%0 Journal Article
%T 一种基于图模型与定序编码的手指静脉识别方法<br>Weighted Graph and Gabor Ordinal Measure Based Description for Finger-Vein Network
%A 叶子云
%A 石滨萌
%A 温梦娜
%J Computer Science and Application
%P 2945-2952
%@ 2161-881X
%D 2021
%I Hans Publishing
%R 10.12677/CSA.2021.1112298
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">手指静脉的网络结构是指静脉区分性的来源，但获得可靠的手指静脉网络结构描述一直是个难题。为此，本文提出一种基于图模型与定序编码的手指静脉网络特征描述方法。对于一幅手指静脉图像，首先通过划分图块来获得图的节点集，其次利用三角剖分法获得图的边集，边的权重由边所连接的节点特征来决定。经过上述操作，一幅手指静脉图像可构建一个加权图，通过度量加权图的邻接矩阵相似度来实现手指静脉识别。本文中研究影响识别结果的几个因素，并通过实验证明了该方法的有效性。<br />
The network structure of finger veins is the source of distinguishment, but it has always been a difficult problem to obtain a reliable description of the vein network structure. So, in this paper, we propose a finger vein network feature description method based on graph model and Gabor ordinal measure. For a finger vein image, this paper first obtains the node-set of the graph by block division, and then uses the triangulation method to obtain the edge-set of the graph. The weights of the edges are determined by the features of the nodes connected by the edges. After the above operations, a finger-vein image could be represented by a weighted graph, and the adjacency matrix of this weighted graph was used for fingervein recognition. In this paper, several factors affecting the recognition results are studied, and the effectiveness of the method is proved through experiments.</span> 
</div>
%K 手指静脉识别，加权图，定序编码<br>Finger-Vein Recognition
%K Weighted Graph
%K Gabor Ordinal Measure
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=47269