手指静脉图像分形特征提取方法  

Fractal feature extracting method of finger vein image

作　　者：杨金锋[1] 李乾司茂 贾桂敏[1] YANG Jinfeng;LI Qiansimao;JIA Guimin(Intelligent Signal and Image Processing Key Lab of Tianjin,CAUC,Tianjin 300300,China)

机构地区：[1]中国民航大学天津市智能信号与图像处理重点实验室,天津300300

出　　处：《中国民航大学学报》2019年第2期53-58,共6页Journal of Civil Aviation University of China

基　　金：国家自然科学基金项目(61502498;U1433120;61379102)

摘　　要：使用Gabor滤波增强并提取指静脉主干血管网络,通过实验对比分析3种不同的图像分维数测算方法,对指静脉主干血管网络的分维特征进行了统计分析。并提出基于二叉树模型的分形几何特征提取方法,提取血管网络的分叉角度、血管长度以及分叉层数,统计分析数据得到血管结构分形特征的一般规律,为实现手指静脉血管建模和识别奠定基础。The main vascular network of finger vein image is enhanced and extracted by Gabor filter. Three fractal dimension calculating methods are investigated and compared,analyzing the fractal feature extracted by the best calculation method. Furthermore,a fractal geometric feature extracting method is proposed basing on binary tree model to extract the fractal geometric features of finger vascular network such as bifurcation angle,vascular length and bifurcation layer feature and obtain general rules of the network,building foundation for finger vascular network modeling and recognition.

关 键 词：指静脉识别 血管网络 分形特征 二叉树 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]