WO2018032861A1 - Procédé et dispositif de reconnaissance de veine de doigt - Google Patents

Procédé et dispositif de reconnaissance de veine de doigt Download PDF

Info

Publication number
WO2018032861A1
WO2018032861A1 PCT/CN2017/087124 CN2017087124W WO2018032861A1 WO 2018032861 A1 WO2018032861 A1 WO 2018032861A1 CN 2017087124 W CN2017087124 W CN 2017087124W WO 2018032861 A1 WO2018032861 A1 WO 2018032861A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
finger vein
region
interest
binary
Prior art date
Application number
PCT/CN2017/087124
Other languages
English (en)
Chinese (zh)
Inventor
罗攀峰
陈侃
梁添才
金晓峰
黎明
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 WO2018032861A1 publication Critical patent/WO2018032861A1/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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • 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 finger vein recognition method and apparatus.
  • 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 present application provides a finger vein recognition method and device, which performs feature matching by collecting finger veins and multi-angle finger vein mosaic images, thereby realizing finger vein recognition, high accuracy, and then identity authentication. Certification is efficient.
  • a finger vein recognition method includes:
  • the image of the region of interest is matched with the target matching image, and if the matching is successful, the finger vein recognition is passed.
  • the matching the image of the region of interest with the target matching image according to the binary structure algorithm comprises:
  • the calculating the similarity between the first binary image and the second binary image comprises:
  • the similarity of the first binary image and the second binary image is obtained by calculating pixels in which the expanded images of the first refined image and the second refined image overlap.
  • the method further includes:
  • the finger vein images of the plurality of angles are stitched into a target matching image.
  • the stitching the plurality of angles of the finger vein images into a target matching image comprises:
  • the registration images are added to obtain the target matching image.
  • the horizontal rotation, the horizontal displacement correction, and the size normalization processing are performed on the plurality of the finger vein images, including:
  • the vein image is normalized to obtain an image of a preset size.
  • the acquiring the region of interest on the corrected image comprises:
  • the region of interest is acquired according to the l i1 , l i2 , l i3 , and l i4 .
  • a finger vein recognition device comprising:
  • a first acquiring module configured to collect a finger vein image, and acquire an image of the region of interest corresponding to the finger vein image
  • the identification module is configured to match the image of the region of interest with the target matching image according to the binary structure algorithm, and if the matching is successful, the finger vein recognition is passed.
  • the identification module comprises:
  • a first processing module configured to perform smoothing processing on the image of the region of interest in the target matching image to obtain an image to be matched
  • a second processing module configured to perform binarization processing on the image of the region of interest and the image to be matched, to obtain a first binary image and a second binary image
  • a calculating module configured to calculate a similarity between the first binary image and the second binary image.
  • the method further includes:
  • a second acquiring module configured to acquire a finger vein image of multiple angles
  • a splicing module for splicing the finger vein images of a plurality of angles into a target matching image.
  • a finger vein recognition method disclosed in the present application acquires a plurality of angles of the finger vein image and stitches the finger vein images of a plurality of angles into a target matching image to obtain an interest. An image of the region, and matching the image of the region of interest with the target matching image, and if the matching is successful, characterizing the finger vein recognition. It can be seen that the program collects finger vein images at different angles and performs feature matching to realize finger vein recognition, high accuracy, and then identity authentication, and the authentication efficiency is high.
  • FIG. 1 is a flowchart of a finger vein recognition method disclosed in the embodiment
  • FIG. 2 is still another flowchart of a method for identifying a finger vein according to the embodiment
  • FIG. 3 is still another flowchart of a finger vein recognition method disclosed in the embodiment.
  • FIG. 1 is a flowchart of a method for identifying a finger vein according to an embodiment of the present invention, including the steps of:
  • S1 acquiring a finger vein image, and acquiring an image of the region of interest corresponding to the finger vein image;
  • S2 Matching the image of the region of interest to the target matching image according to a binary structure algorithm, and if the matching is successful, characterizing the finger vein recognition.
