介绍了一种活体虹膜的定位与分割算法。算法主要分为两部分:圆环的定位与非虹膜区域的去除。本算法根据眼睛的生理特点和数字虹膜图像的实际情况,利用传统定位方法与数学形态学相结合对虹膜区域进行快速而准确的定位,并分别提出了去除眼睑、睫毛和光斑影响的解决方案。算法中也考虑到实际应用可能遇到的影响虹膜定位与分割的问题。实验表明,该算法取得较好的分割结果,并且具有鲁棒性。
The iris localization and the segmentation are a critical stage in the whole iris recognition process. The procedure of live iris localization and segmentation is presented based on the natural properties of the iris. The proposed procedure consists of two main steps: circles localization and non-iris region detection (including eyelids, eyelashes and reflection spots). In this method, some typical problems appeared in practice are considered, such as the eye shape or makeup. Experiments show that the method can achieve good results and has robustness.