中图法分类号：TP391 文献标识码：A 文章编号 - 中国图象图形学报.DOC

中图法分类号：TP391 文献标识码：A 文章编号：1006-8961(200 ) - - 文章索引信息:论文引用格式： 手掌静脉识别技术综述 吴微1，2 ，苑玮琦 1. 沈阳工业大学视觉检测技术研究所，沈阳 110870； 2. 沈阳大学 信息工程学院，辽宁 沈阳 110041 摘 要：作为生物特征识别领域的前沿课题，手掌静脉识别技术以其高安全性等优势拥有着广泛的应用前景，成为近几年的研究热点。本文从手掌静脉识别技术的原理入手，综述了手掌静脉识别的四个阶段：图像采集，图像预处理、特征提取及匹配。根据特征提取方法不同，将掌脉识别方法分为基于结构特征的、基于纹理特征的和基于子空间的三类方法。最后，对掌脉识别技术的难点进行了总结，对发展趋势进行了展望。 关键词 ：模式识别；生物特征识别；手掌静脉识别；特征提取 Wu Wei 1,2, Yuan Weiqi1 1. Computer Vision Group, Shenyang University of Technology, Shenyang 110178, China；2. Information Engineering Department ,Shenyang University, Shenyang 110041, China Abstract: Human palm vein is a permanence and uniqueness physiological feature for every person. It hides under the skin and is difficult to duplicate for complex structure. Palm vein image is difficult to be candid shooting. All these characters make palm vein become a high security biometric feature. As a leading subject of biometrics technology, palm vein image recognition has a wide prospect of application for its outstanding characters, such as high security. Palm vein image recognition has always been a new research focus in recent years. This paper introduces the principle of palm vein imaging firstly, provides a survey of four stages for palm vein image recognition: image acquisition, image preprocessing, feature extraction and matching algorithms secondly. According to different feature extraction approaches, we roughly group these algorithms into three categories: structure based, texture based and subspace based methods. Finally, we conclude this paper with the difficulty of palm vein recognition technology and a discussion of future trends. Key words: pattern recognition； biometrics identification； palm vein recognition；feature extraction 随着社会和经济的不断发展，人们对身份鉴别的准确性、安全性提出了越来越高的要求。传统的身份鉴别方法：特征物品（如身份证、 信用卡等）和特定知识（如密码、口令等），存在容易丢失、遗忘、被复制及盗用的隐患。而通过辨识人的生理和行为特征进行身份认证的生物特征识别技术 (Biometrics)[1]为身份鉴别提供了一个方便可靠的解决方案。生物特征识别是指根据人的生理特征 (如指纹、面部特征、虹膜等) 或行为特征 (如步态、签名等) 进行身份鉴别的技术。我国在《国家中长期科学和技术发展规划纲要（2006-2020）》中，将生物特征识别列为