{"title":"A new effective algorithm for iris location","authors":"Lijun Zhou, Yide Ma, Jing Lian, Zhaobin Wang","doi":"10.1109/ROBIO.2013.6739727","DOIUrl":null,"url":null,"abstract":"Iris location is an essential step and an important part in an iris recognition system. However, traditional iris location methods often involve a large space of search, which is calculation wasting and sensitive to noise. And these methods adopt circular orientation to locate the pupillary boundary; it may lead to inaccurate location result and influence the subsequent feature extraction and recognition. To address these problems, this paper presents a precise iris location algorithm based on Vector Field Convolution (VFC, an improved Snake model) to improve the accuracy of iris location. Firstly, obtaining the iris area completely include the inside and outside boundary from an original iris image, then using minimum average grey value method to determine initialization contour of VFC model automatically, so as to locate an iris inner boundary precisely under the internal and external force of active contour. At last, we adopt the improved Daugman algorithm to locate the iris outer boundary that relatively contains little texture information. Experimental results show that the location accuracy of this method is higher, the iris inner edge location is much closer to the real boundary, the result of location have been improved significantly.","PeriodicalId":434960,"journal":{"name":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBIO.2013.6739727","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
Iris location is an essential step and an important part in an iris recognition system. However, traditional iris location methods often involve a large space of search, which is calculation wasting and sensitive to noise. And these methods adopt circular orientation to locate the pupillary boundary; it may lead to inaccurate location result and influence the subsequent feature extraction and recognition. To address these problems, this paper presents a precise iris location algorithm based on Vector Field Convolution (VFC, an improved Snake model) to improve the accuracy of iris location. Firstly, obtaining the iris area completely include the inside and outside boundary from an original iris image, then using minimum average grey value method to determine initialization contour of VFC model automatically, so as to locate an iris inner boundary precisely under the internal and external force of active contour. At last, we adopt the improved Daugman algorithm to locate the iris outer boundary that relatively contains little texture information. Experimental results show that the location accuracy of this method is higher, the iris inner edge location is much closer to the real boundary, the result of location have been improved significantly.
虹膜定位是虹膜识别系统的关键步骤和重要组成部分。然而,传统的虹膜定位方法往往涉及较大的搜索空间,计算浪费大和对噪声敏感。这些方法均采用圆形定向定位瞳孔边界;这可能导致定位结果不准确,影响后续的特征提取和识别。针对这些问题,本文提出了一种基于矢量场卷积(Vector Field Convolution, VFC,一种改进的Snake模型)的精确虹膜定位算法,以提高虹膜定位的精度。首先从原始虹膜图像中获得完整的包括内外边界的虹膜区域,然后利用最小平均灰度法自动确定VFC模型的初始化轮廓,从而在活动轮廓的内外作用下精确定位虹膜内边界。最后,采用改进的道格曼算法对纹理信息相对较少的虹膜外边界进行定位。实验结果表明,该方法的定位精度较高,虹膜内缘定位更接近真实边界,定位结果有明显改善。