基于极坐标特征的改进模糊C-均值虹膜定位算法

Improved FCM Algorithm Based on Polar Coordinates Transformation for Iris Location

针对非理想情况下虹膜图像定位失败的问题,提出一种新的虹膜定位算法.该算法先使用基于极坐标特征的改进模糊C-均值算法对虹膜外圆半径进行粗定位,再采用圆周差分法对外圆参数进行准确计算.该算法通过使用极坐标作为聚类特征及放宽模糊聚类的聚类条件,提高了虹膜定位算法的鲁棒性.实验结果表明,该方法有效提高了非理想情况下虹膜图像的定位精度.

A new two-step location approach combing coarse location with fine location was presented for iris location under non-ideal situation.Improved fuzzy C-mean clustering based on polar coordinates transformation was proposed for the coarse iris location and a kind of dynamic circular edge template was adopted by the fine iris location.Having used polar coordinates as clustering attribute and relaxed fuzzy clustering restriction,the proposed algorithm improves the robustness of iris location.The experimental results prove the validity of this approach convincingly.