手指静脉图像分形特征提取方法
|
摘要
使用Gabor滤波增强并提取指静脉主干血管网络,通过实验对比分析3种不同的图像分维数测算方法,对指静脉主干血管网络的分维特征进行了统计分析。并提出基于二叉树模型的分形几何特征提取方法,提取血管网络的分叉角度、血管长度以及分叉层数,统计分析数据得到血管结构分形特征的一般规律,为实现手指静脉血管建模和识别奠定基础。
The main vascular network of finger vein image is enhanced and extracted by Gabor filter. Three fractal dimension calculating methods are investigated and compared, analyzing the fractal feature extracted by the best calculation method. Furthermore, a fractal geometric feature extracting method is proposed basing on binary tree model to extract the fractal geometric features of finger vascular network such as bifurcation angle, vascular length and bifurcation layer feature and obtain general rules of the network, building foundation for finger vascular network modeling and recognition.
The main vascular network of finger vein image is enhanced and extracted by Gabor filter. Three fractal dimension calculating methods are investigated and compared, analyzing the fractal feature extracted by the best calculation method. Furthermore, a fractal geometric feature extracting method is proposed basing on binary tree model to extract the fractal geometric features of finger vascular network such as bifurcation angle, vascular length and bifurcation layer feature and obtain general rules of the network, building foundation for finger vascular network modeling and recognition.
引文
[1]V LACHOS M,DERMATAS E.Vein segmentation in infrared images using compound enhancing and crisp clustering[C]//6th ICVS,Santorini,Greece,May 12-15,2008:393-402.
[2]ZHANG LIAN,ZHANG RUI,YU CHENGBO.Study on the identity authentication system on finger vein[C]//Int’l Conf on Bioinformatics and Biomedical Engineering,Shanghai,China,May 16-18,2008:1905-1907.
[3]YANG JINFENG,YANG JINLI,SHI YIHUA.Finger-vein segmentation based on multi-channel even-symmetric gabor filters[C]//Int’l Conf on Intelligent Computing and Intelligent Systems,Shanghai,China,Nov 20-22,2009:500-503.
[4]YANG JINFENG,YANG JINLI,SHI YIHUA.Combination of gabor wavelets and circular gabor filter for finger-vein extraction[C]//Int’l Conf.on Intelligent Computing,Ulsan,South Korea,Sep 16-19,2009:346-354.
[5]MEI CONGLI,XIAO XIAO,LIU GUOHAI,et al.Feature extraction of finger-vein image based on morphologic algorithm[C]//6th Int’l Conf on Fuzzy Systems and Knowledge Discovery,Tianjin,China,Aug 14-16,2009:407-411.
[6]徐鹏.树状分形分叉网络的输运特性[D].武汉:华中科技大学,2008.
[7]LORTHOIS S,CASSOT F.Fractal analysis of vascular networks:Insights from morphogenesis[J].Journal of Theoretical Biology,2010,262(4):614-633.
[8]MACKLIN P,MCDOUGALL S,ANDERSON A R A,et al.Multiscale modelling and nonlinear simulation of vascular tumour growth[J].Journal of Mathematical Biology,2009,58(4-5):765-798.
[9]顾玲玲.基于Radon变换和小波理论的静脉特征提取与匹配[D].沈阳:东北大学,2010.
[10]YANG JINFENG,SHI YIHUA.Finger-vein ROI localization and vein ridge enhancement[J].Pattern Recognition Letters,2012,33(12):1569-1579.
[11]PENG JINJIN,LI YANAN,LI RUIMEI,et al.Multimodal finger feature recognition based on traditional granulation[C]//9th CCBR,Shen-yang,China,Nov 7-9,2014:451-457.
[12]翟丽红.视网膜图像血管分割技术的研究[D].重庆:重庆大学,2015.
[13]ZHANG LIN,ZHANG LEI,ZHANG DAVID.Finger-knuckle-print:Anew biometric identifier[C]//16th IEEE International Conference on Image Processiong(ICIP),Cario,Nov 7-10,2009:1981-1984.
[14]叶德谦,李亮.一种基于模板的指纹核心定点算法[J].计算机应用研究,2009,26(7):2798-2800.
