CN109598247A - Two dimensional code identity identifying method based on vein image minutiae point and patterned feature - Google Patents

Two dimensional code identity identifying method based on vein image minutiae point and patterned feature Download PDF

Info

Publication number
CN109598247A
CN109598247A CN201811494443.5A CN201811494443A CN109598247A CN 109598247 A CN109598247 A CN 109598247A CN 201811494443 A CN201811494443 A CN 201811494443A CN 109598247 A CN109598247 A CN 109598247A
Authority
CN
China
Prior art keywords
vein
image
feature
point
features
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201811494443.5A
Other languages
Chinese (zh)
Other versions
CN109598247B (en
Inventor
马慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Heilongjiang University
Original Assignee
Heilongjiang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Heilongjiang University filed Critical Heilongjiang University
Priority to CN201811494443.5A priority Critical patent/CN109598247B/en
Publication of CN109598247A publication Critical patent/CN109598247A/en
Application granted granted Critical
Publication of CN109598247B publication Critical patent/CN109598247B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/06Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
    • G06K19/06009Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking
    • G06K19/06037Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking multi-dimensional coding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/14Vascular patterns

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Collating Specific Patterns (AREA)

Abstract

基于静脉图像细节点与纹路特征的二维码身份识别方法。本发明的方法包括:首先对读入的手指静脉图像进行滤波增强、分割、细化等预处理操作;在此基础上提取细化后的手指静脉图像的细节点特征与纹路特征,并将这两种特征进行串联,对串联后的静脉特征采用随机正交的方式进行加密;最后,对加密后的特征采用QR码生成静脉特征的二维码图像。本发明将静脉特征与二维码进行有效的结合,并结合有效的随机正交加密处理,具有保密性强使用价值高等优点。

A two-dimensional code identification method based on vein image minutiae and texture features. The method of the present invention includes: first, performing preprocessing operations such as filtering enhancement, segmentation, and thinning on the read finger vein image; The two features are concatenated, and the concatenated vein features are encrypted in a random orthogonal way; finally, a QR code is used for the encrypted features to generate a two-dimensional code image of the vein features. The invention effectively combines the vein feature with the two-dimensional code, and combines the effective random orthogonal encryption processing, and has the advantages of strong confidentiality and high use value.

Description

基于静脉图像细节点与纹路特征的二维码身份认证方法Two-dimensional code authentication method based on vein image detail points and texture features

技术领域technical field

本发明属于模式识别技术领域,具体涉及手指静脉识别技术与二维码技术。The invention belongs to the technical field of pattern recognition, and specifically relates to a finger vein recognition technology and a two-dimensional code technology.

背景技术Background technique

静脉识别技术与掌纹识别、指纹识别等生物特征识别技术相比,除了具备唯一性、普遍性与可采集性外,还有如下几个优势:1)强免疫性:由于静脉血管是一种内部的生物特征,不易受到外界环境影响,降低了误读的可能性;2) 高防伪性:静脉血管特征分布在皮下,只能通过特定的静脉采集装置进行实时、动态的获取,这样便从根本上杜绝了身份信息(指纹、密码、卡等)被盗及伪造的情况;3) 非接触式性:静脉特征采集时,皮肤无须与采集装置接触,便能采集到静脉血管的特征信息,被采集者不会因担心数据遗留而产生排斥心理。因此,静脉识别在越来越多的场合得到了广泛的应用。随之而来的是静脉识别模板特征的安全问题,因为生物特征一旦被窃取就可以获取用户敏感的生物特征信息,对用户造成巨大的损失。针对这一问题,本发明将手指静脉图像的细节点特征与纹路特征进行特征串联,并采用随机正交的方式对串联特征进行加密,对加密后的特征使用QR码生成静脉特征的二维码图像,用于身份信息的验证,以期获得一种性能可靠、保密性强的身份识别方法。Compared with biometric identification technologies such as palmprint identification and fingerprint identification, vein identification technology has the following advantages in addition to uniqueness, universality and collectability: 1) Strong immunity: Because veins are a kind of The internal biological features are not easily affected by the external environment, which reduces the possibility of misreading; 2) High anti-counterfeiting: the characteristics of venous blood vessels are distributed under the skin, and can only be acquired in real time and dynamically through a specific venous collection device. Fundamentally eliminate the theft and forgery of identity information (fingerprints, passwords, cards, etc.); 3) Non-contact: When collecting vein characteristics, the skin can collect the characteristic information of veins without contacting the collection device. Those who are collected will not be repelled by worrying about the data being left behind. Therefore, vein recognition has been widely used in more and more occasions. Then comes the security problem of the vein recognition template feature, because once the biometric feature is stolen, the user's sensitive biometric information can be obtained, causing huge losses to the user. In order to solve this problem, the present invention concatenates the detail point features and texture features of finger vein images, encrypts the concatenated features in a random orthogonal manner, and uses QR codes to generate two-dimensional codes of vein features for the encrypted features. Images are used for the verification of identity information, in order to obtain a reliable and confidential identification method.

