摘要
为使提取的静脉图像特征具有较好的聚类特性以更利于正确识别,提出了一种基于有监督非负矩阵分解的识别算法。首先,对静脉图像进行分块处理,通过融合所有的子图像特征形成静脉的原始特征;其次,采用特征的稀疏性与聚类属性双正则项,对原始的非负矩阵分解模型进行改进;然后,基于梯度下降法对改进的非负矩阵分解模型进行求解,实现对原始特征的降维与优化;最后,利用最近邻算法对新的特征进行匹配,从而获得识别结果。实验结果表明,对于3种静脉样本数据库,所提识别算法的错误接受率与错误拒绝率分别可以达到0.02与0.03;此外,其2.89s的识别时间可以满足实时性要求。
In order to make the extracted vein feature have good clustering performance and thus be more conductive to correct identification,this paper proposed a recognition algorithm based on supervised Nonnegative Matrix Factorization（NMF）.Firstly,vein image is divided into blocks,and the original vein feature can be acquired by fusing all sub image features.Secondly,the sparsity and clustering property of feature vectors are regarded as two regularization terms,and the original NMF model is improved.Then,gradient descent method is used to solve the improved NMF model,and feature optimization and dimension reduction can be achieved.Finally,by using nearest neighbor algorithm to match new vein features,the recognition results can be acquired.Experiment results show that the obtained false accept rate（FAR）and false reject rate（FRR）of the proposed recognition algorithm can be reached 0.02 and 0.03 respectively for three vein databases,in addition,the recognition time of 2.89 seconds can meet real-time requirement.
作者
贾旭
孙福明
李豪杰
曹玉东
JIA Xu;SUN Fu-ming;LI Hao-jie;CAO Yu-dong(School of Electronics ＆ Information Engineering,Liaoning University of Technology,Jinzhou,Liaoning 121001,China;School of Software,Dalian University of Technology,Dalian,Liaoning 116024,China)
出处
《计算机科学》
CSCD
北大核心
2018年第8期283-287,共5页
Computer Science
基金
国家自然科学基金(61502216
61572244)资助
关键词
静脉识别
生物特征
非负矩阵分解
特征降维
稀疏表示
Vein recognition
Biological feature
Nonnegative Matrix Factorization
Feature dimension reduction
Sparse representation
