|本期目录/Table of Contents|

[1]孟宪静,袭肖明,杨 璐,等. 基于灰度不均匀矫正和SIFT的手指静脉识别方法[J].南京大学学报(自然科学),2018,54(1):1.[doi:10.13232/j.cnki.jnju.2018.01.001]
 Meng Xianjing,Xi Xiaoming,Yang Lu,et al.Finger vein recognition based on intensity inhomogeneity correction and scale invariant feature transform[J].Journal of Nanjing University(Natural Sciences),2018,54(1):1.[doi:10.13232/j.cnki.jnju.2018.01.001]
点击复制

 基于灰度不均匀矫正和SIFT的手指静脉识别方法()
     

《南京大学学报(自然科学)》[ISSN:0469-5097/CN:32-1169/N]

卷:
54
期数:
2018年第1期
页码:
1
栏目:
出版日期:
2018-02-01

文章信息/Info

Title:
Finger vein recognition based on intensity inhomogeneity correction and scale invariant feature transform
作者:
 孟宪静1袭肖明1杨 璐1尹义龙2*
 1.山东财经大学计算机科学与技术学院,济南,250014;2.山东大学计算机科学与技术学院,济南,250101
Author(s):
Meng Xianjing1Xi Xiaoming1Yang Lu1Yin Yilong2*
1.School of Computer Science and Technology,Shandong University of Finance and Economics,Ji’nan,250014,China;
2.School of Computer Science and Technology,Shandong University,Ji’nan,250101,China
关键词:
手指静脉识别尺度不变性特征潜在特征匹配点灰度不均匀矫正
Keywords:
 finger vein recognitionscale invariant feature transformpotential matching key-pointintensity inhomogeneity correction
分类号:
TP391.4
DOI:
10.13232/j.cnki.jnju.2018.01.001
文献标志码:
A
摘要:
       基于手指静脉的身份识别以其方便性和安全性奠定了其在生物特征识别中的优势地位.在手指静脉识别方法中,尺度不变性特征(Scale Invariant Feature Transform,SIFT)虽然普遍被认为效果不佳,但鉴于SIFT在自然图像中取得的良好效果,在分析了手指静脉图像的质量和结构特点之后,设计了一种基于灰度不均匀矫正和SIFT的手指静脉识别方法.首先,根据手指静脉图像对比度低、模糊等特点,利用灰度不均匀矫正增强图像细节;其次,考虑到在尺度不变性特征的匹配过程中,相似特征点的存在也会影响手指静脉识别的性能;第三,在匹配的过程中,还考虑了潜在的特征匹配点.基于灰度不均匀矫正和潜在特征匹配点的手指静脉识别方法取得了良好的识别效果,在香港理工大学手指静脉库(PolyU Finger Vein Database)上六折交叉验证的等错误率(Equal Error Rate,EER)从0.0358降低到了0.0006,表明了方法的有效性.
Abstract:
Finger vein,one of the most promising biometric pattern,has received considerable attention from researchers because of its convenience and security.Scale Invariant Feature Transform(SIFT)is an algorithm to detect local features in images,which is rotation and scale invariant,and is widely applied in detection and recognition tasks.However,the results of finger vein recognition methods based on SIFT are demonstrated to be unsatisfactory.To deal with this problem,we propose a finger vein recognition method based on SIFT with intensity inhomogeneity correction and a new matching technique.The finger vein image is firstly processed by intensity inhomogeneity correction based upon the observation that the obscured image quality is bad for SIFT key-points detection.The key-points extracted are usually unstable and small in amount.After the correction of intensity inhomogeneity,the textures in images can be enhanced,and key-points can be correctly detected and be more stable.In the SIFT matching process,the existing of too many similar key-points can also degrade the performance.This is because possessing which is more than one similar key-points may lead to false matching.We believe key-points match successfully with more than one key-point should also be considered in matching,and name it as potential matching key-point.Accordingly,we calculate the matrix of matching scores for two images,on which the distribution of potential matching key-point is assessed.Finally,the matching scores is calculated as normalized number of potential matching key-points.Extensive experiments have been conducted on the PolyU and MLA databases.The Equal Error Rate(EER)under six-fold cross validation on the PolyU database is reduced to 0.0006 from 0.0358,which indicates the effectiveness of the proposed method.

