一种序列虹膜图像的综合质量评价研究  

A Study on an Integrated Quality Assessment of Sequence Iris Image

作　　者：张立云[1] 黄健[1] 薛征宇[1] 赵欣[1] 

机构地区：[1]大连海事大学,辽宁大连116026

出　　处：《计算机技术与发展》2009年第11期104-107,共4页Computer Technology and Development

摘　　要：虹膜识别是身份识别最可靠的方法之一,近些年来已经引起了广泛的关注,并且取得了相应的成果,然而在识别速度和准确率方面,很难做到两全其美,而序列虹膜图像的质量评估则使解决此瓶颈成为可能。文中在对现有序列虹膜图像质量评价算法的基础上,提出了一种综合的序列虹膜图像质量评价算法,该算法包含3个部分:虹膜活体检测、虹膜有效区域的确定以及虹膜图像清晰度检测。实验结果表明,该方法能够有效地筛选出符合要求的虹膜图像,并且相应地提高了虹膜识别正确率。Iris recognition is one of the most reliable methods for personal identification in recent years,which has received increasing attention and obtained the corresponding results, however, in recognition speed and accuracy, it is difficult to achieve the best of both worlds, the sequence iris image quality assessment makes it possible to resolve this bottleneck. On the base of sequence iris image quality evaluation in existence, proposing a algorithm of integrated sequence iris image quality, which includes three parts live detection of iris, iris effective area calculating as well as definition evaluation. The experimental results indicate that the iris image with high quality can be picked out effectively and correspondingly improve the accuracy rate of the iris recogrfition.

关 键 词：质量评价 活体检测 睫毛检测 眼睑检测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]