手掌静脉识别算法  

Palm vein recognition algorithm

作　　者：张环[1] 胡德文[1] 

机构地区：[1]国防科学技术大学机电工程与自动化学院,长沙410073

出　　处：《计算机应用》2010年第12期97-99,共3页journal of Computer Applications

基　　金：国家自然科学基金资助项目(90736018)

摘　　要：对手掌静脉识别算法中的预处理、特征提取和匹配判别进行了研究。首先利用自主设计的手掌静脉采集设备采集一定规模的手掌静脉图像并相应建立小规模手掌静脉数据库,然后对采集到的手掌静脉图像进行提取感兴趣区域(RO I)、平滑滤波和图像增强等预处理操作,以及进行二值化、滤波去噪和细化修复等操作来提取关键点的特征信息,最后利用成熟的指纹特征点匹配方法进行匹配判别。通过对实验结果分析表明,该算法的识别率高且性能良好,具有较好的应用前景。This paper presented some researches on preprocessing,pattern extraction,matching and decision of palm vein recognition algorithm.First,the palm vein images were collected by designing palm vein capture device to build a small palm vein database,then Region of Interest（ROI） extraction,smooth filtering and image enhancement were implemented to preprocess the collected images.The pattern information of minutiae was extracted by binarization,noise elimination and thinning.With the help of the mature fingerprint algorithm,a decision was made by matching the pattern of minutiae.The experimental results show that the proposed algorithm achieves a high recognition rate,and it has a fine performance and promising applicable future.

关 键 词：血管 手掌静脉 感兴趣区域 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]