手背静脉识别利用静脉血管分布的网络结构实现个人身份鉴定,是一种新兴的生物特征识别技术。分析了静脉成像原理,设计了静脉图像采集系统,并建立了具有较高质量的手背静脉图像数据库。在身份识别过程中,首先对手背静脉图像进行滤波和灰度归一化等预处理,然后对图像进行二级小波包分解,并利用得到的细节图像提取手背静脉的纹理特征,最后将k近邻分类器和支持向量机相结合实现了个人身份识别。在识别模式下利用建立的手背静脉图像数据库对本系统进行了性能测试,实验结果表明该系统具有较高的识别性能,其正确识别率达99.07%,应用前景十分广阔。

Hand vein recognition is a newly arisen biometrics technology,which adopts the net structure of vein vessels to achieve personal individual identification. The hand vein image acquisition system is designed according to vein imaging theory,and consequently construct hand vein image database with high quality. To verify personal indetification,firstly the hand vein image is preprocessed by image filtering and grey normalization,and then the detail images derived from two-level wavelet packet decomposition are used to extract the texture information of hand vein. Finally,the k neighbor classifier and support vector machines are combined for individual recognition. The performance of the proposed method is tested using the hand vein image database constructed by our group under the identification mode. The result shows its correct recognition rate is up to 99.07%,which demonstrates that this system has good recognition performance and possesses wide application prospect.