基于指纹块中主要脊和次要脊的方向场估计  

Fingerprint Orientation Field Estimation Based on the Primary and Secondary Ridges within Fingerprint Block

作　　者：刘欢喜[1] 李雄[1] 刘亚雄[1] 刘允才[1] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240

出　　处：《上海交通大学学报》2010年第3期423-427,共5页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金项目(60833009);国家重点基础研究发展规划(973)项目(2006CB303103);国家高技术研究发展计划(863)项目(2009AA01Z330)

摘　　要：针对方向场估计算法存在估计精度不高、计算时间开销过大的现象,提出一种基于指纹块中主要脊和次要脊的指纹方向场估计方法.它主要包括4个处理步骤:预处理原始指纹图像,利用上半邻域搜索算法提取指纹前景块中的主要脊和次要脊,利用脊的直线模型估计指纹前景块方向,以及采用修正方案提高方向场估计的精度.实验结果表明,该方法不仅具有令人满意的估计精度,而且拥有很高的计算效率;且具有很强的抗噪性能,能够有效提高指纹识别系统的性能.A novel algorithm based on the primary and secondary ridges within the fingerprint block was proposed for the orientation field estimation.The algorithm comprises four steps： preprocessing original fingerprint image,determining the primary and secondary ridges of fingerprint foreground block using the top semi-neighbor searching algorithm,estimating block direction based on straight-line model of such a primary ridge and correcting the spurious block directions.The experimental results show that it achieves satisfying estimation accuracy with low computational time expense.A further experiment shows that it is more accurate and robust to noise compared with the previous methods and can improve the performance of a fingerprint recognition system.

关 键 词：指纹方向场 主要脊和次要脊 上半邻域搜索算法 脊的直线模型 修正方案 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]