发明内容SUMMARY OF THE INVENTION

本发明的目的在于提供一种基于静脉图像细节点与纹路特征的二维码身份识别方法,将手指静脉图像的细节点特征与纹路特征进行特征串联,并采用随机正交的方式对串联特征进行加密,对加密后的特征使用QR码生成静脉特征的二维码图像,从而实现静脉特征向量的保护,提高生物特征的安全性。The purpose of the present invention is to provide a two-dimensional code identification method based on vein image minutiae points and texture features, which feature concatenation of the minutiae point features and texture features of finger vein images, and adopts a random orthogonal way to perform serialization on the concatenated features. Encryption, using QR code to generate a two-dimensional code image of vein feature for the encrypted feature, so as to realize the protection of vein feature vector and improve the security of biometric feature.

本发明的目的是这样实现的:The object of the present invention is achieved in this way:

一种基于静脉图像细节点特征的二维码身份识别方法,其特征是:首先对读入的手指静脉图像进行滤波增强、分割、细化等预处理操作;在此基础上提取细化后的手指静脉图像的细节点特征与纹路特征,并将这两种特征进行串联;对串联后的静脉特征采用随机正交的方式进行加密;最后,对加密后的特征采用QR码生成静脉特征的二维码图像。A two-dimensional code identification method based on the feature of the detail point of the vein image, which is characterized in that: firstly, preprocessing operations such as filtering enhancement, segmentation, and thinning are performed on the read finger vein image; The detail point features and texture features of the finger vein image, and these two features are concatenated; the concatenated vein features are encrypted in a random orthogonal way; finally, the encrypted features are generated by using QR codes to generate the second part of the vein features. QR code image.

所述的预处理操作与细节点特征提取方法,其特征是:滤波增强、分割、细化等预处理操作。具体方法为:The preprocessing operation and detail point feature extraction method are characterized by preprocessing operations such as filter enhancement, segmentation, and refinement. The specific method is:

滤波增强:本发明采用Gabor滤波增强算法对静脉图像进行滤波增强。在顺着静脉纹路的方向使用Gabor窗口函数来过滤图像,使纹路信息得到加强。由于是顺着纹路的方向滤波,在纹路方向上有平滑的作用,因此能将一些断裂的纹路进行修复。此外,Gabor滤波器具有很好的频率选择性,可以在有效地去除纹路噪声的同时,保持纹路的结构。Filter enhancement: The present invention adopts the Gabor filter enhancement algorithm to filter and enhance the vein image. Use the Gabor window function to filter the image in the direction of the vein pattern, so that the grain information is enhanced. Because it is filtered along the direction of the texture, it has a smoothing effect in the direction of the texture, so some broken textures can be repaired. In addition, the Gabor filter has good frequency selectivity, which can effectively remove the grain noise while maintaining the grain structure.

分割:由于手指静脉图像前景区域与背景区域的梯度变化明显,因此,本发明采用基于梯度场的指静脉图像分割方法。首先计算静脉图像的梯度场,然后通过梯度场中静脉纹路部分与背景部分显示的不同来分割图像的前景与背景。Segmentation: Since the gradient of the foreground area and the background area of the finger vein image changes obviously, the present invention adopts the method of segmenting the finger vein image based on the gradient field. Firstly, the gradient field of the vein image is calculated, and then the foreground and background of the image are segmented by the difference between the vein pattern part and the background part in the gradient field.

细化:采用串行细化算法对分割出的静脉纹路进行细化操作,主要步骤如下:Refinement: The serial refinement algorithm is used to refine the segmented vein lines. The main steps are as follows:

1)从指静脉二值图像第一行第一列位置开始,逐行检测目标点即像素值为1的点;1) Starting from the position of the first row and the first column of the finger vein binary image, the target point is detected row by row, that is, the point whose pixel value is 1;

2)将每个目标像素点的8邻域像素点与给定的八个消除模板分别进行比较,若均不匹配,则保留该目标点;否则再将该点的15邻域内的像素点与六个保留模板分别比较,如果符合其中任意一个保留模板,则保留该点,否则删除该点。2) Compare the 8-neighborhood pixels of each target pixel with the given eight elimination templates, if they do not match, keep the target point; otherwise, compare the pixels in the 15-neighborhood of the point with The six retention templates are compared separately, if any of the retention templates are met, the point is retained, otherwise the point is deleted.

3)转到下一个目标像素点,重复步骤2),直至遍历整幅指静脉图像的所有目标像素点,得到手指静脉细化图像。3) Go to the next target pixel and repeat step 2) until all target pixels of the entire finger vein image are traversed to obtain a finger vein refined image.

所述的静脉特征提取方法,其特征是:The described vein feature extraction method is characterized in that:

1) 细节点特征提取1) Minutiae feature extraction

在细化后的指静脉图像中采用的3×3模板来检测细节点的位置与细节点的类型(端点与交叉点)。A 3×3 template is used in the refined finger vein image to detect the location of minutiae and the type of minutiae (endpoints and intersections).

细化图像上点的交叉数定义为:The number of intersections of points on the refined image is defined as:

其中,f(k)为3×3的模板中心点的八邻域像素值(二值图像像素点的值为0或1),k取值为1,2,…,8,代表细节检测模板上对应位置的像素点,具体对应位置如图3所示。Among them, f ( k ) is the eight-neighbor pixel value of the 3×3 template center point (the value of the binary image pixel point is 0 or 1), and k is 1, 2,…, 8, representing the detail detection template The pixel points at the corresponding positions above, the specific corresponding positions are shown in Figure 3.

