基于梯度离散度和互信息准则的残缺指纹方向场重建融合算法  

Fusion Algorithm for Incomplete Fingerprint Orientation Field Reconstruction Based on Gradient Dispersion and Mutual Information

作　　者：张博[1] 景晓军[1] 孙松林[1] 张少乐[1] 

机构地区：[1]北京邮电大学信息与通信工程学院,北京100876

出　　处：《电子学报》2011年第9期2130-2134,共5页Acta Electronica Sinica

基　　金：国家自然科学基金项目(No.60872148);国家自然科学基金青年科学基金项目(No.60702049)

摘　　要：针对残缺指纹中方向场的重构,本文提出了一种利用全局方向信息和局部梯度信息的基于互信息准则的方向场融合算法.此算法根据局部梯度信息的竞争性、结合全局方向信息的互补性、冗余性,首先根据局部指纹梯度信息定义离散度,自适应的融合梯度信息,其次运用互信息准则结合指纹全局信息,对残缺部分的方向进行重估和修正.根据融合结果,进行后期指纹Gabor滤波和匹配.实验证明了本算法的有效性.Based on the global orientation,the local gradient and the mutual information function,a novel fingerprint orientation field fusion algorithm is proposed for incomplete fingerprint orientation field reconstruction.First,according to the properties of competition of the local fingerprint,complementation and redundancy of the global fingerprint,the gradient dispersion function is proposed,adaptively.Then,the fingerprint orientation field of the incomplete area is re-computed and measured by mutual information function.And hence the fusion orientation field is used for Gabor filtering and minutiae matching.The experimental results indicate that the proposed algorithm is effective for incomplete fingerprint.

关 键 词：残缺指纹 信息融合 方向场 梯度离散度 互信息 

分 类 号：TN911.73[电子电信—通信与信息系统]