摘要
手背静脉识别技术是一种利用手背静脉特征来实现身份识别的技术,作为一种新颖的身份识别技术,近年来得到了一些学者的关注.研制了一套手背静脉识别系统,能够完成手背静脉红外图像的采集、预处理、特征提取和匹配.首先设计了一种改良的手背静脉图像采集设备来获得手背静脉原始图像,然后对图像进行小波去噪、灰度拉伸、NiBlack二值化、图像细化等预处理操作,得到手背静脉骨架图像,最后使用随机投影算法进行特征提取并用最邻近分类器进行匹配.实验测试结果表明本系统有96%的识别率,具备一定实用价值,对手背静脉识别系统的研制有一定的参考借鉴意义.
The dorsal hand vein recognition technology is a kind of technology which uses the network structure of the dorsal hand vein to identify people. As a newly arisen biometric identity recognition technology,it has got the attention of some scholars in recent years. This paper developed a set of miniature dorsal hand vein recognition system which can complete infrared hand vein image acquisition,image pre-processing,feature extraction and identity match. This paper designed an improved dorsal hand vein image capture system to acquire hand vein image firstly,then performs wavelet denoising,gray stretch,NiBlack thresholding and image thinning operations on it to get dorsal hand vein skeleton image. Finally use random projection method to extract features and match samples with a nearest neighbour classifier. Experiment result shows that our system has a 96% accuracy which offers valuable reference for development and miniaturization of dorsal hand vein recognition system.
作者
何振邦
徐喜荣
胡旭明
戴鑫邦
HE Zhen-bang;XU Xi-rong;HU Xu-ming;DAI Xin-bang(School of Computer Science and Technology,Dalian University of Technology,Dalian 116024,China)
出处
《小型微型计算机系统》
CSCD
北大核心
2019年第3期628-634,共7页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61472465
61562066
61170303)资助
国家大学生创新创业项目(2017101410201010955)资助
关键词
红外图像
手背静脉识别
特征提取
infrared image
dorsal hand vein recognition
feature extraction
