基于复合梯度向量的指纹匹配算法
|
摘要
针对接触式指纹识别中存在的非线性形变问题,提出了一种基于复合梯度向量(Composite Gradient Vector,CGV)的指纹匹配算法.该算法首先在经过预处理的指纹图像上建立直角坐标系和第一个基向量,并对指纹图像进行旋转;然后在旋转后的指纹图像上采样基向量,组建向量簇,提取极大梯度向量,并以极大梯度向量为元素组建复合梯度向量;最后以分层标记规则对复合梯度向量进行分层标记,通过对指纹库进行指纹检索、复合梯度向量匹配、维度和梯度匹配,识别出指纹图像.实验结果表明,该方法克服了接触式指纹识别中旋转、偏移、拉伸等问题,有较强的抗非线性形变能力,同时具有较快的识别速度和较高的识别准确率.
An approach based on composite gradient vector is proposed to overcome the problem of nonlinear distortion in contact fingerprint identification. Firstly, rectangular coordinate system and the first base vector are set up, and then the fingerprint image is rotated. Base vectors are collected on rotated fingerprint image. All the base vectors are set into vector cluster. Then the basis vectors are made into greatly gradient vector. Finally,hierarchical markup method is used for markup on the composite gradient vector. The target fingerprint image is recognized by fingerprint searching, compound gradient vector matching,dimension and gradient matching auxiliary. Experiment results show that the proposed approach has overcome the problem of rotation, translation and scaling situation and has a strong ability of anti-nonlinear deformation with fast recognition speed and high recognition accuracy.
An approach based on composite gradient vector is proposed to overcome the problem of nonlinear distortion in contact fingerprint identification. Firstly, rectangular coordinate system and the first base vector are set up, and then the fingerprint image is rotated. Base vectors are collected on rotated fingerprint image. All the base vectors are set into vector cluster. Then the basis vectors are made into greatly gradient vector. Finally,hierarchical markup method is used for markup on the composite gradient vector. The target fingerprint image is recognized by fingerprint searching, compound gradient vector matching,dimension and gradient matching auxiliary. Experiment results show that the proposed approach has overcome the problem of rotation, translation and scaling situation and has a strong ability of anti-nonlinear deformation with fast recognition speed and high recognition accuracy.
引文
[1]殷俊,杨万扣.核稀疏保持投影及生物特征识别应用[J].电子学报,2013,41(4):639-645.YIN Jun,YANG Wan-kou.Kernel sparsity preserving projections and its application to biometrics[J].Acta Electronica Sinica,2013,41(4):639-645.(in Chinese)
[2]詹曙,王俊,杨福猛,方琪.基于Gabor特征和字典学习的高斯混合稀疏表示图像识别[J].电子学报,2015,43(3):523-528.ZHAN Shu,WANG Jun,YANG Fu-meng,FANG Qi.Gaussian mixture sparse representation for image recognition based on Gabor features and dictionary learning[J].Acta Electronica Sinica,2015,43(3):523-528.(in Chinese)
[3]桂振文,刘越,陈靖,王涌天,徐志伟.一种适用于智能手机的图像识别算法[J].电子学报,2014,42(8):1487-1494.GUI Zhen-wen,LIU Yue,CHEN Jing,WANG Yong-tian,XU Zhi-wei.A novel image recognition algorithm for smartphones[J].Acta Electronica Sinica,2014,42(8):1487-1494.(in Chinese)
[4]ZAHEDI M,GHADI O R.Combining Gabor filter and FFTfor fingerprint enhancement based on a regional adaption method and automatic segmentation[J].Signal Image and Video Processing,2015,9(2):267-275.
[5]KOCEVAR M,KOTNIK B,CHOWDHURY A,KACIC Z.Real-time fingerprint image enhancement with a two-stage algorithm and block-local normalization[J/OL].Journal of Real-Time Image Processing,2014:1-10.DOI:10.1007/s11554-014-0440-z.
[6]THANH-NGHI D,PHILIPPE L,STEPHANE L.Classifying many-class high-dimensional fingerprint datasets using random forest of oblique decision trees[J].Vietnam Journal of Computer Science,2015,2(1):3-12.
[7]SUMANA K,GOUTAMS.A modified SOM-based RBFNfor rotation invariant clear and occluded fingerprint recognition[A].Intelligence Computing and Applications[C].India:Springer,2015.343:11-18.
[8]SAMAYITA B,KALYANI M.Fingerprint recognition by divide and conquer method[A].Information Systems Design and Intelligent Applications[C].India:Springer,2015.340:153-163.
[9]DHANUSHA V,SWAPNA T R.Improving the accuracy of latent fingerprint matching using texture descriptors[A].Artificial Intelligence and Evolutionary Algorithms in Engineering Systems[C].India:Springer,2015.325:695-703.