  • the finger vein images of multiple angles are acquired, and then the images are matched and synthesized by the features, the finger veins are recognized, the accuracy is high, and the identity authentication is performed, and the authentication efficiency is high.
  • the embodiment may further include the following steps:
  • S4 splicing the finger vein images of the plurality of angles into a target matching image.
  • FIG. 2 and FIG. 3 Please refer to FIG. 2 and FIG. 3 for a detailed description of the finger vein recognition method provided by the present solution, wherein multiple angles may be two or more angles, and an example of a finger vein image that collects three angles is taken as an example.
  • the introduction of the program mainly includes the following steps:
  • Step 1 Obtain three angles for vein image acquisition, such as:
  • the light source 1 emits light, the light source 2 and the light source 3 do not emit light, and the image f 1 is acquired;
  • the light source 2 emits light, the light source 1 and the light source 3 do not emit light, and the image f 2 is acquired;
  • the light source 3 emits light, the light source 1 and the light source 2 do not emit light, and the image f 3 is acquired;
  • Step 2 Finger vein image mosaic fusion: the finger vein images f 1 , f 2 and f 3 of the user's multiple angles are spliced into a mosaic image (user matching template).
  • the image stitching technology is mainly divided into three main steps: image preprocessing, image registration and image fusion, as follows:
  • Image registration Image NorF 1 and NorF 3 are used as target images, and NorF 2 is used as reference image to realize image registration of finger vein images collected at different angles.
  • the specific process is as follows:
  • m 2 and m 5 represent the amounts of translation of the two figures, respectively, m 0 , m 1 , m 3 and m 4 represent the scale and the amount of rotation, respectively, and m 6 and m 7 represent the amount of deformation in the horizontal and vertical directions.
  • Equation 2 Perform a Fourier transform on both sides of Equation 2 and calculate the cross power spectrum, ie:
  • Equation 3 Perform an inverse Fourier change on Equation 3 to obtain the amount of translation (x 0 , y 0 ).
  • Step 3 The user refers to vein image acquisition and image extraction of the region of interest.
  • the process is as follows:
  • the light source 2 emits light, the light source 1 and the light source 3 do not emit light, and the image F 4 is acquired;
  • step 2 the region of interest image NorF 4 (the size is w*h) of the image F 4 is acquired.
  • Step 4 User finger vein image recognition: the user refers to the region of interest NorF 4 of the vein acquisition image and the mosaic image MosaicF (target matching image) to perform the best matching region selection, and uses the binary structure feature to complete the identification work, which mainly includes :
  • SubMosaicF is taken as the best to-be-matched region MaxF
  • W and H represent the width and height of SkeletonNorF, respectively, and N represents the number of non-zero pixels of SkeletonNorF.
  • the embodiment further provides a finger vein recognition device, including:
  • a first acquiring module configured to collect a finger vein image, and acquire an image of the region of interest corresponding to the finger vein image
  • the identification module is configured to match the image of the region of interest with the target matching image according to the binary structure algorithm, and if the matching is successful, the finger vein recognition is passed.
  • the identification module comprises:
  • a first processing module configured to perform smoothing processing on the image of the region of interest in the target matching image to obtain an image to be matched
  • a second processing module configured to perform binarization processing on the image of the region of interest and the image to be matched, to obtain a first binary image and a second binary image
  • a calculating module configured to calculate a similarity between the first binary image and the second binary image.
  • the method further includes:
  • a second acquiring module configured to acquire a finger vein image of multiple angles
  • a splicing module for splicing the finger vein images of a plurality of angles into a target matching image.
  • a finger vein recognition method disclosed in the present application acquires an image of a region of interest by stitching a plurality of angles of the finger vein image into a target matching image by acquiring a plurality of angle finger vein images, and The image of the region of interest is matched with the target matching image, and if the matching is successful, the finger vein recognition is passed. It can be seen that the program collects finger vein images at different angles and performs feature matching to realize finger vein recognition, high accuracy, and then 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. Can choose according to actual needs Some or all of the modules are used to achieve the objectives 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Vascular Medicine (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