[15]杨金锋,张海金.手指静脉图像感兴趣区域提取方法研究[J].山东大学学报(工学版),2012,42(3):6-12.
[16]孙久琦.视网膜动静脉血管的识别及血管维数研究[D].北京:北京工业大学,2014.
[17]赵海英,杨光俊,徐正光.图像分形维数计算方法的比较[J].计算机系统应用,2011,20(3):238-241.
[18]谢建斌,刘通,李沛秦,等.基于二叉树的指静脉识别方法:中国,CN104463120A[P].2015-03-25.
[19]曹迪.基于结构特征的手指静脉识别方法研究[D].天津:中国民航大学,2014.
[20]JOSHI V S.Analysis of retinal vessel networks using quantitative descriptors of vascular morpholory[D].Iowa City:University of Iowa.2012.
[2]ZHANG LIAN,ZHANG RUI,YU CHENGBO.Study on the identity authentication system on finger vein[C]//Int’l Conf on Bioinformatics and Biomedical Engineering,Shanghai,China,May 16-18,2008:1905-1907.
[3]YANG JINFENG,YANG JINLI,SHI YIHUA.Finger-vein segmentation based on multi-channel even-symmetric gabor filters[C]//Int’l Conf on Intelligent Computing and Intelligent Systems,Shanghai,China,Nov 20-22,2009:500-503.
[4]YANG JINFENG,YANG JINLI,SHI YIHUA.Combination of gabor wavelets and circular gabor filter for finger-vein extraction[C]//Int’l Conf.on Intelligent Computing,Ulsan,South Korea,Sep 16-19,2009:346-354.
[5]MEI CONGLI,XIAO XIAO,LIU GUOHAI,et al.Feature extraction of finger-vein image based on morphologic algorithm[C]//6th Int’l Conf on Fuzzy Systems and Knowledge Discovery,Tianjin,China,Aug 14-16,2009:407-411.
[6]徐鹏.树状分形分叉网络的输运特性[D].武汉:华中科技大学,2008.
[7]LORTHOIS S,CASSOT F.Fractal analysis of vascular networks:Insights from morphogenesis[J].Journal of Theoretical Biology,2010,262(4):614-633.
[8]MACKLIN P,MCDOUGALL S,ANDERSON A R A,et al.Multiscale modelling and nonlinear simulation of vascular tumour growth[J].Journal of Mathematical Biology,2009,58(4-5):765-798.
[9]顾玲玲.基于Radon变换和小波理论的静脉特征提取与匹配[D].沈阳:东北大学,2010.
[10]YANG JINFENG,SHI YIHUA.Finger-vein ROI localization and vein ridge enhancement[J].Pattern Recognition Letters,2012,33(12):1569-1579.
[11]PENG JINJIN,LI YANAN,LI RUIMEI,et al.Multimodal finger feature recognition based on traditional granulation[C]//9th CCBR,Shen-yang,China,Nov 7-9,2014:451-457.
[12]翟丽红.视网膜图像血管分割技术的研究[D].重庆:重庆大学,2015.
[13]ZHANG LIN,ZHANG LEI,ZHANG DAVID.Finger-knuckle-print:Anew biometric identifier[C]//16th IEEE International Conference on Image Processiong(ICIP),Cario,Nov 7-10,2009:1981-1984.
[14]叶德谦,李亮.一种基于模板的指纹核心定点算法[J].计算机应用研究,2009,26(7):2798-2800.
[15]杨金锋,张海金.手指静脉图像感兴趣区域提取方法研究[J].山东大学学报(工学版),2012,42(3):6-12.
[16]孙久琦.视网膜动静脉血管的识别及血管维数研究[D].北京:北京工业大学,2014.
[17]赵海英,杨光俊,徐正光.图像分形维数计算方法的比较[J].计算机系统应用,2011,20(3):238-241.
[18]谢建斌,刘通,李沛秦,等.基于二叉树的指静脉识别方法:中国,CN104463120A[P].2015-03-25.
[19]曹迪.基于结构特征的手指静脉识别方法研究[D].天津:中国民航大学,2014.
[20]JOSHI V S.Analysis of retinal vessel networks using quantitative descriptors of vascular morpholory[D].Iowa City:University of Iowa.2012.