手掌静脉图像识别技术综述  

A survey of palm-vein image recognition

作　　者：吴微[1,2] 苑玮琦[1] 

机构地区：[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,沈阳110041

出　　处：《中国图象图形学报》2013年第10期1215-1224,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60972123);教育部高等学校博士学科点专项科研基金项目(20092102110002);沈阳市科技计划项目(F10-213-1-00);辽宁省教育厅科研项目(L2012034)

摘　　要：人体的手掌静脉具有唯一性、稳定性,隐藏在表皮下,结构复杂很难被复制,手掌静脉图像难以窃取拍摄,这些使得手掌静脉成为一种高安全性的生物特征。作为生物特征识别领域的前沿课题,手掌静脉图像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。从手掌静脉图像识别技术的原理入手,综述了手掌静脉图像识别的4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,将掌脉图像识别方法分为基于结构特征的方法、基于纹理特征的方法和基于子空间的3类方法。最后,对掌脉图像识别技术的难点进行了总结,对发展趋势进行了展望。Human palm-vein is a permanent and unique physiological feature for each person. It hides under the skin and is difficult to duplicate because of its complex structure. Furthermore, palm vein images are difficult for candid shootings. All these characteristics make palm-vein 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 research focus in recent years. This paper introduces the principle of palm-vein imaging first, then it provides a survey of the four stages for palm-vein image recognition ： image acquisition, image prepro- cessing, feature extraction, and matching algorithms. According to different feature extraction approaches, we roughly group these algorithms into three categories： structure based, texture based, and subspace based methods. Finally, we con- clude this paper describing the difficulty of palm-vein recognition technology and a discussion of future trends.

关 键 词：模式识别 生物特征识别 手掌静脉图像识别 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]