[10]CAPPELLI R,MAio D,MALTONI D.Modelling plastic distortion in fingerprint images[A].Proceedings of the 2th International Conference on Advances in Pattern Recognition[C].London:Springer-Verlag,2001.369-376.
[11]BAZEN A M,GEREZ S H.Elastic minutiae matching by means of thin-plate spline models[A].Proceedings of the16th International Conference Pattern Recognition[C].Quebec:IEEE Computer Society,2002.985-988.
[12]BAZEN A M,GEREZ S H.Fingerprint matching by thinplate spline modeling of elastic deformations[J].Pattern Recognition,2003,36(8):1859-1867.
[13]TONG X F,HUANG J H,TANG X L,et al.Fingerprint minutiae matching using the adjacent feature vector[J].Pattern Recognition Letters,2005,26(9):1337-1345.
[14]TONG X F,LIU S B,HUANG J H,et al.Local relative location error descriptor-based fingerprint minutiae matching[J].Pattern Recognition Letters,2008,29(3):286-294.
[15]罗希平,田捷.自动指纹识别中的图像增强和细节匹配算法[J].软件学报,2002,13(5):946-956.LUO Xi-ping,TIAN Jie.Image enhancement and minutia matching algorithms in automated fingerprint identification system[J].Journal of Softw are,2002,13(5):946-956.(in Chinese)
[16]陈宏,田捷.检验配准模式的指纹匹配算法[J].软件学报,2005,16(6):1046-1053.CHEN Hong,TIAN Jie.A fingerprint matching algorithm with registration pattern inspection[J].Journal of Softw are,2005,16(6):1046-1053.(in Chinese)
[17]陈晖,殷建平,祝恩.一种扭曲指纹图像的细节点修正方法[J].计算机研究与发展,2010,47(12):2141-2148.CHEN Hui,YIN Jian-ping,ZHU En.A method to adjust minutiae location and direction in nonlinear distorted fingerprint image[J].Journal of Computer Research and Development,2010,47(12):2141-2148.(in Chinese)
[18]曹国,孙权森,毛志红,梅园.一种新的形变指纹匹配方法[J].中国图象图形学报,2010,15(4):645-649.CAO Guo,SUN Quan-sen,MAO Zhi-hong,MEI Yuan.Anew algorithm for distorted fingerprint matching[J].Journal of Image and Graphics,2010,15(4):645-649.(in Chinese)
[19]陈小光,封举富.基于稳定区域的形变指纹匹配算法[J].中国图象图形学报,2010,15(8):1220-1229.CHEN Xiao-guang,FENG Ju-fu.A novel algorithm for distorted fingerprint matching using stable regions[J].Journal of Image and Graphics,2010,15(8):1220-1229.(in Chinese)
[20]王志宏,袁姮,姜文涛.基于复合梯度向量的人脸识别算法[J].自动化学报,2011,37(12):1145-1154.WANG Zhi-hong,YUAN Heng,JIANG Wen-tao.A face recognition algorithm based on composite gradient vector[J].Acta Automatica Sinica,2011,37(12):1145-1154.(in Chinese)
[21]HONG L,WAN Y F,JAIN A K.Fingerprint image enhancement:algorithm and performance evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):777-789.
[22]KAWAGOE M,TOJO A.Fingerprint pattern classification[J].Pattern Recognition,1984,17(3):295-303.
[23]CAPPELLI R,FERRERA M,FRANCO A,MALTONID.Fingerprint Verification Competition[OL].http://bias.csr.unibo.it/fvc2006.2015-10-15.
[2]詹曙,王俊,杨福猛,方琪.基于Gabor特征和字典学习的高斯混合稀疏表示图像识别[J].电子学报,2015,43(3):523-528.ZHAN Shu,WANG Jun,YANG Fu-meng,FANG Qi.Gaussian mixture sparse representation for image recognition based on Gabor features and dictionary learning[J].Acta Electronica Sinica,2015,43(3):523-528.(in Chinese)
[3]桂振文,刘越,陈靖,王涌天,徐志伟.一种适用于智能手机的图像识别算法[J].电子学报,2014,42(8):1487-1494.GUI Zhen-wen,LIU Yue,CHEN Jing,WANG Yong-tian,XU Zhi-wei.A novel image recognition algorithm for smartphones[J].Acta Electronica Sinica,2014,42(8):1487-1494.(in Chinese)
[4]ZAHEDI M,GHADI O R.Combining Gabor filter and FFTfor fingerprint enhancement based on a regional adaption method and automatic segmentation[J].Signal Image and Video Processing,2015,9(2):267-275.