,则N为静脉纹路的端点;若,则N为静脉纹路的分叉点。 like , then N is the endpoint of the vein pattern; if , then N is the bifurcation point of the vein pattern.

将所有细节点类型及位置记录于特征 中,其中a i 为第i个细节点位置的行号,b i 为第i个细节点位置的列号,c i 为第i个细节点的细 节点类型,端点值为0,交叉点值为1。 Record all minutiae types and locations in the feature , where a i is the row number of the ith minutiae position, b i is the column number of the ith minutiae position, c i is the minutiae type of the ith minutiae, the endpoint value is 0, and the intersection value is 1.

将细节点位置的行号与列号的十进制数字转换为对应的二进制数字,则上述静脉特征数据均可采用二进制表示。Converting the decimal numbers of the row numbers and column numbers of the minutiae positions into corresponding binary numbers, the above vein feature data can all be represented in binary.

2) 纹路计数特征2) Texture count feature

在静脉细化图像中统计检测出的静脉纹路长度、纹路类型及纹路条数作为特征的一部 分,用F 2表示,则,其中d i 为第i个条纹路的长度,e i 为第i个纹路的类型,若该纹路起始点分别为一个端点一个交叉点用0表示,起始点均为 交叉点则用1表示,g为整幅图像中总的静脉纹路条数。 The length, type and number of vein lines detected in the vein thinning image are counted as part of the feature, represented by F 2 , then , where d i is the length of the i -th stripe road, e i is the type of the i -th stripe, if the starting point of the stripe is an endpoint and an intersection, it is represented by 0, and the starting points are all intersections, it is represented by 1, g is the total number of vein lines in the whole image.

3) 特征串联3) Feature concatenation

为了充分利用不同静脉特征的鉴别信息,本发明将上述提取出的静脉细节点特征与纹 路特征进行串联,合并为一个维数更大的向量,这样可以得到一个对生物个体具有更好分 辨能力的特征。即最终的静脉特征In order to make full use of the identification information of different vein features, the present invention connects the above-mentioned extracted vein detail point features and texture features in series, and merges them into a vector with a larger dimension. feature. the final vein feature .

所述的静脉特征加密方法,其特征是:将上述提取出的静脉图像特征中加入BCH纠错码,提高识别系统的纠错功能。对加入纠错码后的特征进行加密处理,具体方法如下:The vein feature encryption method is characterized in that: the BCH error correction code is added to the extracted vein image feature to improve the error correction function of the identification system. Encrypt the feature after adding the error correction code, and the specific method is as follows:

1)首先生成一个随机向量,随机向量的长度小于等于静脉特 征向量长度; 1) First generate a random vector , the length of the random vector is less than or equal to the length of the vein feature vector;

2)求取随机向量的正交矩阵2) Find the orthogonal matrix of random vectors ;

3)求取正交矩阵与静脉特征矩阵F的内积Y3) Find the orthogonal matrix Inner product Y with vein feature matrix F ;

4)将Y中每一维数据与预设阈值进行比较,大于阈值将该维数据置为0,否则置为1,最后得到一组二进制的加密后的静脉特征向量。4) Compare each dimension data in Y with a preset threshold, set the dimension data to 0 if the value is greater than the threshold, and set it to 1 otherwise, and finally obtain a set of binary encrypted vein feature vectors.

本发明的主要贡献和特点在于:The main contributions and features of the present invention are:

本发明针对个人手指静脉特征模板存在的可能被破坏与盗取等安全性问题,提出了一种基于手指静脉特征的二维码身份认证方法,将提取出的手指静脉特征进行随机正交加密后进行QR 编码,使其变成二维码图像用于身份信息的验证,以期获得一种具有保密性强、使用价值高的身份认证方法。Aiming at the security problems that the personal finger vein feature template may be destroyed and stolen, the present invention proposes a two-dimensional code identity authentication method based on the finger vein feature. The extracted finger vein feature is subjected to random orthogonal encryption. Carry out QR code to make it into a two-dimensional code image for identity information verification, in order to obtain an identity authentication method with strong confidentiality and high use value.

附图说明Description of drawings

图1本发明主要流程图。Fig. 1 main flow chart of the present invention.

图2 细化方法流程图。Figure 2. Flow chart of the refinement method.

图3 细节检测模板。Figure 3 Detail detection template.

具体实施方式Detailed ways

下面结合附图举例对本发明做更详细地描述:The present invention will be described in more detail below in conjunction with the accompanying drawings:

1 手指静脉图像预处理1 Finger vein image preprocessing

首先对读入的手指静脉图像进行滤波增强、图像分割、细化等预处理操作。具体方法为:Firstly, preprocessing operations such as filtering enhancement, image segmentation, and thinning are performed on the read finger vein image. The specific method is:

1.1滤波增强1.1 Filter enhancement

本发明采用Gabor滤波增强算法对静脉图像进行滤波增强。在顺着静脉纹路的方向使用Gabor窗口函数来过滤图像,使纹路信息得到加强。由于是顺着纹路的方向滤波,在纹路方向上有平滑的作用,因此能将一些断裂的纹路进行修复。此外,Gabor滤波器具有很好的频率选择性,可以在有效地去除纹路噪声的同时,保持纹路的结构。The invention adopts the Gabor filter enhancement algorithm to filter and enhance the vein image. Use the Gabor window function to filter the image in the direction of the vein pattern, so that the grain information is enhanced. Because it is filtered along the direction of the texture, it has a smoothing effect in the direction of the texture, so some broken textures can be repaired. In addition, the Gabor filter has good frequency selectivity, which can effectively remove the grain noise while maintaining the grain structure.

