基于指导滤波与二值图像组互相关匹配的3D掌纹识别  

3D Palmprint Recognition Based on Guided Filter and Cross-correlation of Binary Image Groups

作　　者：刘明[1,2] 李丽华[1] 李哲[1] 

机构地区：[1]河北大学电子信息工程学院,保定071002 [2]河北省数字医疗工程重点实验室,保定071002

出　　处：《计算机科学》2014年第9期301-305,324,共6页Computer Science

基　　金：国家自然基金(61203160;61100143);河北大学医工交叉研究项目(BM201104)资助

摘　　要：提出了一种鲁棒的掌纹识别方法。在特征提取阶段,使用指导图像滤波去除噪声,然后基于Gabor变换提取鲁棒的掌纹方向特征,并使用一组二值图像表示每幅3D掌纹图像;在匹配阶段,采用了基于二值图像组互相关运算的匹配算法。该方法能够充分利用图像组中的特征配准图像来得到准确的匹配分数。HK-PolyU 2D+3Dpalmprint database数据库上的实验表明,该方法能够有效提高掌纹识别算法的识别率。A robust personal recognition method was proposed based on the 3D palmprint in this paper. In the stage ot feature extraction,guided filter is used to remove the noise in the image. Then robust orientation features, namely a group binary images, are extracted based on Gabor transformation. In the stage of matching, the matching score is calculated based on the cross-correlation of binary image groups. The algorithm can make full use of the information in the image groups to obtain the accurate matching score. Experimental results on the HK-Poly 2D＋3D palmprint database demonstrate that the proposed approach can improve the performance of the 3D palmprint verification system.

关 键 词：生物特征识别 3D掌纹识别 指导滤器 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]