第14卷第3期 智能系统学报 Vol.14 No.3 2019年5月 CAAI Transactions on Intelligent Systems May 2019 D0:10.11992/tis.201801014 网络出版地址：http:/kns.cnki.net/kcms/detail/23.1538.tp.20180425.1001.004.html 融合LBP纹理特征与B2DPCA技术的 手指静脉识别方法 胡娜，马慧，湛涛 (黑龙江大学电子工程学院，黑龙江哈尔滨150001) 摘要：鉴于传统局部二进制模式(local binary pattern,LBP)算法对光照方向的变化非常敏感的问题，本文提出 一种融合旋转不变模式的LBP算子与B2DPCA技术的手指静脉识别方法。首先提取手指静脉图像子块的 LBP纹理谱特征，然后采用双向二维主成分分析方法对LBP特征向量构成的特征矩阵进行有效的降维处理， 再通过比对降维后的待识别静脉图像特征向量与其他样本的特征向量之间的欧式距离来实现最终的样本分 类。通过在天津市智能实验室静脉库及马来西亚理科大学FV-USM静脉库上进行实验验证，在不同训练样本 数量下比较了8种算法的识别性能，相比于单一的LBP特征提取算法、经典降维算法和LBP与经典降维组合 特征提取算法，该方法的识别率有很大的提高，证明了本文方法的有效性。 关键词：手指静脉识别：特征提取：LBP纹理特征：二维主成分分析：双向二维主成分分析；欧氏距离：图像特征 向量；降维 中图分类号：TP391.4文献标志码：A文章编号：1673-4785(2019)03-0533-08 中文引用格式：胡娜，马慧，湛涛.融合LBP纹理特征与B2DPCA技术的手指静脉识别方法J.智能系统学报，2019,14(3)： 533-540. 英文引用格式：HUNa,MA Hui,.ZHAN Tao.Finger vein recognition method combining LBP texture feature and B.2 DPCA techno- logyJ]CAAI transactions on intelligent systems,2019,14(3):533-540. Finger vein recognition method combining LBP texture feature and B2DPCA technology HU Na,MA Hui,ZHAN Tao (College of Electronic Engineering,Heilongjiang University,Harbin 150001,China) Abstract:By considering the sensitivity of the traditional local binary pattern(LBP)algorithms while varying the illu- mination,this study proposes a finger vein recognition method using a rotation invariant LBP operator and B2DPCA. This method initially extracts the LBP texture spectrum feature of the image block of a finger vein,uses a bidirectional two-dimensional main component analysis method to effectively reduce the dimension of the eigenmatrix comprising the LBP eigenvectors,and finally classifies the final samples by comparing the Euclidean distance between the vein im- age eigenvectors that are to be identified and the eigenvectors of other samples after dimension reduction.The experi- ments were implemented on the finger vein image databases obtained from the Tianjin Intelligence Laboratory and from the FV-USM database of the University of Science,Malaysia.Further,eight methods with different numbers of training samples are compared,which exhibit that the fusion features that are proposed by this study perform considerably better than the single LBP operator.single traditional dimension-reduced methods.and the fusion of LBP and traditional di- mension-reduced algorithms.Additionally,the recognition rate of the generated method was observed to significantly improve.This indicated that the analysis method proposed in this study is proper and effective. Keywords:finger vein recognition;feature extraction;local binary patterns,two-dimensional principal component;bid- irectional two-dimensional principal component analysis;euclidean distance;image feature vector;dimensionality re- duction 收稿日期：2018-01-08.网络出版日期：2018-04-26. 基金项目：国家自然科学基金项目(61573132)：黑龙江省高校 手指静脉识别是一种活体生物特征识别技 基本科研业务费项目(HDRCCX-20I602):黑龙江省 高校重点实验室开放基金项目(DZGC201610). 术，它利用近红外光透射手指后采用CCD或摄像 通信作者：马慧.E-mail:2011043@hlju.edu.cn. 