1.2分割1.2 Segmentation

由于手指静脉图像前景区域与背景区域的梯度变化明显,因此,本发明采用基于梯度场的指静脉图像分割方法。首先计算静脉图像的梯度场,然后通过梯度场中静脉纹路部分与背景部分显示的不同来分割图像的前景与背景。Since the gradient of the foreground area and the background area of the finger vein image changes obviously, the present invention adopts the method of segmenting the finger vein image based on the gradient field. Firstly, the gradient field of the vein image is calculated, and then the foreground and background of the image are segmented by the difference between the vein pattern part and the background part in the gradient field.

1.3细化1.3 Refinement

采用串行细化算法对分割出的静脉纹路进行细化操作,主要步骤如下:The serial thinning algorithm is used to refine the segmented vein lines. The main steps are as follows:

1)从指静脉二值图像第一行第一列位置开始,逐行检测目标点即像素值为1的点;1) Starting from the position of the first row and the first column of the finger vein binary image, the target point is detected row by row, that is, the point whose pixel value is 1;

2)将每个目标像素点的8邻域像素点与给定的八个消除模板分别进行比较,若均不匹配,则保留该目标点;否则再将该点的15邻域内的像素点与六个保留模板分别比较,如果符合其中任意一个保留模板,则保留该点,否则删除该点;2) Compare the 8-neighborhood pixels of each target pixel with the given eight elimination templates, if they do not match, keep the target point; otherwise, compare the pixels in the 15-neighborhood of the point with The six retention templates are compared separately, if any of the retention templates are met, the point is retained, otherwise the point is deleted;

3)转到下一个目标像素点,重复步骤2),直至遍历整幅指静脉图像的所有目标像素点,得到手指静脉细化图像。整个细化方法流程图如图2所示。3) Go to the next target pixel and repeat step 2) until all target pixels of the entire finger vein image are traversed to obtain a finger vein refined image. The flow chart of the whole refinement method is shown in Figure 2.

2 手指静脉图像特征提取2 Feature extraction of finger vein images

2.1细节点特征提取2.1 Minutiae feature extraction

在细化后的指静脉图像中采用的3×3模板来检测细节点的位置与细节点的类型(端点与交叉点)。A 3×3 template is used in the refined finger vein image to detect the location of minutiae and the type of minutiae (endpoints and intersections).

细化图像上点的交叉数定义为:The number of intersections of points on the refined image is defined as:

其中,f(k)为3×3的模板中心点的八邻域像素值(二值图像像素点的值为0或1),k取值为1,2,…,8,代表细节检测模板上对应位置的像素点,具体对应位置如图3所示。Among them, f ( k ) is the eight-neighbor pixel value of the 3×3 template center point (the value of the binary image pixel point is 0 or 1), and k is 1, 2,…, 8, representing the detail detection template The pixel points at the corresponding positions above, the specific corresponding positions are shown in Figure 3.

,则N为静脉纹路的端点;若,则N为静脉纹路的分叉点。 like , then N is the endpoint of the vein pattern; if , then N is the bifurcation point of the vein pattern.

将所有细节点类型及位置记录于特征 中,其中a i 为第i个细节点位置的行号,b i 为第i个细节点位置的列号,c i 为第i个细节点的细 节点类型,端点值为0,交叉点值为1。 Record all minutiae types and locations in the feature , where a i is the row number of the ith minutiae position, b i is the column number of the ith minutiae position, c i is the minutiae type of the ith minutiae, the endpoint value is 0, and the intersection value is 1.

将细节点位置的行号与列号的十进制数字转换为对应的二进制数字,则上述静脉特征数据均可采用二进制表示。Converting the decimal numbers of the row numbers and column numbers of the minutiae positions into corresponding binary numbers, the above vein feature data can all be represented in binary.

2.2 纹路计数特征2.2 Texture count feature

在静脉细化图像中统计检测出的静脉纹路长度、纹路类型及纹路条数作为特征的一部 分,用F 2表示,则,其中d i 为第i个条纹路的长度,e i 为第i个纹路的类型,若该纹路起始点分别为一个端点一个交叉点用0表示,起始点均为 交叉点则用1表示,g为整幅图像中总的静脉纹路条数。 The length, type and number of vein lines detected in the vein thinning image are counted as part of the feature, represented by F 2 , then , where d i is the length of the i -th stripe road, e i is the type of the i -th stripe, if the starting point of the stripe is an endpoint and an intersection, it is represented by 0, and the starting points are all intersections, it is represented by 1, g is the total number of vein lines in the whole image.

