一种基于小波变换的虹膜识别方法

An Iris Recognition Method Based On Wavelet Transform

虹膜上的纹理或结构的差异 ,是不同虹膜相互区别的最主要原因和体现。因此 ,要想获得很高的识别率 ,就必须运用虹膜图像的边缘信息。利用二维小波变换 ,构造出了一种新的虹膜识别方法。该方法的基本思想是 :对于小波多层分解的低频分量 ,用一种变形的互相关方法由粗到精地进行匹配 ,以筛选出少数匹配较好的虹膜图像 ;然后在第一级小波分解的边缘分量上提取图像边缘 ,并用一种新的基于边缘特征的距离量度对筛选出的虹膜图像进行最终识别。与国外的虹膜识别方法相比 ,该方法把全局特征与局部特征很好地结合起来 。

Irises can be distinguished mainly due to textural or structural difference among them.In order to acquire a high recognition probability,the edge information of iris images must be employed.A new iris recognition method is presented by taking advantages of 2 D wavelet transform.The basic principle of the method is as follows.For the low frequency components of multiresolution decomposition,an improved correlation approach is adopted for image match stage by stage so that a few well matched iris images are picked out.The edge components of the first wavelet transform stage are then used for image edge detection and a new distance measurement is defined for final match.Compared with other iris recognition methods,our method combines global features with local features very well and uses image edge information more efficiently.