High confidence visual recognition of persons by a test of statistical independence-英文文献.pdf

1148 IEEE TRANSACTIONS ON PA’ITERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 15,NO. 11, NOVEMBER 1993 High Confidence Visual Recognition of Persons by a Test of Statistical Independence John G. Daugman Abstruct- A method for rapid visual recognition of personal well as some of the numerous geometric facial measurements identity is described, based on the failure of a statistical test of currently being tried, are described in [17], [25]. independence. The most unique phenotypic feature visible in a Today there is renewed interest in reliable, rapid, and 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 unintrusive means for automatically recognizing the identity reveals variation corresponding to several hundred independent of persons. Security breaches in access to restricted areas at degrees-of-freedom. Morphogenetic randomness in the texture airports are known to have contributed to terrorism; and credit expressed phenotypically in the iris trabecular meshwork ensures card fraud now costs six billion dollars annually [3]. Other that a test of statistical independence on two coded patterns applications for high confidence personal identification include originating from different eyes is passed almost certainly, whereas the same test is failed almost certainly when the compared codes passport control, bank automatic teller machines, protected originate