基于分数维的虹膜身份信息稳健识别方法仿真  

Simulation of Robust Iris Identification Method Based on Fractal Dimension

作　　者：涂娟[1] TU Juan(Xihua University,Chengdu Sichuan 610039,China)

机构地区：[1]西华大学,四川成都610082

出　　处：《计算机仿真》2021年第8期430-434,共5页Computer Simulation

摘　　要：针对现有虹膜身份信息稳健识别方法存在识别准确率低、识别速率差的缺陷,提出了一种基于分数维对虹膜身份信息稳健识别方法。采用Gaussian模板对虹膜图像进行平滑处理,根据微分法对采集的虹膜图像进行锐化预处理;依据灰度级分布函数获得灰度直方图,通过灰度差分法对虹膜图像内、外边界进行定位,并实现尺寸与光照的归一化处理,获得虹膜基础图像;采用二维Gabor滤波器对虹膜图像特征进行提取,利用加权融合匹配算法对特征进行匹配运算,实现虹膜身份信息稳健识别。通过仿真得到,与现有的三种虹膜身份信息稳健识别方法相比较,提出的虹膜身份信息稳健识别方法极大的提升了识别准确率与速率,充分说明提出的虹膜身份信息稳健识别方法具备更好的识别性能。Due to low recognition accuracy and poor recognition rate in current iris information identification methods,a robust identification method of iris identity information based on fractal dimension was proposed.The Gaussian template was used to smooth the iris image,and the iris image was sharpened by the differential method.The gray histogram was obtained by the grayscale distribution function.The inner and outer boundaries of the iris image were located by the gray difference method.Meanwhile,the size and illumination were normalized to obtain the basic iris image.A two-dimensional Gabor filter was used to extract iris image features.Moreover,the weighted fusion matching algorithm was used to match the features,so as to realize the robust recognition of iris identity information.Following conclusions can be drawn from the simulation experiment.Compared with the existing methods,the proposed method greatly improves the accuracy and speed of identification.The proposed method has better identification performance.

关 键 词：分数维 虹膜 身份 信息 识别 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]