Wiley Handbook of Science and Technology for Homeland Security, 4 Volume Set

NEW APPROACHES TO IRIS RECOGNITION: ONE-DIMENSIONAL ALGORITHMS

YINGZI DU

Indiana University-Purdue University Indianapolis, Indianapolis, Indiana

ROBERT W. IVES

United States Naval Academy, Annapolis, Maryland

DELORES M. ETTER

Southern Methodist University, Dallas, Texas

1 INTRODUCTION

The key step in many current iris pattern recognition algorithms is to transform the iris pattern into a two-dimensional code [1–3]. To eliminate the effect of eye tilt, circular rotation or area-based image registration of the iris pattern is usually necessary in iris matching and identification algorithms [1–3]. Generally, iris recognition systems require a cooperative subject [3] who willingly stares into a camera for a few seconds. The performance range (from subject to camera) of commercially available iris recognition systems is usually less than 2 ft [4]. Recently, Matey [5] from the Sarnoff Corporation has developed a remote iris recognition system, which can perform iris recognition up to 10 ft. As with other iris cameras, the user must look at the camera while moving toward it. The current functional speed is 1 m/s. Under these conditions, the iris image is obtained with the maximum amount of iris information. On the other hand, for a noncooperative subject, who may be facing away from the camera, only a portion of the iris information may be captured (a partial iris). Partial iris recognition algorithms would be very important in surveillance applications where capturing the entire iris ...