基于方向梯度的快速手掌静脉识别  

Fast palm-vein recognition based on direction gradient

作　　者：逄增耀 杨杰[1] Pang Zengyao;Yang Jie(College of Information Engineering,Wuhan University of Technology,Wuhan 430070,China)

机构地区：[1]武汉理工大学信息工程学院,武汉430070

出　　处：《计算机应用研究》2018年第3期953-956,960,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(51479159)

摘　　要：针对目前在静脉纹理提取算法中,对图像质量要求高、算法复杂度高的问题,利用静脉图像的剖面线在静脉区域中灰度值会呈现山谷状变化的特征,通过计算静脉图像多方向的梯度矩阵,提出一种计算简单、快速且稳定的掌脉纹路中心和纹路宽度提取算法。在此基础上,采用相应的编码方法确定纹理图像灰度值分布。最后,利用模糊阈值判定以及全局灰度值匹配算法来提高算法的鲁棒性及识别精度。实验结果表明,算法纹路特征提取的速度为25.2 ms;在掌脉图像两两匹配的条件下,该算法EER达到3.21%。最终可以得出该算法在纹路提取效果、匹配正确率以及算法效率上都有较为明显的优势的结论。Although many doors have been opened in extracting vein textures,most of them depend heavily on high-quality images as well as complex algorithms.Inspired by the fact that features in those vein areas have similar appearance as valleys,this paper proposed a novel method to extract center and width of palm vein based on multi-directional gradients,which was easy-computing,quick and stable.On this basis,it designed an encoding method to determine the gray value distribution of texture image.This algorithm could effectively overcome the edge of the texture extraction error.Finally,the system was equipped with higher robustness and recognition accuracy by utilizing fuzzy threshold determination and global gray value matching algorithm.Experimental results on pairs of matched palm images show that,the proposed method has a EER with 3.21%extracts features at the speed of 25.2 ms per image.It can be concluded that the proposed algorithm has obvious advantages in grain extraction efficiency,matching accuracy and algorithm efficiency.

关 键 词：纹理特征 梯度 灰度值分布 模糊判定 灰度值匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]