一种近红外手背静脉图像识别算法  

Palm-Dorsal Vein Biometrics Based on Watershed Algorithm

作　　者：吴作凌[1] 陈雄[1] 郑英杰[1] 

机构地区：[1]复旦大学电子工程系,上海200433

出　　处：《微电子学与计算机》2010年第10期114-116,119,共4页Microelectronics & Computer

基　　金：国家自然科学基金项目(60671062;60571052);国家重点基础研究项目(2005CB724303)

摘　　要：为了避免传统静脉图像识别中分割细化步骤的错误,文中提出了一种基于分水岭算法的近红外手背静脉图像识别方法.该方法利用分水岭算法从灰度静脉图像中取得静脉的的骨架特征,根据骨架的交叉点和端点等特征点,运用改进的Haudorff距离来计算手背静脉模式的相似度.在手背静脉样本库上进行测试,取得了0.1%的等错误概率(EER)实验结果表明该算法可以作为一种有效的身份认证方法.A novel approach based on watershed algorithm to near infrared palm-dorsal vein image recognition is presented to avoid errors introduced in traditional vein image skeletonization stage.Skeletonization is performed directly on gray-scale vein image using watershed algorithm in our method.We use modified Hausdorff distance to evaluate the matching degree of vein patterns.Experiments were conducted on our own palm-dorsal vein image database and the results are satisfactory with 0.1% error equation rate（EER）,which indicates our method is a potentially usefull biometric.

关 键 词：手背静脉 分水岭 HAUSDORFF距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]