基于主动轮廓线的虹膜内边界的定位方法

New method of interior boundary of iris location based on active contour

在图像中虹膜位置的有效定位是虹膜识别的关键问题。用一种基于主动轮廓线的方法定位虹膜内边界,先用灰度投影法检测出瞳孔内的一点作为瞳孔的伪圆心,不要求该点一定在瞳孔中心附近,只要能落在瞳孔内部即可;然后以该点为中心,在其周围等间隔地取几个点作为初始的snake,按照snake的运行机制不断进化,直到虹膜的内边界为止;最后,计算进化后的snake形心和snake上的控制点与该形心的距离,取其平均值作为瞳孔的半径,形心作为瞳孔的圆心,即可准确定位出虹膜内边界的位置。实验表明,与常见的定位方法———Hough变换和Daugman的圆形检测算子相比,文中的方法速度快、精度高,而且,对瞳孔初始的伪圆心要求不高,鲁棒性更强。

The key problem in iris recognition is how to locate iris's position in an image. A new method of interior boundary of iris location based on active contour is presented. Firstly, a point in pupil called pseudo-center, which isn't required to be located at the real center of pupil, is detected by a method of gray projection. Secondly, several points spaced evenly around the pseudo-center are chosen as initial snake, and then the snake evolves until it gets the interior boundary of iris. Finally, two values are computed --one is the real center of pupil, which is expressed through the center of snake, and the other is the radius of pupil, the average distances between every control point of snake and the center. Experiments show that our method has better performance in speed and precision than Hough transform and daugman method. Moreover, our method is more robust because the pseudo-center is not rigorous.