2.3 特征串联2.3 Feature concatenation

为了充分利用不同静脉特征的鉴别信息,本发明将上述提取出的静脉细节点特征与纹 路特征进行串联,合并为一个维数更大的向量,这样可以得到一个对生物个体具有更好分 辨能力的特征。即最终的静脉特征In order to make full use of the identification information of different vein features, the present invention connects the above-mentioned extracted vein detail point features and texture features in series, and merges them into a vector with a larger dimension. feature. the final vein feature .

3. 静脉图像特征加密3. Vein Image Feature Encryption

将上述提取出的静脉图像特征中加入BCH纠错码,提高识别系统的纠错功能。对加入纠错码后的特征进行加密处理,具体方法如下:The BCH error correction code is added to the vein image features extracted above to improve the error correction function of the identification system. Encrypt the feature after adding the error correction code, and the specific method is as follows:

1)首先生成一个随机向量,随机向量的长度小于等于静脉特 征向量长度; 1) First generate a random vector , the length of the random vector is less than or equal to the length of the vein feature vector;

2)求取随机向量的正交矩阵2) Find the orthogonal matrix of random vectors ;

3)求取正交矩阵与静脉特征矩阵F的内积Y3) Find the orthogonal matrix Inner product Y with vein feature matrix F ;

4)将Y中每一维数据与预设阈值进行比较,大于阈值将该维数据置为0,否则置为1,最后得到一组二进制的加密后的静脉特征向量。4) Compare each dimension data in Y with a preset threshold, set the dimension data to 0 if the value is greater than the threshold, and set it to 1 otherwise, and finally obtain a set of binary encrypted vein feature vectors.

4 .基于手指静脉特征的二维码生成与身份认证4. QR code generation and identity authentication based on finger vein features

本发明将上述经过加密的静脉特征采用QR码生成静脉二维码图像。手指静脉图像特征二维码编码步骤如下:In the present invention, the above encrypted vein feature is used to generate a vein two-dimensional code image by QR code. The steps of QR code encoding of finger vein image features are as follows:

1) 静脉特征数据分析,构造码字序列;1) Analysis of vein feature data to construct codeword sequence;

2) 在码字序列中置模;2) Set the modulo in the codeword sequence;

3) 掩模;3) mask;

4) 确定QR码的版本信息;4) Determine the version information of the QR code;

5) 生成静脉特征的二维码图像。5) Generate a QR code image of vein features.

5. 静脉二维码身份验证5. Vein QR code authentication

静脉二维码身份验证过程如下:The vein QR code authentication process is as follows:

1)对生成的静脉二维码图像进行QR码解码操作;1) Perform a QR code decoding operation on the generated vein QR code image;

2)对解码后的特征序列进行解密操作,获取原图像特征;2) Decrypt the decoded feature sequence to obtain the original image features;

3)再通过比对待识别静脉图像特征与模板样本的特征向量之间的欧式距离来实现最终的匹配识别,完成身份认证。3) Then, by comparing the Euclidean distance between the feature vector of the vein image to be identified and the feature vector of the template sample, the final matching and identification are realized, and the identity authentication is completed.

Claims (4)

