基于三角模融合算子的指纹图像分割方法  

Fingerprint Image Segmentation Based on Triangle Module Operator

作　　者：祁兵[1] 景晓军[2] 唐良瑞[1] 翟明岳[1] 梁明[1] 

机构地区：[1]华北电力大学信息工程系,北京102206 [2]北京邮电大学电信工程学院,北京100876

出　　处：《计算机工程》2004年第2期157-158,195,共3页Computer Engineering

摘　　要：针对指纹图像提出了一种基于三角模融合算子的图像分割算法。该方法使用方向性和对比度两个信息分别作为两个分类器的特征,并求出各分类器的判决信度,利用三角模融合算子将两个分类器的结果进行融合判决。该方法具有较高的稳健性和精确度。最后给出的实验结果验证了算法的有效性。A novel segmentation method is proposed for fingerprint image based on triangle module operator. According to characteristics of the fingerprint image, two-threshold segmentation is used to discern ridge and non-ridge areas in fingerprints, and then direction and contrast are respectively selected as features for two separate classifiers. At last, the fusion method of triangle module operator is used to determine the final result of both classifiers. Thus the clear fingerprint areas, noisy fingerprint areas and fuzzy areas are achieved. Experimental results have proved the feasibility and high robust of this algorithm.

关 键 词：指纹 图像分割 三角模算子 信息融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]