基于局部频率特征和局部方向特征的虹膜识别算法

An Iris Recognition Algorithm Combining Local Frequency Features with Local Orientation Features

描述了一种不同于现有方法的新颖虹膜识别算法,利用多尺度多方向的二维奇对称Gabor滤波器,同时提取虹膜纹理的局部频率特征和局部方向特征.这种方法更全面的描述了虹膜纹理的特征空间,克服了之前的虹膜识别算法只提取局部频率特征或者只提取局部方向特征的局限性.特征匹配采用类似加权市街距离的方法来进行,而且根据眼睑和睫毛的分布特点设计匹配模板,能够最大限度的减少它们对匹配的干扰.与Daugman算法进行对比的实验数据表明,本算法具有非常优越的识别性能.

Unlike other already existed iris recognition algorithms,a new efficient algorithm for iris recognition is proposed. In this approach, a bank of multi-scale and multi-orientation odd symmetric Gabor filters are used to capture local frequency informarion and local orientation information of the iris so as to produce discriminating feature. This Algorithm can represent the feature spatial patterns of the iris more comprehensively and avoid the disadvantage caused by only capturing local frequency features or local orientation features. The method of iris matching is similar to a method computing the adopted city block distance, moreover according to the eyelid and eyelash＇ s distribution, a matching template is used to reduce their disturbance to minimum. Compared with the Daugman＇ s method,extensive experimental results demonstrate that the proposed method has an encouraging recognition performance.