1.一种基于静脉图像细节点与纹路特征的二维码身份识别方法,其特征是:首先对读入的手指静脉图像进行滤波增强、分割、细化等预处理操作;在此基础上提取细化后的手指静脉图像的细节点特征与纹路特征,并将这两种特征进行串联;对串联后的静脉特征采用随机正交的方式进行加密;最后,对加密后的特征采用QR码生成静脉特征的二维码图像。1. A two-dimensional code identification method based on vein image detail points and texture features, is characterized in that: at first, preprocessing operations such as filtering enhancement, segmentation, and thinning are performed on the read-in finger vein image; The detailed point features and texture features of the refined finger vein image are concatenated; the concatenated vein features are encrypted in a random orthogonal way; finally, the encrypted features are generated by QR code QR code image of vein features. 2.根据权利要求1所述的预处理操作与细节点特征提取方法,其特征是:滤波增强、分割、细化等预处理操作,具体方法为:2. The preprocessing operation and detail point feature extraction method according to claim 1, characterized in that: preprocessing operations such as filter enhancement, segmentation, and refinement, and the concrete method is: 滤波增强:本发明采用Gabor滤波增强算法对静脉图像进行滤波增强;在顺着静脉纹路的方向使用Gabor窗口函数来过滤图像,使纹路信息得到加强;由于是顺着纹路的方向滤波,在纹路方向上有平滑的作用,因此能将一些断裂的纹路进行修复;此外,Gabor滤波器具有很好的频率选择性,可以在有效地去除纹路噪声的同时,保持纹路的结构;Filtering enhancement: the present invention uses the Gabor filter enhancement algorithm to filter and enhance the vein image; the Gabor window function is used to filter the image in the direction of the vein texture, so that the texture information is enhanced; There is a smoothing effect on the filter, so some broken lines can be repaired; in addition, the Gabor filter has good frequency selectivity, which can effectively remove the grain noise while maintaining the structure of the grain; 分割:由于手指静脉图像前景区域与背景区域的梯度变化明显,因此,本发明采用基于梯度场的指静脉图像分割方法;首先计算静脉图像的梯度场,然后通过梯度场中静脉纹路部分与背景部分显示的不同来分割图像的前景与背景;Segmentation: Since the gradient between the foreground area and the background area of the finger vein image changes obviously, the present invention adopts the method of segmenting the finger vein image based on the gradient field; first, the gradient field of the vein image is calculated, and then the vein pattern part and the background part in the gradient field are calculated. Display the difference to segment the foreground and background of the image; 细化:采用串行细化算法对分割出的静脉纹路进行细化操作,主要步骤如下:Refinement: The serial refinement algorithm is used to refine the segmented vein lines. The main steps are as follows: 1)从指静脉二值图像第一行第一列位置开始,逐行检测目标点即像素值为1的点;1) Starting from the position of the first row and the first column of the finger vein binary image, the target point is detected row by row, that is, the point whose pixel value is 1; 2)将每个目标像素点的8邻域像素点与给定的八个消除模板分别进行比较,若均不匹配,则保留该目标点;否则再将该点的15邻域内的像素点与六个保留模板分别比较,如果符合其中任意一个保留模板,则保留该点,否则删除该点;2) Compare the 8-neighborhood pixels of each target pixel with the given eight elimination templates, if they do not match, keep the target point; otherwise, compare the pixels in the 15-neighborhood of the point with The six retention templates are compared separately, if any of the retention templates are met, the point is retained, otherwise the point is deleted; 3)转到下一个目标像素点,重复步骤2),直至遍历整幅指静脉图像的所有目标像素点,得到手指静脉细化图像。3) Go to the next target pixel and repeat step 2) until all target pixels of the entire finger vein image are traversed to obtain a finger vein refined image. 3.根据权利要求1所述的静脉特征提取方法,其特征是:3. vein feature extraction method according to claim 1 is characterized in that: 1)细节点特征提取1) Feature extraction of minutiae points 在细化后的指静脉图像中采用3×3的模板来检测细节点的位置与细节点的类型(端点与交叉点);In the refined finger vein image, a 3×3 template is used to detect the location of minutiae and the type of minutiae (endpoints and intersections); 细化图像上点的交叉数定义为:The number of intersections of points on the refined image is defined as: 其中,f(k)为3×3的模板中心点的八邻域像素值(二值图像像素点的值为0或1),k取值为1,2,…,8,代表细节检测模板上对应位置的像素点,具体对应位置如图3所示;Among them, f ( k ) is the eight-neighbor pixel value of the 3×3 template center point (the value of the binary image pixel point is 0 or 1), and k is 1, 2,…, 8, representing the detail detection template The pixel points at the corresponding positions on the top, the specific corresponding positions are shown in Figure 3; ,则N为静脉纹路的端点;若,则N为静脉纹路的分叉点; like , then N is the endpoint of the vein pattern; if , then N is the bifurcation point of the vein pattern; 将所有细节点类型及位置记录于特征 中,其中a i 为第i个细节点位置的行号,b i 为第i个细节点位置的列号,c i 为第i个细节点的细 节点类型,端点值为0,交叉点值为1; Record all minutiae types and locations in the feature , where a i is the row number of the ith minutiae position, b i is the column number of the ith minutiae position, c i is the minutiae type of the ith minutiae, the endpoint value is 0, and the intersection value is 1; 将细节点位置的行号与列号的十进制数字转换为对应的二进制数字,则上述静脉特征数据均可采用二进制表示;Convert the decimal number of the row number and column number of the detail point position into the corresponding binary number, then the above vein feature data can be represented in binary; 2)纹路计数特征2) Texture count feature 在静脉细化图像中统计检测出的静脉纹路长度、纹路类型及纹路条数作为特征的一部 分,用F 2表示,则,其中d i 为第i个条纹路的长度,e i 为第i个纹路的类型,若该纹路起始点分别为一个端点一个交叉点用0表示,起始点均为 交叉点则用1表示,g为整幅图像中总的静脉纹路条数; The length, type and number of vein lines detected in the vein thinning image are counted as part of the feature, represented by F 2 , then , where d i is the length of the i -th stripe road, e i is the type of the i -th stripe, if the starting point of the stripe is an endpoint and an intersection, it is represented by 0, and the starting points are all intersections, it is represented by 1, g is the total number of vein lines in the whole image; 3)特征串联3) Feature concatenation 为了充分利用不同静脉特征的鉴别信息,本发明将上述提取出的静脉细节点特征与纹 路特征进行串联,合并为一个维数更大的向量,这样可以得到一个对生物个体具有更好分 辨能力的特征,即最终的静脉特征In order to make full use of the identification information of different vein features, the present invention connects the above-mentioned extracted vein detail point features and texture features in series, and merges them into a vector with a larger dimension. feature, the final vein feature . 4.根据权利要求1所述的静脉特征加密方法,其特征是:将上述提取出的静脉图像特征中加入BCH纠错码,提高识别系统的纠错功能;对加入纠错码后的特征进行加密处理,具体方法如下:4. vein feature encryption method according to claim 1 is characterized in that: BCH error correction code is added in the vein image feature of above-mentioned extraction, improves the error correction function of identification system; The feature after adding error correction code is carried out Encryption processing, the specific method is as follows: 1)首先生成一个随机向量,随机向量的长度小于等于静脉特征 向量长度; 1) First generate a random vector , the length of the random vector is less than or equal to the length of the vein feature vector; 2)求取随机向量的正交矩阵2) Find the orthogonal matrix of random vectors ; 3)求取正交矩阵与静脉特征矩阵F的内积Y3) Find the orthogonal matrix Inner product Y with vein feature matrix F ; 4)将Y中每一维数据与预设阈值进行比较,大于阈值将该维数据置为0,否则置为1,最后得到一组二进制的加密后的静脉特征向量。4) Compare each dimension data in Y with a preset threshold, set the dimension data to 0 if the value is greater than the threshold, and set it to 1 otherwise, and finally obtain a set of binary encrypted vein feature vectors.
CN201811494443.5A 2018-12-07 2018-12-07 Two-dimensional code identity authentication method based on vein image detail point and grain characteristics Active CN109598247B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811494443.5A CN109598247B (en) 2018-12-07 2018-12-07 Two-dimensional code identity authentication method based on vein image detail point and grain characteristics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811494443.5A CN109598247B (en) 2018-12-07 2018-12-07 Two-dimensional code identity authentication method based on vein image detail point and grain characteristics