La présente invention concerne un procédé de reconnaissance de veine de doigt consistant : à capturer des images de veine de doigt à de multiples angles (S3) ; après avoir associé les images de veine de doigt capturées à de multiples angles dans une image d'appariement cible (S4), à capturer une image d'une région d'intérêt (S1) ; et à mettre en correspondance l'image de la région d'intérêt et l'image d'appariement cible, une mise en correspondance réussie indiquant que la reconnaissance de veine de doigt est réussie (S2). Le procédé ci-dessus capture des images de veine de doigt à différents angles, et effectue une mise en correspondance de caractéristiques pour réaliser une reconnaissance d'une veine de doigt, ce qui présente une précision élevée. L'application de l'invention dans la vérification d'identité permet d'obtenir un niveau d'efficacité de vérification élevé.
PCT/CN2017/087124 2016-08-17 2017-06-05 Procédé et dispositif de reconnaissance de veine de doigt WO2018032861A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610681717.6 2016-08-17
CN201610681717.6A CN107766776A (zh) 2016-08-17 2016-08-17 一种手指静脉识别方法及装置

Publications (1)

Publication Number Publication Date
WO2018032861A1 true WO2018032861A1 (fr) 2018-02-22

Family

ID=61196453

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/087124 WO2018032861A1 (fr) 2016-08-17 2017-06-05 Procédé et dispositif de reconnaissance de veine de doigt

Country Status (2)

Country Link
CN (1) CN107766776A (fr)
WO (1) WO2018032861A1 (fr)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109684950A (zh) * 2018-12-12 2019-04-26 联想(北京)有限公司 一种处理方法及电子设备
CN110348289A (zh) * 2019-05-27 2019-10-18 广州中国科学院先进技术研究所 一种基于二值图的手指静脉识别方法
CN110599436A (zh) * 2019-09-24 2019-12-20 北京凌云天润智能科技有限公司 一种双目图像拼接融合算法
CN111310688A (zh) * 2020-02-25 2020-06-19 重庆大学 一种基于多角度成像的手指静脉识别方法
CN113269029A (zh) * 2021-04-07 2021-08-17 张烨 一种多模态及多特征的指静脉图像识别方法
CN113673363A (zh) * 2021-07-28 2021-11-19 大连海事大学 结合表观相似度与奇异点匹配个数的手指静脉识别方法
CN115311696A (zh) * 2022-10-11 2022-11-08 山东圣点世纪科技有限公司 一种基于静脉纹理特征的手指区域检测方法
CN116778538A (zh) * 2023-07-24 2023-09-19 北京全景优图科技有限公司 一种基于小波分解的静脉图像识别方法及系统

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108549887B (zh) * 2018-07-23 2021-07-30 北京智芯原动科技有限公司 一种活体人脸检测方法及装置
CN109727194B (zh) * 2018-11-20 2023-08-04 广东智媒云图科技股份有限公司 一种获取宠物鼻纹的方法、电子设备和存储介质
CN109784174A (zh) * 2018-12-14 2019-05-21 深圳壹账通智能科技有限公司 一种用户账户的登录方法及设备
CN110008902B (zh) * 2019-04-04 2020-11-17 山东财经大学 一种融合基本特征和形变特征的手指静脉识别方法及系统
CN110532851B (zh) * 2019-07-04 2022-04-15 珠海格力电器股份有限公司 指静脉识别方法、装置、计算机设备和存储介质
CN111191623B (zh) * 2020-01-03 2023-09-19 圣点世纪科技股份有限公司 一种指静脉拍摄距离的确定方法
CN111652088B (zh) * 2020-05-15 2023-06-20 圣点世纪科技股份有限公司 一种基于视频选优机制的指静脉注册方法及注册装置
CN111898455B (zh) * 2020-07-02 2023-04-07 珠海格力电器股份有限公司 一种静脉图像的匹配方法和装置
CN112883356B (zh) * 2021-03-31 2024-04-23 中国工商银行股份有限公司 一种身份认证方法、装置及设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120057011A1 (en) * 2010-09-03 2012-03-08 Shi-Jinn Horng Finger vein recognition system and method
CN102663393A (zh) * 2012-03-02 2012-09-12 哈尔滨工程大学 基于旋转校正的手指静脉图像感兴趣区域提取方法
CN103310196A (zh) * 2013-06-13 2013-09-18 黑龙江大学 感兴趣区域与方向元素的手指静脉识别方法
CN103729640A (zh) * 2013-12-24 2014-04-16 小米科技有限责任公司 一种手指静脉特征提取方法、装置及一种终端
CN105474234A (zh) * 2015-11-24 2016-04-06 厦门中控生物识别信息技术有限公司 一种掌静脉识别的方法和掌静脉识别装置
WO2016072921A1 (fr) * 2014-11-07 2016-05-12 Fingerprint Cards Ab Authentification d'empreinte digitale par assemblage-coupure

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120057011A1 (en) * 2010-09-03 2012-03-08 Shi-Jinn Horng Finger vein recognition system and method
CN102663393A (zh) * 2012-03-02 2012-09-12 哈尔滨工程大学 基于旋转校正的手指静脉图像感兴趣区域提取方法
CN103310196A (zh) * 2013-06-13 2013-09-18 黑龙江大学 感兴趣区域与方向元素的手指静脉识别方法
CN103729640A (zh) * 2013-12-24 2014-04-16 小米科技有限责任公司 一种手指静脉特征提取方法、装置及一种终端
WO2016072921A1 (fr) * 2014-11-07 2016-05-12 Fingerprint Cards Ab Authentification d'empreinte digitale par assemblage-coupure
CN105474234A (zh) * 2015-11-24 2016-04-06 厦门中控生物识别信息技术有限公司 一种掌静脉识别的方法和掌静脉识别装置