参考文献/References:

 [1] Hashimoto J.Finger vein authentication technology and its future ∥ Proceedings of 2016 Symposium on VLSI Circuits,2016.Digest of Technical Papers.Honolulu,HI,USA:IEEE,2006:5-8.
[2] Yanagawa T,Aoki S,Ohyama T,et al.Human finger vein images are diverse and its patterns are useful for personal identification ∥ MHF Preprint Series.21st Century COE Program Development of Dynamic Mathematics with High Functionality.Fukuoka-ken,Japan:Kyushu University,2007:1-7.
[3] Kono M,Ueki H,Umemura S I.Near-infrared finger vein patterns for personal identification.Applied Optics,2002,41(35):7429-7436.
[4] Liu Z,Yin Y L,Wang H J,et al.Finger vein recognition with manifold learning.Journal of Network and Computer Applications,2010,33(3):275-282.
[5] Wu J D,Ye S H.Driver identification using finger-vein patterns with Radon transform and neural network.Expert Systems with Applications,2009,36(3):5793-5799.
[6] Sato H.Finger vein authentication apparatus and finger vein authentication method.U.S.Patent 8229179,2012-07-24.
[7] Kiyomizu H,Miura N,Miyatake T,et al.Finger vein authentication device.U.S.Patent 8811689,2014-08-19.
[8] Rosdi B A,Shing C W,Suandi S A.Finger vein recognition using local line binary pattern.Sensors,2011,11(12):11357-11371.
[9] Lee E C,Jung H,Kim D.New finger biometric method using near infrared imaging.Sensors,2011,11(3):2319-2333.
[10] Meng X J,Yang G P,Yin Y L,et al.Finger vein recognition based on local directional code.Sensors,2012,12(11):14937-14952.
[11] Song W,Kim T,Kim H C,et al.A finger-vein verification system using mean curvature.Pattern Recognition Letters,2011,32(11):1541-1547.
[12] Miura N,Nagasaka A,Miyatake T.Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification.Machine Vision and Applications,2004,15(4):194-203.
[13] Kumar A,Zhou Y B.Human identification using finger images.IEEE Transactions on image processing,2012,21(4):2228-2244.
[14] Yu C B,Qin H F,Cui Y Z,et al.Finger-vein image recognition combining modified hausdorff distance with minutiae feature matching.Interdisciplinary Sciences:Computational Life Sciences,2009,1(4):280-289.
[15] Liu F,Yang G P,Yin Y L,et al.Singular value decomposition based minutiae matching method for finger vein recognition.Neurocomputing,2014,145:75-89.
[16] Pang S H,Yin Y L,Yang G P,et al.Rotation invariant finger vein recognition ∥ The 7th Chinese Conference on Biometric Recognition.Guangzhou,China:Springer,2012:151-156.
[17] Peng J L,Wang N,El-Latif A A A,et al.Finger-vein verification using Gabor filter and sift feature matching ∥ The 8th International Conference on Intelligent Information Hiding and Multimedia Signal Processing.Piraeus,Greece:IEEE,2012:45-48.
[18] Kim H G,Lee E J,Yoon G J,et al.Illumination normalization for SIFT based finger vein authentication ∥ Bebis G,Boyle R,Parvin B,et al.Advances in Visual Computing.Springer Berlin Heidelberg,2012:21-30.
[19] Yang J F,Shi Y H.Finger-vein ROI localization and vein ridge enhancement.Pattern Recognition Letters,2012,33(12):1569-1579.
[20] Lee E C,Park K R.Image restoration of skin scattering and optical blurring for finger vein recognition.Optics and Lasers in Engineering,2011,49(7):816-828.
[21] Mulyono D,Jinn H S.A study of finger vein biometric for personal identification ∥ Proceedings of the International Symposium on Biometrics and Security Technologies.Islamabad,Pakistan:IEEE,2008:1-8.
[22] Yang L,Yang G P,Yin Y L,et al.Sliding window-based region of interest extraction for finger vein images.Sensors,2013,13(3):3799-3815. 
[23] Miura N,Nagasaka A,Miyatake T.Extraction of finger-vein patterns using maximum curvature points in image profiles.IEICE Transactions on Information and Systems,2007,90(8):1185-1194.

相似文献/References:

备注/Memo

备注/Memo:
 基金项目:国家自然科学基金(61701280,61573219,61671274),山东省自然科学基金青年项目(ZR2016FQ18),山东省高等学校优势学科人才团队培育计划
收稿日期:2017-12-09
*通讯联系人,E-mail:ylyin@sdu.edu.cn
更新日期/Last Update: 2018-01-30