BIOMETRIC PERSONAL IDENTIFICATION SYSTEM BASED ON IRIS ANALYSIS

摘要

Image analysis algorithms find the iris in a live video image (10) of aperson's face, and encode its texture into an "iriscode" (24). Iris texture is extracted from the image at multiple scales ofanalysis by a self-similar set of quadrature bandpassfilters defined in a dimensionless polar coordinate system. The sign of theprojection of many different parts of the iris onto thesefilters determines each bit in an iris code. Comparisons between codes arereadily implemented by the Exclusive-OR (XOR) logicaloperation. Pattern recognition is achieved by combining signal processingmethods with statistical decision theory, leading toa statistical test of independence based on a similarity metric (Hammingdistance) (26) that is computed from the XOR of anytwo iris codes. This measure positively establishes, confirms, or disconfirms,the identity of any individual (28). It also generatesan objective confidence level (30) associated with the identificationdecision.