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109684950A (zh) * 2018-12-12 2019-04-26 联想(北京)有限公司 一种处理方法及电子设备
CN110348289B (zh) * 2019-05-27 2023-04-07 广州中国科学院先进技术研究所 一种基于二值图的手指静脉识别方法
CN110348289A (zh) * 2019-05-27 2019-10-18 广州中国科学院先进技术研究所 一种基于二值图的手指静脉识别方法
CN110599436A (zh) * 2019-09-24 2019-12-20 北京凌云天润智能科技有限公司 一种双目图像拼接融合算法
CN111310688A (zh) * 2020-02-25 2020-06-19 重庆大学 一种基于多角度成像的手指静脉识别方法
CN111310688B (zh) * 2020-02-25 2023-04-21 重庆大学 一种基于多角度成像的手指静脉识别方法
CN113269029B (zh) * 2021-04-07 2022-09-13 张烨 一种多模态及多特征的指静脉图像识别方法
CN113269029A (zh) * 2021-04-07 2021-08-17 张烨 一种多模态及多特征的指静脉图像识别方法
CN113673363A (zh) * 2021-07-28 2021-11-19 大连海事大学 结合表观相似度与奇异点匹配个数的手指静脉识别方法
CN113673363B (zh) * 2021-07-28 2024-03-01 大连海事大学 结合表观相似度与奇异点匹配个数的手指静脉识别方法
CN115311696A (zh) * 2022-10-11 2022-11-08 山东圣点世纪科技有限公司 一种基于静脉纹理特征的手指区域检测方法
CN115311696B (zh) * 2022-10-11 2023-02-28 山东圣点世纪科技有限公司 一种基于静脉纹理特征的手指区域检测方法
CN116778538A (zh) * 2023-07-24 2023-09-19 北京全景优图科技有限公司 一种基于小波分解的静脉图像识别方法及系统
CN116778538B (zh) * 2023-07-24 2024-01-30 北京全景优图科技有限公司 一种基于小波分解的静脉图像识别方法及系统

Also Published As

Publication number Publication date
CN107766776A (zh) 2018-03-06

Similar Documents

Publication Publication Date Title
WO2018032861A1 (fr) Procédé et dispositif de reconnaissance de veine de doigt
US11176406B2 (en) Edge-based recognition, systems and methods
WO2019196308A1 (fr) Dispositif et procédé de génération de modèle de reconnaissance faciale, et support d'informations lisible par ordinateur
JP6167733B2 (ja) 生体特徴ベクトル抽出装置、生体特徴ベクトル抽出方法、および生体特徴ベクトル抽出プログラム
AU2015317344B2 (en) Mobility empowered biometric appliance a tool for real-time verification of identity through fingerprints
CN108230383B (zh) 手部三维数据确定方法、装置及电子设备
JP7242528B2 (ja) モバイルデバイスを用いてキャプチャした画像を使用する、指紋によるユーザ認証を実施するためのシステムおよび方法
WO2017059591A1 (fr) Procédé et dispositif d'identification de veine de doigt
US8208692B2 (en) Method and system for identifying a person using their finger-joint print
JP5715833B2 (ja) 姿勢状態推定装置および姿勢状態推定方法
CN105740781B (zh) 一种三维人脸活体检测的方法和装置
JP6648639B2 (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
Ambeth Kumar et al. Exploration of an innovative geometric parameter based on performance enhancement for foot print recognition
Boutellaa et al. On the use of Kinect depth data for identity, gender and ethnicity classification from facial images
Zhang et al. Hand-based single sample biometrics recognition
Wang et al. Automatic fundus images mosaic based on SIFT feature
TW201222433A (en) Identity verification apparatus and method thereof based on biometric features
WO2018196521A1 (fr) Procédé et dispositif de calcul de score de qualité pour image de veine de doigt
Raju et al. A proposed feature extraction technique for dental X-ray images based on multiple features
Caya et al. Recognition of tongue print biometrie using binary robust independent elementary features
CN111652018B (zh) 一种人脸注册方法和认证方法
JP2010240215A (ja) 静脈深度判定装置、静脈深度判定方法およびプログラム
Panetta et al. Unrolling post-mortem 3D fingerprints using mosaicking pressure simulation technique
JP6978665B2 (ja) 生体画像処理装置、生体画像処理方法及び生体画像処理プログラム
JP6187262B2 (ja) 生体情報処理装置、生体情報処理方法及び生体情報処理用コンピュータプログラム

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: 17840837

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: 17840837

Country of ref document: EP

Kind code of ref document: A1