Publications (2)

Publication Number Publication Date
CN109598247A true CN109598247A (en) 2019-04-09
CN109598247B CN109598247B (en) 2022-09-06

Family

ID=65961399

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811494443.5A Active CN109598247B (en) 2018-12-07 2018-12-07 Two-dimensional code identity authentication method based on vein image detail point and grain characteristics

Country Status (1)

Country Link
CN (1) CN109598247B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109993142A (en) * 2019-04-10 2019-07-09 黑龙江大学 Two-dimensional code identity authentication method based on finger multimodal biometrics
CN109993257A (en) * 2019-04-10 2019-07-09 黑龙江大学 A two-dimensional code based on vein features
CN110135142A (en) * 2019-04-30 2019-08-16 成都甄识科技有限公司 A Method for Reticular Physiological Texture Characterization Based on Geometric Slope
CN111209851A (en) * 2020-01-04 2020-05-29 圣点世纪科技股份有限公司 Finger vein identification method based on finger ventral vein and finger dorsal vein deep fusion
CN112102209A (en) * 2020-11-17 2020-12-18 四川圣点世纪科技有限公司 Abnormal vein image restoration method and device
CN112668412A (en) * 2020-12-15 2021-04-16 深兰科技(上海)有限公司 Two-dimensional code generation method and device, electronic equipment and storage medium
CN113052045A (en) * 2021-03-17 2021-06-29 中国工商银行股份有限公司 Method, apparatus, computing device and medium for recognizing finger vein image
CN115223211A (en) * 2022-09-20 2022-10-21 山东圣点世纪科技有限公司 Identification method for converting vein image into fingerprint image

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102063740A (en) * 2010-11-15 2011-05-18 北京交通大学 Real-name railway ticket detecting system based on palm vein network characteristic authentication
CN201993808U (en) * 2011-04-13 2011-09-28 甄为忠 Intelligent instrument safety-management system
CN103870733A (en) * 2014-02-27 2014-06-18 中国船舶重工集团公司第七一〇研究所 Staff-identity monitoring system and terminal based on finger vein recognition
US20150063661A1 (en) * 2013-09-03 2015-03-05 Samsung Electronics Co., Ltd. Method and computer-readable recording medium for recognizing object using captured image
CN105956579A (en) * 2016-05-27 2016-09-21 国创科视科技股份有限公司 Rapid finger vein identification method integrating fuzzy template and point characteristics
CN106330464A (en) * 2016-10-26 2017-01-11 上海众人网络安全技术有限公司 An identity authentication method, device and system
CN206249318U (en) * 2016-10-26 2017-06-13 广西理工职业技术学院 A kind of encryption identity card Intelligent Recognition management system
CN107862282A (en) * 2017-11-07 2018-03-30 深圳市金城保密技术有限公司 A kind of finger vena identification and safety certifying method and its terminal and system
CN108304701A (en) * 2017-01-13 2018-07-20 阳振庭 A kind of method and system for generating identity and writing comments on a document
CN108306738A (en) * 2017-01-13 2018-07-20 阳振庭 A kind of method and system of identification identity
CN108319911A (en) * 2018-01-30 2018-07-24 深兰科技(上海)有限公司 Biometric identity certification and payment system based on the identification of hand arteries and veins and identity identifying method
CN108846269A (en) * 2018-06-04 2018-11-20 黑龙江大学 One kind is towards manifold identity identifying method and identification authentication system

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102063740A (en) * 2010-11-15 2011-05-18 北京交通大学 Real-name railway ticket detecting system based on palm vein network characteristic authentication
CN201993808U (en) * 2011-04-13 2011-09-28 甄为忠 Intelligent instrument safety-management system
US20150063661A1 (en) * 2013-09-03 2015-03-05 Samsung Electronics Co., Ltd. Method and computer-readable recording medium for recognizing object using captured image
CN103870733A (en) * 2014-02-27 2014-06-18 中国船舶重工集团公司第七一〇研究所 Staff-identity monitoring system and terminal based on finger vein recognition
CN105956579A (en) * 2016-05-27 2016-09-21 国创科视科技股份有限公司 Rapid finger vein identification method integrating fuzzy template and point characteristics
CN106330464A (en) * 2016-10-26 2017-01-11 上海众人网络安全技术有限公司 An identity authentication method, device and system
CN206249318U (en) * 2016-10-26 2017-06-13 广西理工职业技术学院 A kind of encryption identity card Intelligent Recognition management system
CN108304701A (en) * 2017-01-13 2018-07-20 阳振庭 A kind of method and system for generating identity and writing comments on a document
CN108306738A (en) * 2017-01-13 2018-07-20 阳振庭 A kind of method and system of identification identity
CN107862282A (en) * 2017-11-07 2018-03-30 深圳市金城保密技术有限公司 A kind of finger vena identification and safety certifying method and its terminal and system
CN108319911A (en) * 2018-01-30 2018-07-24 深兰科技(上海)有限公司 Biometric identity certification and payment system based on the identification of hand arteries and veins and identity identifying method
CN108846269A (en) * 2018-06-04 2018-11-20 黑龙江大学 One kind is towards manifold identity identifying method and identification authentication system

