Iris recognition: an emerging biometric technology

Abstract

This paper examines automated iris recognition as a biometrically based technology for personal identification and verification. The motivation for this endeavor stems from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric assessment. In particular, the biomedical literature suggests that irises are as distinct as fingerprints or patterns of retinal blood vessels. Further, since the iris is an overt body, its appearance is amenable to remote examination with the aid of a machine vision system. The body of this paper details issues in the design and operation of such systems. For the sake of illustration, extant systems are described in some amount of detail.

UBIRIS: A Noisy Iris Image Database

“…This methodology was included on the analysis essentially to represent several approaches on iris segmentation literature. In fact, several other authors propose minor variants to the Wildes [26] method, essentially to adjust the process to different image intensities and contrasts. Liam and Chekima's method This iris segmentation approach [16], is based on the fact that the pupil is typically darker than the iris and the iris darker than the sclera.…”

“…This method was chosen because, although it was proposed about 11 years ago, it remains as one of the most referred on iris segmentation literature and was the first methodology effectively implemented in a working biometric system [8]. Wildes method Proposed in 1997, this methodology performs iris contour fitting in two steps [26]. First, the image intensity information is converted into a binary edge map.…”

“…This fact can obviously constitute one weak point as we are concerned with robustness, which includes the ability to deal with heterogeneous image contrast and intensities. Masek's method Based on the methodology suggested on [26], this author proposes a method [20] that begins with the binary edge image map construction, using the Kovesi [15] edge detector, a variation of the well known Canny [2] edge detector. The next step consists in applying the circular Hough transform in order to determine the iris/sclera border and then the one correspondent to iris/pupil.…”

“…This operator remains actual and was proposed with some minor differences in 2004 by [23]. Wildes [26] proposes iris segmentation through a gradient based binary edge map construction followed by circular Hough transform. This methodology is the most widely used, being proposed with minor several variants in [3], [11], [14], [17], [19], [18] and [20].…”

A New Iris Identification Method Based on Ridgelet Transform

“…Boles and Boashash [3] used zero crossing point of 1-D wavelet at different levels on same center circle of the iris and pupil centralism. Wildes [4] used Laplace pyramid with four various resolution levels to range and normalize correlation for comparison between input image and database images. Ma et al [5] steps decomposition.…”