头获取被采集手指内部静脉纹路的分布图，再通DOI: 10.11992/tis.201801014 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.tp.20180425.1001.004.html 融合 LBP 纹理特征与 B2DPCA 技术的 手指静脉识别方法 胡娜，马慧，湛涛 （黑龙江大学 电子工程学院，黑龙江 哈尔滨 150001） 摘 要：鉴于传统局部二进制模式 (local binary pattern, LBP) 算法对光照方向的变化非常敏感的问题，本文提出 一种融合旋转不变模式的 LBP 算子与 B2DPCA 技术的手指静脉识别方法。首先提取手指静脉图像子块的 LBP 纹理谱特征，然后采用双向二维主成分分析方法对 LBP 特征向量构成的特征矩阵进行有效的降维处理， 再通过比对降维后的待识别静脉图像特征向量与其他样本的特征向量之间的欧式距离来实现最终的样本分 类。通过在天津市智能实验室静脉库及马来西亚理科大学 FV-USM 静脉库上进行实验验证，在不同训练样本 数量下比较了 8 种算法的识别性能，相比于单一的 LBP 特征提取算法、经典降维算法和 LBP 与经典降维组合 特征提取算法，该方法的识别率有很大的提高，证明了本文方法的有效性。 关键词：手指静脉识别；特征提取；LBP 纹理特征；二维主成分分析；双向二维主成分分析；欧氏距离；图像特征 向量；降维 中图分类号：TP391.4 文献标志码：A 文章编号：1673−4785(2019)03−0533−08 中文引用格式：胡娜, 马慧, 湛涛. 融合 LBP 纹理特征与 B2DPCA 技术的手指静脉识别方法[J]. 智能系统学报, 2019, 14(3): 533–540. 英文引用格式：HU Na, MA Hui, ZHAN Tao. Finger vein recognition method combining LBP texture feature and B2DPCA techno￾logy[J]. CAAI transactions on intelligent systems, 2019, 14(3): 533–540. Finger vein recognition method combining LBP texture feature and B2DPCA technology HU Na，MA Hui，ZHAN Tao (College of Electronic Engineering, Heilongjiang University, Harbin 150001, China) Abstract: By considering the sensitivity of the traditional local binary pattern (LBP) algorithms while varying the illu￾mination, this study proposes a finger vein recognition method using a rotation invariant LBP operator and B2DPCA. This method initially extracts the LBP texture spectrum feature of the image block of a finger vein, uses a bidirectional two-dimensional main component analysis method to effectively reduce the dimension of the eigenmatrix comprising the LBP eigenvectors, and finally classifies the final samples by comparing the Euclidean distance between the vein im￾age eigenvectors that are to be identified and the eigenvectors of other samples after dimension reduction. The experi￾ments were implemented on the finger vein image databases obtained from the Tianjin Intelligence Laboratory and from the FV-USM database of the University of Science, Malaysia. Further, eight methods with different numbers of training samples are compared, which exhibit that the fusion features that are proposed by this study perform considerably better than the single LBP operator, single traditional dimension-reduced methods, and the fusion of LBP and traditional di￾mension-reduced algorithms. Additionally, the recognition rate of the generated method was observed to significantly improve. This indicated that the analysis method proposed in this study is proper and effective. Keywords: finger vein recognition; feature extraction; local binary patterns; two-dimensional principal component; bid￾irectional two-dimensional principal component analysis; euclidean distance; image feature vector; dimensionality re￾duction 手指静脉识别是一种活体生物特征识别技 术，它利用近红外光透射手指后采用 CCD 或摄像 头获取被采集手指内部静脉纹路的分布图，再通 收稿日期：2018−01−08. 网络出版日期：2018−04−26. 基金项目：国家自然科学基金项目 (61573132)；黑龙江省高校 基本科研业务费项目 (HDRCCX-201602)；黑龙江省 高校重点实验室开放基金项目 (DZGC201610). 通信作者：马慧. E-mail：2011043@hlju.edu.cn. 第 14 卷第 3 期 智 能 系 统 学 报 Vol.14 No.3 2019 年 5 月 CAAI Transactions on Intelligent Systems May 2019