一种基于指纹中心点的匹配算法  

A Fingerprint Matching Algorithm Based on Center Point of the Fingerprint

作　　者：谭台哲[1] 宁新宝[1] 尹义龙[2] 詹小四[1] 

机构地区：[1]南京大学电子科学与工程系,南京210093 [2]山东大学计算机学院,济南250100

出　　处：《南京大学学报（自然科学版）》2003年第4期483-490,共8页Journal of Nanjing University（Natural Science）

基　　金：南京大学重大应用研究预研项目基金(2001-03)

摘　　要：针对基于点模式匹配的指纹匹配算法速度较慢的现状,研究了一种基于指纹中心点的指纹匹配算法。该算法首先根据指纹模式区中检测的奇异点结构特征信息对指纹进行粗匹配,判断指纹不匹配的情况。其次,对无法判断的情形,则进行精确匹配,进一步利用奇异点或者指纹有效区域的质心点寻找匹配的基准特征点对和相应的变换参数,并将待识指纹相对于模板指纹做姿势纠正,最后采用坐标匹配的方式实现两枚指纹的比对。实验结果证明,该算法可以快速、准确的定位基准点,精确求取变换参数,误识率低,准确性高,并具有图像旋转平移不变性。对面积适中的指纹图像,匹配结果可以满足在线应用的需要。Since the fingerprint matching algorithm based-on point pattern matching is not quick enough, a new fingerprint matching algorithm based on center point is presented here. First, according to the structural information of the singularities detected in the pattern area, the coarse fingerprint matching is performed to find out the cases of no matching. Second, the other cases perform the accurate matching. Furthermore, the singularities or the centriod of the usable fingerprint area are used to choose a pair of reference minutiae. Then the translation and rotation parameters of two fingerprint images (the template image and the input image) are figured out based on the coordinates of the pair of reference minutiae. The posture of the input image relative to the template image is adjusted too. At last the fingerprint matching resuls given are the method of by coordinate-based matching. Experimental results indicate that fingerprint matching can be performed correctly and fast by the algorithm and the algorithm is invariant to translation and rotation of images. As for fingerprint images of moderate sizes, the needs for online application can be met. The algorithm is expected to be a convenient and effective fingerprint matching technique.

关 键 词：指纹图像 指纹匹配算法 图像匹配 指纹奇异点 基准特征点对 指纹中心点 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]