指纹与指静脉双模态识别决策级融合方法  

Decision fusion of dual-modal recognition of fingerprints and finger veins

作　　者：王科俊[1] 马慧 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001

出　　处：《华中科技大学学报（自然科学版）》2011年第4期90-93,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家高技术研究发展计划资助项目(2008AA01Z148);国家自然科学基金资助项目(60975022);黑龙江省杰出青年科学基金资助项目(JC200703)

摘　　要：针对单模态生物特征识别系统固有的缺点,提出一种新的指纹与指静脉识别的决策级融合方法.首先对指纹及指静脉2种模态分别进行第一级分类器设计,得出各自的识别结果;然后将提取出的指纹与指静脉特征点集以特征串联的方式形成新的特征矢量,构成第二级分类器,再得出一个识别结果;最后将上述3个识别结果进行决策级融合得到系统最终的识别结果.实验结果表明本方法克服了单一模态识别方法的局限性,有效地提高了系统的性能.In order to overcome the inherent limitations of single modal fingerprint and finger vein recognition systems, a novel decision fusion algorithm based on fingerprint and finger vein dual-mode recognition was proposed. First two classifiers were designed for fingerprint and finger vein recognition, respectively. Then the extracted feature vectors from the first stage were concatenated to make the third classifier for second-level decision. Finally, the recognition was achieved by the fusion of the three classifiers′ recognition results at the decision level. Experimental results show that this new algorithm can overcome the limitations of single-modal biometrics and improve the recognition performance of the system effectively

关 键 词：多模态生物特征识别 指纹识别 静脉识别 决策级融合 二级分类 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]