Stand-off Iris Recognition System

Abstract

The iris is a highly accurate biometric identifier. However widespread adoption is hindered by the difficulty of capturing high-quality iris images with minimal user cooperation. This paper describes a first-generation prototype iris identification system designed for stand-off cooperative access control. This system identifies individuals who stand in front of and face the system after 3.2 seconds on average. Subjects within a capture zone are imaged with a calibrated pair of wide-field-of-view surveillance cameras. A subject is located in three dimensions using face detection and triangulation. A zoomed near infrared iris camera on a pan-tilt platform is then targeted to the subject. The iris camera lens has its focal distance automatically adjusted based on the subject distance. Integrated with the iris camera on the pan-tilt platform is a near infrared illuminator that is composed of an array of directed LEDs. Video frames from the iris camera are processed to detect and segment the iris, generate a template and then identify the subject.

Enhancing Iris Matching Using Levenshtein Distance with Alignment Constraints

“…While iris recognition in reasonably constrained environments provides high confidence authentication with equal error rates (EERs) of less that 1% [1], a reduction of constraints is quite challenging. First-generation prototype iris identification systems designed for stand-off video-based iris recognition, e.g Sarnoff's Iris-on-the-move [2], or General Electric's Stand-off Iris Recognition system [3], have proven the feasibility of iris recognition from surveillance-type imagery. But also the need for better segmentation techniques than usually applied in still-image iris recognition to account for distortions like motion blur, defocusing or off-axis gaze direction has been identified as a main issue.…”

A Selective Feature Matching Approach for Iris Recognition

“…Compared with the stored template of iris, the Euclidean distance between the two corresponding global iris features vector is obtained. The Euclidean distance gives a measure of how similar a collection of values is between two templates as given in (13). Zero distance implies a perfect match, and signature tends towards mismatch as the distance increases.…”

“…The approximate and detail coefficients obtained by discrete wavelet transform [21,22] of image f(x, y) of size M x N is then given in (8) with scaled and translated basis functions are given as in (9).…”

“…Matching was performed using Hamming and Euclidean distance algorithms. To narrate a few more issues on the recognition system advancement, F M Wheeler et al [13] proposed the standoff iris recognition technique. Here a dual iris approach was adopted for feature details extraction and Hamming code has been used for matching purpose.…”

Iris Recognition Using Ridgelets

“…The database used in this work is both the Chinese Academy of Sciences-Institute of Automation-CASIA (Version 1 and Version 3) database and the UPOL database [42][43][44][45][46][47][48]. The Chinese Version 1 database used in the experimentation consists of 756 different iris images from the CASIA iris image database [7].…”