[5]KOCEVAR M,KOTNIK B,CHOWDHURY A,KACIC Z.Real-time fingerprint image enhancement with a two-stage algorithm and block-local normalization[J/OL].Journal of Real-Time Image Processing,2014:1-10.DOI:10.1007/s11554-014-0440-z.
[6]THANH-NGHI D,PHILIPPE L,STEPHANE L.Classifying many-class high-dimensional fingerprint datasets using random forest of oblique decision trees[J].Vietnam Journal of Computer Science,2015,2(1):3-12.
[7]SUMANA K,GOUTAMS.A modified SOM-based RBFNfor rotation invariant clear and occluded fingerprint recognition[A].Intelligence Computing and Applications[C].India:Springer,2015.343:11-18.
[8]SAMAYITA B,KALYANI M.Fingerprint recognition by divide and conquer method[A].Information Systems Design and Intelligent Applications[C].India:Springer,2015.340:153-163.
[9]DHANUSHA V,SWAPNA T R.Improving the accuracy of latent fingerprint matching using texture descriptors[A].Artificial Intelligence and Evolutionary Algorithms in Engineering Systems[C].India:Springer,2015.325:695-703.
[10]CAPPELLI R,MAio D,MALTONI D.Modelling plastic distortion in fingerprint images[A].Proceedings of the 2th International Conference on Advances in Pattern Recognition[C].London:Springer-Verlag,2001.369-376.
[11]BAZEN A M,GEREZ S H.Elastic minutiae matching by means of thin-plate spline models[A].Proceedings of the16th International Conference Pattern Recognition[C].Quebec:IEEE Computer Society,2002.985-988.
[12]BAZEN A M,GEREZ S H.Fingerprint matching by thinplate spline modeling of elastic deformations[J].Pattern Recognition,2003,36(8):1859-1867.
[13]TONG X F,HUANG J H,TANG X L,et al.Fingerprint minutiae matching using the adjacent feature vector[J].Pattern Recognition Letters,2005,26(9):1337-1345.
[14]TONG X F,LIU S B,HUANG J H,et al.Local relative location error descriptor-based fingerprint minutiae matching[J].Pattern Recognition Letters,2008,29(3):286-294.
[15]罗希平,田捷.自动指纹识别中的图像增强和细节匹配算法[J].软件学报,2002,13(5):946-956.LUO Xi-ping,TIAN Jie.Image enhancement and minutia matching algorithms in automated fingerprint identification system[J].Journal of Softw are,2002,13(5):946-956.(in Chinese)
[16]陈宏,田捷.检验配准模式的指纹匹配算法[J].软件学报,2005,16(6):1046-1053.CHEN Hong,TIAN Jie.A fingerprint matching algorithm with registration pattern inspection[J].Journal of Softw are,2005,16(6):1046-1053.(in Chinese)
[17]陈晖,殷建平,祝恩.一种扭曲指纹图像的细节点修正方法[J].计算机研究与发展,2010,47(12):2141-2148.CHEN Hui,YIN Jian-ping,ZHU En.A method to adjust minutiae location and direction in nonlinear distorted fingerprint image[J].Journal of Computer Research and Development,2010,47(12):2141-2148.(in Chinese)
[18]曹国,孙权森,毛志红,梅园.一种新的形变指纹匹配方法[J].中国图象图形学报,2010,15(4):645-649.CAO Guo,SUN Quan-sen,MAO Zhi-hong,MEI Yuan.Anew algorithm for distorted fingerprint matching[J].Journal of Image and Graphics,2010,15(4):645-649.(in Chinese)
[19]陈小光,封举富.基于稳定区域的形变指纹匹配算法[J].中国图象图形学报,2010,15(8):1220-1229.CHEN Xiao-guang,FENG Ju-fu.A novel algorithm for distorted fingerprint matching using stable regions[J].Journal of Image and Graphics,2010,15(8):1220-1229.(in Chinese)
[20]王志宏,袁姮,姜文涛.基于复合梯度向量的人脸识别算法[J].自动化学报,2011,37(12):1145-1154.WANG Zhi-hong,YUAN Heng,JIANG Wen-tao.A face recognition algorithm based on composite gradient vector[J].Acta Automatica Sinica,2011,37(12):1145-1154.(in Chinese)
[21]HONG L,WAN Y F,JAIN A K.Fingerprint image enhancement:algorithm and performance evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(8):777-789.
[22]KAWAGOE M,TOJO A.Fingerprint pattern classification[J].Pattern Recognition,1984,17(3):295-303.
[23]CAPPELLI R,FERRERA M,FRANCO A,MALTONID.Fingerprint Verification Competition[OL].http://bias.csr.unibo.it/fvc2006.2015-10-15.