistical test rapid visual recognition iris trabecular meshwork eye iris real-time video image human population reveals false accept statistical pattern recognition identification decision morphogenetic randomness false reject error rate iris code agreement complete iris code different eye compact sequence 2-d gabor filter decision criterion person face
