基于复数滤波的指纹中心点定位复合算法

Fusing Algorithm for Fingerprint Core Point Detection Based on Complex-Filters

由于指纹中心点的位置、方向等信息,在一定程度上具有描述指纹的拓扑结构甚至类型的能力,所以中心点定位算法的效果在指纹分类、检索以及识别结果上都产生了重要的影响。为降低中心点的误定位率,提出一个根据方向场正弦图进行中心点粗定位的方法,以及根据中心点分布规律与常用定位算法原理制定了一系列筛选规则,并将复数滤波与其它中心点定位算法进行融合。实验表明改进方法有效减少了指纹中心点的误定位率,并有效增加了指纹分类的准确率2%-8%。

ABSTRACT ： Because the location, direction and other information contained in the core points of fingerprint are able to describe the topology and even the class of fingerprint, the detection of core points plays an important role in finger- print classification, indexing and recognition. In order to reduce the detection error rate of core points, a new ap- proach for core points＇ rough detection based on the sin-map of fingerprint＇ s orientation and several rules for filtering concluded by the regularities of core points＇ distribution and the principle of the common detection approaches is pro- posed, and a complex-filter is fused with other core point detection approaches. Experiment shows that the detection error rate of core points is effectively reduced, and the accuracy of fingerprint classification is increased by 2%-8% using the improved approach.