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
HUI MA: "Finger Vein Identification Based on 2DPCA", 《ADVANCED MATERIALS RESEARCH》 *
JIANAN TANG等: "A review of recent advances in identity identification technology based on biological features", 《BIG DATA 2018》 *
彭加亮: "基于手指多模态生物特征的身份认证关键问题研究", 《中国博士学位论文全文数据库 信息科技辑》 *
赵建国: "基于人体手指静脉特征的身份认证系统设计", 《信息通信》 *
陈暄: "基于手指静脉特征图像的加密研究", 《计算机测量与控制》 *
马慧: "指纹与指静脉双模态识别决策级融合方法", 《华中科技大学学报(自然科学版)》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109993142A (en) * 2019-04-10 2019-07-09 黑龙江大学 Two-dimensional code identity authentication method based on finger multimodal biometrics
CN109993257A (en) * 2019-04-10 2019-07-09 黑龙江大学 A two-dimensional code based on vein features
CN109993142B (en) * 2019-04-10 2023-09-12 黑龙江大学 QR code identity authentication method based on finger multi-modal biometric features
CN110135142A (en) * 2019-04-30 2019-08-16 成都甄识科技有限公司 A Method for Reticular Physiological Texture Characterization Based on Geometric Slope
CN111209851A (en) * 2020-01-04 2020-05-29 圣点世纪科技股份有限公司 Finger vein identification method based on finger ventral vein and finger dorsal vein deep fusion
CN112102209A (en) * 2020-11-17 2020-12-18 四川圣点世纪科技有限公司 Abnormal vein image restoration method and device
CN112102209B (en) * 2020-11-17 2021-02-19 四川圣点世纪科技有限公司 Abnormal vein image restoration method and device
CN112668412A (en) * 2020-12-15 2021-04-16 深兰科技(上海)有限公司 Two-dimensional code generation method and device, electronic equipment and storage medium
CN113052045A (en) * 2021-03-17 2021-06-29 中国工商银行股份有限公司 Method, apparatus, computing device and medium for recognizing finger vein image
CN115223211A (en) * 2022-09-20 2022-10-21 山东圣点世纪科技有限公司 Identification method for converting vein image into fingerprint image

Also Published As

Publication number Publication date
CN109598247B (en) 2022-09-06

Similar Documents

Publication Publication Date Title
CN109598247B (en) Two-dimensional code identity authentication method based on vein image detail point and grain characteristics
Chin et al. High security iris verification system based on random secret integration
Sumalatha et al. A comprehensive review of unimodal and multimodal fingerprint biometric authentication systems: Fusion, attacks, and template protection
CN109993142B (en) QR code identity authentication method based on finger multi-modal biometric features
CN109635756B (en) Two-dimensional code authentication method integrating fingerprint and finger vein
Lee et al. Secure user identification for consumer electronics devices
CN109886202B (en) IoM-based revocable palmprint competitive code feature recognition method
Arunachalam et al. AES Based Multimodal Biometric Authentication using Cryptographic Level Fusion with Fingerprint and Finger Knuckle Print.
Prasanalakshmi et al. Biometric cryptosystem involving two traits and palm vein as key
Nagar et al. Alignment and bit extraction for secure fingerprint biometrics
Kanjan et al. A comparative study of fingerprint matching algorithms
Khallaf et al. Implementation of quaternion mathematics for biometric security
Nadiya et al. Dorsal hand vein biometric recognition based on orientation of local binary pattern
Prasanalakshmi et al. Multimodal biometric cryptosystem involving face, fingerprint and palm vein
Esan et al. Bimodal biometrics for financial infrastructure security
Kaur Multimodal biometrics feature level fusion for iris and hand geometry using chaos-based encryption technique
Choudhary et al. Multi-instance finger vein-based authentication with secured templates
Tantubay et al. A Survey of Biometric Key-Binding Biocrypto-System Using Different Techniques
Teng et al. Finger Vein Template Protection with Directional Bloom Filter
EP3093793A1 (en) Fingerprint identification method and device using same
Brindha Finger knuckle print as unimodal fuzzy vault implementation
Kumar et al. Fingerprint matching based on orientation feature
Kaizhi et al. An enhancing fingerprint template protection method
Praseetha et al. Novel Web Service Based Fingerprint Identification Using Steganography and Xml Mining
Joshi et al. Reversible watermarking technique to enhance security of a biometric authentication system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant