WO2018196521A1 - Procédé et dispositif de calcul de score de qualité pour image de veine de doigt - Google Patents

Procédé et dispositif de calcul de score de qualité pour image de veine de doigt Download PDF

Info

Publication number
WO2018196521A1
WO2018196521A1 PCT/CN2018/079932 CN2018079932W WO2018196521A1 WO 2018196521 A1 WO2018196521 A1 WO 2018196521A1 CN 2018079932 W CN2018079932 W CN 2018079932W WO 2018196521 A1 WO2018196521 A1 WO 2018196521A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
finger vein
points
calculating
boundary point
Prior art date
Application number
PCT/CN2018/079932
Other languages
English (en)
Chinese (zh)
Inventor
梁添才
陈侃
金晓峰
龚文川
Original Assignee
广州广电运通金融电子股份有限公司
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 广州广电运通金融电子股份有限公司 filed Critical 广州广电运通金融电子股份有限公司
Publication of WO2018196521A1 publication Critical patent/WO2018196521A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/32—Normalisation of the pattern dimensions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/14—Vascular patterns

Definitions

  • the present application relates to the field of biometrics, and more particularly to a method and apparatus for calculating a quality score of a finger vein image.
  • biometrics With the continuous development of technology, traditional methods of user identification and verification through user names and passwords are insufficient to meet the growing demand for online payment.
  • Biometrics has developed rapidly with its uniqueness. Specifically, the biometric identification technology utilizes biometric or behavioral characteristics of the human body for personal identity authentication, wherein the biometric features may include fingerprints, palms, irises, faces, etc., and the behavioral features may include actions, sounds, signatures, and the like.
  • the vein recognition technology is one of the biometric identification technologies, which achieves the purpose of identification and authentication by performing living body recognition on the vein image of the finger or the palm, and has the characteristics of high anti-counterfeiting, living body detection, high precision, and easy operation.
  • the quality of the finger vein image directly affects the accuracy of the finger vein recognition.
  • the present application provides a method and a device for calculating a quality score of a finger vein image.
  • a mass score of a finger vein image By calculating a mass score of a finger vein image, a high quality finger vein image is obtained, and the accuracy is high, thereby performing identity authentication, and the authentication efficiency is high. .
  • a method for calculating a quality score of a vein image comprising:
  • the points are accumulated and normalized to obtain a quality score of the finger vein image.
  • the acquiring a boundary point and an intermediate point of each finger vein in the binarized image includes:
  • Each column of the binarized image is vertically scanned to acquire a boundary point and an intermediate point of each finger vein, respectively.
  • the calculating an average gray level difference between the intermediate point and the boundary point comprises:
  • MeanGraz is the average gray scale difference
  • Ggra1 is a gray scale difference between gz1 and gzm
  • Ggra2 is a gray scale difference between gz2 and gzm
  • gz1, gz2, and gzm are respectively The gray values of the upper boundary point, the lower boundary point, and the intermediate point.
  • the sum of the points of different preset thresholds is added to obtain a sum of points when different thresholds are obtained, including:
  • Numk is a number of points in the average gray level difference array that is greater than a preset threshold
  • MeanGraA is an average gray level difference array between the intermediate point and the boundary point
  • Tk is the preset threshold
  • the normalized image and the binarized image of the finger vein image obtained by the quality judgment are obtained, including:
  • the normalized image is binarized to obtain a binarized image.
  • a mass score calculation device for a vein image comprising:
  • a first obtaining module configured to obtain a normalized image of the finger vein image to be quality judged and a binarized image
  • a second acquiring module configured to acquire a boundary point and an intermediate point of each finger vein in the binarized image
  • a third acquiring module configured to acquire a gray value of the boundary point and the intermediate point in the normalized image, and calculate an average gray level difference between the intermediate point and the boundary point;
  • a creating module configured to create an average gray level difference array of the intermediate point and the boundary point according to the average gray level difference
  • a calculation module configured to calculate a number of points in the average grayscale difference array that is greater than a preset threshold
  • An summation module configured to add the points of different preset thresholds to obtain a sum of points when different thresholds are obtained
  • a fourth obtaining module configured to accumulate and normalize the points, and obtain a quality score of the finger vein image.
  • the second obtaining module comprises:
  • a scanning unit configured to vertically scan each column of the binarized image, and acquire a boundary point and an intermediate point of each finger vein respectively.
  • the third obtaining module comprises:
  • Calculation unit for formulating Calculating the average gray scale difference, wherein MeanGraz is the average gray scale difference, Ggra1 is a gray scale difference between gz1 and gzm, Ggra2 is a gray scale difference between gz2 and gzm, and gz1, gz2, and gzm are respectively The gray values of the upper boundary point, the lower boundary point, and the intermediate point.
  • the adding module comprises:
  • the first acquiring module includes:
  • An acquiring unit configured to acquire a region of interest of the finger vein image determined by the quality determination, and normalize the region of interest to obtain a normalized image
  • a processing unit configured to perform binarization processing on the normalized image to obtain a binarized image.
  • the present application provides a method for calculating a quality score of a finger vein image, by obtaining a normalized image of a finger vein image to be judged by quality and a binarized image, and acquiring a binarized image.
  • the boundary point and the intermediate point of each finger vein then obtain the gray value of the boundary point and the intermediate point in the normalized image, and calculate the average gray difference between the intermediate point and the boundary point, and according to the average gray difference , creating an average gray-scale difference array of intermediate points and boundary points, and then calculating the number of points in the average gray-scale difference array that is greater than the preset threshold, and finally summing the points of different preset thresholds to obtain the sum of points when different thresholds are obtained.
  • the points are accumulated and normalized to obtain the quality score of the finger vein image. It can be seen that the program obtains high-quality finger vein images with high accuracy, and then carries out identity authentication, and the authentication efficiency is high.
  • FIG. 1 is a schematic flowchart diagram of a method for calculating a quality score of a finger vein image according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a mass score calculation device for a finger vein image according to an embodiment of the present invention.
  • the present application provides a method for calculating a quality score of a finger vein image, by obtaining a normalized image of a finger vein image to be judged by quality and a binarized image, and acquiring a boundary point of each finger vein in the binarized image and The intermediate point, then obtain the gray value of the boundary point and the intermediate point in the normalized image, and calculate the average gray difference between the intermediate point and the boundary point, and create an average of the intermediate point and the boundary point according to the average gray difference An array of grayscale differences, and then calculating the number of points in the average grayscale difference array that is greater than the preset threshold, and finally summing the points of different preset thresholds to obtain the sum of the points when different thresholds are obtained, and accumulating and normalizing the points. Processing, obtaining the quality score of the finger vein image. It can be seen that the program obtains high-quality finger vein images with high accuracy, and then carries out identity authentication, and the authentication efficiency is high.
  • FIG. 1 is a flowchart of a method for calculating a quality score of a finger vein image, which includes the following steps:
  • S1 Obtain a normalized image of the finger vein image to be judged by the quality and a binarized image.
  • step S3 Calculating, in step S3, calculating an average gray scale difference between the intermediate point and the boundary point according to a formula Calculating the average gray scale difference, wherein MeanGraz is the average gray scale difference, Ggra1 is a gray scale difference between gz1 and gzm, Ggra2 is a gray scale difference between gz2 and gzm, and gz1, gz2, and gzm are respectively The gray values of the upper boundary point, the lower boundary point, and the intermediate point.
  • MeanGraz is the average gray scale difference
  • Ggra1 is a gray scale difference between gz1 and gzm
  • Ggra2 is a gray scale difference between gz2 and gzm
  • gz1, gz2, and gzm are respectively The gray values of the upper boundary point, the lower boundary point, and the intermediate point.
  • Step S6 is based on the formula Calculating the cumulative sum of the points, wherein Numk is a number of points in the average grayscale difference array that is greater than a preset threshold, and MeanGraA is an array of average grayscale differences between the intermediate point and the boundary point, and Tk is the preset threshold.
  • Step S1 may be: first acquiring a region of interest of the finger vein image determined by the mass to be determined, and normalizing the region of interest to obtain a normalized image; and then performing binary value on the normalized image. Processing to obtain a binarized image.
  • this embodiment further provides a specific implementation manner of step S1, as follows:
  • Step 1 Collect finger vein images.
  • the specific collection process is as follows:
  • the user places the finger at a preset position of the finger vein recognition device, and the finger pressure sensing unit 2 senses the pressure of the user's finger, and notifies the control unit 5 through the cable B;
  • the control unit 5 controls the light source 1 to be turned on or off through the cable A, and the control unit 5 controls the opening of the CMOS image capturing unit 4 through the cable C to acquire the finger vein image;
  • the CMOS image acquisition unit 4 transmits the acquired image to the image storage unit 6 in accordance with the timing under the control of the control unit 5.
  • Step 2 Obtain a finger vein image f that needs to be judged from the finger vein storage unit; the process has two main steps:
  • Step 3 Extract the region of interest of the finger vein image: In order to reduce the amount of data processing, the region of interest of the finger needs to be extracted and normalized to obtain a normalized image; the specific steps are as follows:
  • i 1, . . . n ⁇ between the two boundaries are obtained, and are fitted by a straight line.
  • the method obtains the inclination angle ⁇ of the straight line;
  • the region of interest image SubF is acquired according to l1, l2, l3, and l4.
  • the region of interest image SubF is normalized to obtain a normalized image NorF of size w*h;
  • Step 4 Binarization of the normalized image: In order to effectively eliminate the interference of the background region and effectively locate the boundary point and the center point of the finger vein, binarization processing is required; the specific steps are as follows:
  • the binarized image BinF is obtained from the enhanced vein image EnF.
  • the present application provides a method and a device for calculating the quality score of a finger vein image.
  • a method and a device for calculating the quality score of a finger vein image By calculating the mass fraction of the finger vein image, a high-quality finger vein image is obtained, and the accuracy is high, and then the identity authentication is performed, and the authentication efficiency is high.
  • the embodiment further provides a mass score calculation device for a finger vein image, as shown in FIG. 2, comprising:
  • the first obtaining module 10 is configured to obtain a normalized image of the finger vein image to be quality judged and a binarized image;
  • a second obtaining module 20 configured to acquire a boundary point and an intermediate point of each finger vein in the binarized image
  • a third obtaining module 30 configured to acquire a gray value of the boundary point and the intermediate point in the normalized image, and calculate an average gray level difference between the intermediate point and the boundary point;
  • a creating module 40 configured to create an average gray level difference array of the intermediate point and the boundary point according to the average gray level difference
  • the calculating module 50 is configured to calculate a number of points in the average gray level difference array that is greater than a preset threshold
  • An summation module 60 configured to add the points of different preset thresholds to obtain a sum of points when different thresholds are obtained;
  • the fourth obtaining module 70 is configured to accumulate and perform normalization processing on the points to obtain a quality score of the finger vein image.
  • the second obtaining module includes:
  • a scanning unit configured to vertically scan each column of the binarized image, and acquire a boundary point and an intermediate point of each finger vein respectively.
  • the third obtaining module comprises:
  • Calculation unit for formulating Calculating the average gray scale difference, wherein MeanGraz is the average gray scale difference, Ggra1 is a gray scale difference between gz1 and gzm, Ggra2 is a gray scale difference between gz2 and gzm, and gz1, gz2, and gzm are respectively The gray values of the upper boundary point, the lower boundary point, and the intermediate point.
  • the adding module comprises:
  • Addition unit for formulating Calculating the cumulative sum of the points, wherein Numk is a number of points in the average grayscale difference array that is greater than a preset threshold, and MeanGraA is an array of average grayscale differences between the intermediate point and the boundary point, and Tk is the preset threshold.
  • the first acquiring module includes:
  • An acquiring unit configured to acquire a region of interest of the finger vein image determined by the quality determination, and normalize the region of interest to obtain a normalized image
  • a processing unit configured to perform binarization processing on the normalized image to obtain a binarized image.
  • the present application provides a method for calculating a quality score of a finger vein image, by obtaining a normalized image of a finger vein image to be judged by quality and a binarized image, and acquiring each finger vein of the binarized image.
  • the boundary point and the intermediate point then obtain the gray value of the boundary point and the intermediate point in the normalized image, and calculate the average gray difference between the intermediate point and the boundary point, and create an intermediate point and a boundary according to the average gray difference
  • An average gray-scale difference array of points and then, the number of points in the average gray-scale difference array that is greater than the preset threshold is calculated, and finally the points of different preset thresholds are summed to obtain the sum of points of different thresholds, and the points are accumulated and performed. Normalized processing to obtain the mass fraction of the finger vein image. It can be seen that the program obtains high-quality finger vein images with high accuracy, and then carries out identity authentication, and the authentication efficiency is high.
  • the device embodiment since it basically corresponds to the method embodiment, it can be referred to the partial description of the method embodiment.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without any creative effort.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)

Abstract

La présente invention concerne un procédé de calcul de score de qualité pour une image de veine de doigt. Le procédé consiste à : acquérir une image normalisée et une image binaire d'une image de veine de doigt dont la qualité doit être déterminée; acquérir un point limite et un point intermédiaire de chaque veine de doigt dans l'image binaire; puis acquérir des valeurs de niveau de gris du point limite et du point intermédiaire dans l'image normalisée, et calculer une différence moyenne d'échelle de gris entre le point intermédiaire et le point limite; créer une matrice de différence de niveau de gris moyenne du point intermédiaire et du point limite en fonction de la différence moyenne d'échelle de gris; calculer des points qui sont supérieurs à un seuil prédéfini dans le réseau de différence de niveau de gris moyen; enfin, additionner les points avec différents seuils prédéfinis pour obtenir des sommes cumulatives des points avec différents seuils prédéfinis; et normaliser les sommes cumulatives des points pour obtenir un score de qualité de l'image de veine de doigt. Par conséquent, au moyen de la présente solution, une image de veine de doigt de haute qualité est obtenue, une précision élevée est obtenue, puis une authentification d'identité est effectuée, et une efficacité d'authentification élevée est obtenue.
PCT/CN2018/079932 2017-04-24 2018-03-22 Procédé et dispositif de calcul de score de qualité pour image de veine de doigt WO2018196521A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710270385.7A CN108734069B (zh) 2017-04-24 2017-04-24 一种指静脉图像的质量分数计算方法及装置
CN201710270385.7 2017-04-24

Publications (1)

Publication Number Publication Date
WO2018196521A1 true WO2018196521A1 (fr) 2018-11-01

Family

ID=63920141

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/079932 WO2018196521A1 (fr) 2017-04-24 2018-03-22 Procédé et dispositif de calcul de score de qualité pour image de veine de doigt

Country Status (2)

Country Link
CN (1) CN108734069B (fr)
WO (1) WO2018196521A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110866503A (zh) * 2019-11-19 2020-03-06 圣点世纪科技股份有限公司 指静脉设备的异常检测方法及系统
CN112488935A (zh) * 2020-11-26 2021-03-12 杭州电子科技大学 基于纹理约束和泊松融合的生成对抗指静脉图像修复方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112084840A (zh) * 2020-07-24 2020-12-15 浙江工业大学 一种基于三维nmi的指静脉识别方法
CN115376167B (zh) * 2022-10-26 2023-02-24 山东圣点世纪科技有限公司 一种复杂背景下的手掌检测方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101866486A (zh) * 2010-06-11 2010-10-20 哈尔滨工程大学 手指静脉图像质量判断方法
EP2579182A1 (fr) * 2011-10-03 2013-04-10 Accenture Global Services Limited Moteur de correspondance biométrique
US20130251213A1 (en) * 2012-03-23 2013-09-26 Fujitsu Limited Biometric information processing apparatus, biometric information processing method
CN104239769A (zh) * 2014-09-18 2014-12-24 北京智慧眼科技发展有限公司 基于手指静脉特征的身份识别方法及系统
CN105975905A (zh) * 2016-04-26 2016-09-28 山西圣点世纪科技股份有限公司 一种手指静脉快速识别方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101901336B (zh) * 2010-06-11 2012-03-14 哈尔滨工程大学 指纹与指静脉双模态识别决策级融合法
CN102214297B (zh) * 2011-06-14 2012-11-28 中国人民解放军国防科学技术大学 用于特征提取的静脉图像质量检测方法
KR101315646B1 (ko) * 2012-07-25 2013-10-08 목포대학교산학협력단 가이디드 가버 필터를 이용한 지정맥 패턴 추출 방법 및 장치
CN106203497B (zh) * 2016-07-01 2019-05-31 浙江工业大学 基于图像质量评价的手指静脉感兴趣区域图像筛选方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101866486A (zh) * 2010-06-11 2010-10-20 哈尔滨工程大学 手指静脉图像质量判断方法
EP2579182A1 (fr) * 2011-10-03 2013-04-10 Accenture Global Services Limited Moteur de correspondance biométrique
US20130251213A1 (en) * 2012-03-23 2013-09-26 Fujitsu Limited Biometric information processing apparatus, biometric information processing method
CN104239769A (zh) * 2014-09-18 2014-12-24 北京智慧眼科技发展有限公司 基于手指静脉特征的身份识别方法及系统
CN105975905A (zh) * 2016-04-26 2016-09-28 山西圣点世纪科技股份有限公司 一种手指静脉快速识别方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
QIN, HUAFENG ET AL.: "Quality Assessment of Finger-Vein Image", SIGNAL & INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, 3 December 2012 (2012-12-03), Asia-Pacific, XP032310082 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110866503A (zh) * 2019-11-19 2020-03-06 圣点世纪科技股份有限公司 指静脉设备的异常检测方法及系统
CN110866503B (zh) * 2019-11-19 2024-01-05 圣点世纪科技股份有限公司 指静脉设备的异常检测方法及系统
CN112488935A (zh) * 2020-11-26 2021-03-12 杭州电子科技大学 基于纹理约束和泊松融合的生成对抗指静脉图像修复方法
CN112488935B (zh) * 2020-11-26 2024-02-06 杭州电子科技大学 基于纹理约束和泊松融合的生成对抗指静脉图像修复方法

Also Published As

Publication number Publication date
CN108734069A (zh) 2018-11-02
CN108734069B (zh) 2020-01-24

Similar Documents

Publication Publication Date Title
WO2018032861A1 (fr) Procédé et dispositif de reconnaissance de veine de doigt
WO2018196521A1 (fr) Procédé et dispositif de calcul de score de qualité pour image de veine de doigt
US9922238B2 (en) Apparatuses, systems, and methods for confirming identity
JP5504928B2 (ja) 生体認証装置、生体認証方法およびプログラム
US8872909B2 (en) Method and apparatus for personal identification using finger imaging
WO2017059591A1 (fr) Procédé et dispositif d'identification de veine de doigt
CN105740779B (zh) 人脸活体检测的方法和装置
CN104392229B (zh) 基于笔画片段方向分布特征的笔迹识别方法
WO2017161636A1 (fr) Procédé et dispositif de paiement sur terminal basé sur une empreinte digitale
JP5846291B2 (ja) 生体認証装置、生体認証方法、および生体認証プログラム
Abidin et al. Iris segmentation analysis using integro-differential and hough transform in biometric system
CN107195124A (zh) 基于掌纹和掌静脉的图书馆自助借书方法及系统
Vega et al. Biometric personal identification system based on patterns created by finger veins
JP5751019B2 (ja) 生体情報処理装置、生体情報処理方法、および生体情報処理プログラム
WO2021001322A1 (fr) Segmentation par division forcée d'images d'empreintes digitales sans contact
CN114882539B (zh) 一种静脉图像roi提取方法及装置
Zayed et al. A comprehensive survey on finger vein biometric
CN109697347A (zh) 基于指静脉和指形特征的用户特征认证方法及其装置
TWI727514B (zh) 指紋識別方法、裝置、儲存介質，及終端
JP2018169943A5 (fr)
Bendre et al. An Improved Approach for IRIS Authentication System by Using Daugman’s Rubber Sheet Model, Segmentation, Normalization and RSA Security Algorithm
Alavalapati Biometric authentication using near infrared hand vein pattern with adaptive threshold technique
Gopinath Human identification based on finger veins-a review
Sharma et al. Region of Interest Extraction for Personal Authentication Using Automated Thresholding
WO2015056210A2 (fr) Procédé d'authentification d'une personne

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18791484

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18791484

Country of ref document: EP

Kind code of ref document: A1