基于线性模板和模糊规则的虹膜坑洞纹理检测

Iris crypt texture detection based on linear template and fuzzy rules

基于虹膜表面特定形状纹理的虹膜识别方法是虹膜识别的一种有效手段。然而,由于虹膜纹理复杂多样,形态各异,因此如何快速、准确地检测出虹膜表面各种不同类型的特征纹理仍然是目前亟待解决的一个难题。针对坑洞纹理的检测,提出一种基于定长线性模板和模糊规则的虹膜坑洞纹理的检测方法,首先使用一个定长的线性模板提取出虹膜表面所有纹理的边缘。然后,根据坑洞纹理与其他类型的纹理在形状上存在的不同,定义相应的模糊规则,从各种不同类型的纹理中识别出坑洞纹理。该算法对图库中人工标定的坑洞纹理检测的正确率为86.06%;对色素斑、裂缝以及眼睑的排除率分别为84.62%,71.56%,100%。实验结果表明,该方法能够从背景复杂的可见光虹膜图像中识别出坑洞纹理,为虹膜的特征提取提供了一个新的思路。

Iris detection method based on specific shape textures on the iris surface is a kind of effective iris identification method. Due to the facts that iris textures are very complex and have many different kinds of shapes,by now,how to fast and accurately detect all different kinds of feature textures is still a challenging task to be solved. Aiming at the issue of crypt texture detection,an iris crypt texture detection method based on fixed- length linear template and fuzzy rules is proposed in this paper. Firstly,a fixed-length linear template is applied to extract all the edges of all specific shape textures on the iris surface. And then,according to the differences between crypt textures and other kinds of textures in shape,a series of fuzzy rules are defined to detect the crypt textures from all kinds of different types of textures. To test the performance of this method,the method was used to detect the crypts that were artificially marked in our image gallery,and the detection accuracy is 86. 06%; the exclusion accuracies of pigmentary patch,furrow and eyelid are 84. 62%,73. 34% and 100%,respectively. The experiment results show that the proposed method can detect the crypt textures from the visible iris images with complex background and provides a new idea for iris feature extraction.