Improved identification of iris and eyelash features

Abstract

This paper proposes a novel algorithm to improve localization and segmentation of an iris image. Since in many practical applications, user cooperation is not possible, eyelash occlusion can seriously affect the performance of an iris recognition system. This paper discusses a robust method for accurate localization and segmentation of the exact iris region without eyelash occlusion.Our algorithm uses a logarithmic image enhancement technique and the Hough transform for iris localization as well as an intensity gradient based method for eyelash detection using local region statistics of the image. Experimental results show the accuracy of our algorithm leading to exact iris region segmentation. INTRODUCTIONProper Iris segmentation is essential for various security applications using iris recognition technology for personal identification [1]. Irises are occluded by the eyelid and eyelashes as well as from specular reflections from the (typically infra-red) illumination system. In order to accurately process the image, it is important to identify such occluded regions to remove them from further processing. Inaccurate detection of these occlusions reduces considerably the performance of an iris-based identification system when subject cooperation is not possible. Cooperative users can be asked to stand still for multiple image acquisitions, while for Iris On the Move [11] or covert surveillance applications (i.e. in airport security) such cooperation is not available. This will greatly affect the localization of the iris inner and outer boundaries as well as it will degrade the iris feature extraction process. For this reason, exact eyelash detection and segmentation is required to improve the entire biometrics system's accuracy and avoiding poor recognition performance. In this paper we develop an algorithm for accurate iris segmentation in images where the major portion of the iris is occluded. Our algorithm detects separable and multiple eyelashes, respectively. Separable eyelashes are first detected using a local intensity variation based algorithm while multiple eyelashes are found using the block mean and variance approach. Various methods have been proposed for eyelash detection [2, 3, 4, 5] which uses 1-D Gabor filter, intensity variance, phase congruency, template mean, standard deviation for multiple eyelash detection and a local intensity minimum method for separable eyelash detection. All these methods perform generally quite well but do suffer from some limitations such as computational complexity, inexact iris boundaries segmentation, false eyelash detection and improper eyelash segmentation over the iris region. Specifically, all previous approaches tend to overestimate the occluded regions, and thus lose iris information that could be used for identification. This information loss is potentially important in the covert surveillance applications we consider in this paper. For this reason, the proposed method addresses all these issues using a collection of image processing techniques such a...

Comparison of Color and Texture for Iris Recognition

“…Wildes et al, 46 represented iris texture with a Laplacian pyramid constructed with four di®erent resolution levels. They used normalized correlation to determine the 45 Zhifang et al, 49 Frederick et al, 24 Xueyi et al, 47 Youmaran et al, 48 Li et al, 28 Sheikh and Matthew, 40 Jinyu and Schimd, 26 proposed di®erent algorithms. Feng et al, 22 proposed a novel method called classi¯er combination and its application in iris recognition, for matching.…”

Evaluación del impacto del preprocesamiento de imágenes en la segmentación del iris

“…Como paso previo a la segmentación, algunos autores utilizan una etapa de preprocesamiento de la imagen adquirida con el fin de mejorar, principalmente, el contraste de la imagen y resaltar los bordes de la misma. Es así como en [3], [12] ponen aplicar un filtrado de la imagen del tipo Gaussiano, en [13] se sugiere realizar una ecualización local del histograma, en [5] se aplica una mejora de contraste basada en la normalización de los valores en la escala de grises para cada pixel y en [2], [5] y [12] se propone suprimir los reflejos especulares como mejora de la imagen y etapa previa a la segmentación, argumentando que estos reflejos son una de las causas de errores en sistemas de reconocimiento del iris. Sin embargo, esta etapa previa de preprocesamiento no se incluye en la mayoría de las publicaciones relacionadas con reconocimiento del iris, y tampoco se evidencia un estudio que compare diferentes algoritmos de preprocesamiento de la imagen y su impacto en la etapa de segmentación en los sistemas de reconocimiento biométrico basados en el patrón del iris.…”