WO2016127767A1 - Authentication device and method combining finger vein recognition and facial vein recognition - Google Patents

Authentication device and method combining finger vein recognition and facial vein recognition Download PDF

Info

Publication number
WO2016127767A1
WO2016127767A1 PCT/CN2016/071412 CN2016071412W WO2016127767A1 WO 2016127767 A1 WO2016127767 A1 WO 2016127767A1 CN 2016071412 W CN2016071412 W CN 2016071412W WO 2016127767 A1 WO2016127767 A1 WO 2016127767A1
Authority
WO
WIPO (PCT)
Prior art keywords
finger
feature information
vein
facial
feature
Prior art date
Application number
PCT/CN2016/071412
Other languages
French (fr)
Chinese (zh)
Inventor
张丽琴
Original Assignee
张丽琴
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 张丽琴 filed Critical 张丽琴
Publication of WO2016127767A1 publication Critical patent/WO2016127767A1/en

Links

Images

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
    • G06V40/70Multimodal biometrics, e.g. combining information from different biometric modalities
    • 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
    • G06V40/12Fingerprints or palmprints
    • G06V40/13Sensors therefor
    • 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
    • G06V40/145Sensors therefor
    • 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
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements

Definitions

  • FIG. 1 is a schematic structural view of an authentication device combining finger vein recognition and facial vein recognition of the present invention.
  • FIG. 2 is a schematic view showing the structure of a finger vein recognition portion of the authentication device in combination with the finger vein recognition and the facial vein recognition of the present invention.
  • the base 31 of the facial vein feature information collecting device 3 is slidably disposed on the surface of the table body 4 near the finger vein feature information collecting device 2, so that the authenticator can simultaneously collect the finger vein feature information and the facial vein feature information.
  • the base 31 is provided with a rotatable and folded mechanical arm 32.
  • the facial vein characteristic information collecting member 33 is disposed at the top end of the mechanical arm 32, and includes a housing 34, a second infrared imaging light source 35, and a second infrared imaging device 36.
  • the outer casing 34 includes a left side panel, a right side panel and a front panel.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Vascular Medicine (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)
  • Image Input (AREA)

Abstract

An authentication device and method combining finger vein recognition and facial vein recognition. The authentication device comprises a facial vein characteristic information collection device (3) and a finger vein characteristic information collection device (2). Collected finger vein characteristic information with angle and position information and collected facial vein characteristic information with facial position information are processed by means of a data standardization method, so as to form a characteristic information matching group comprising the shapes and the directions of finger veins and the shapes of facial vein characteristics, and then identity authentication is performed by using the matching group. The accuracy and the reliability of identity authentication in the security field are greatly improved.

Description

一种手指静脉识别与面部静脉识别相结合的认证装置及方法Authentication device and method combining finger vein recognition and facial vein recognition 技术领域Technical field
本发明涉及的是一种利用生物特征进行身份识别和认证的技术领域,特别地涉及手指静脉识别与面部静脉识别相结合的认证装置及方法。The invention relates to the technical field of identification and authentication using biometrics, in particular to an authentication device and method combining finger vein recognition and facial vein recognition.
背景技术Background technique
随着社会的发展,在当今社会信息安全问题备受人们关注。自身安全和个人隐私保护成为这个时代的热门话题。基于密码、个人识别码、磁卡和钥匙等传统的安全措施已不能完全满足社会要求。在这样一个背景下,人们把目光投向了生物特征识别技术——利用人体固有的生理特征或行为特征来进行身份的鉴别或确认。现有技术中,常见的生物特征识别技术例如包括指纹识别、人脸识别等,指纹识别会受到很多限制,必然手指皮肤的突然变化会影响指纹识别的效果,另外,部分人或某些群体的指纹因为特征较少,因此很难成像,并且存在指纹磨损或者手指污染等导致精确度受到影响;另外,面部的外形很不稳定,人可以通过脸部的变化产生很多表情,而在不同观察角度,面部的视觉图像也相差很大,另外,面部识别还受光照条件(例如白天和夜晚,室内和室外等)、面部的很多遮盖物(例如口罩、墨镜、头发、胡须等)、年龄等多方面因素的影响。面部识别不同个体之间的区别不大,所有的面部的结构都相似,甚至面部器官的结构外形都很相似,对于利用面部区分人类个体是不利的。With the development of society, the issue of information security in today's society has attracted much attention. Self-security and personal privacy protection have become hot topics in this era. Traditional security measures based on passwords, personal identification numbers, magnetic cards and keys are no longer sufficient to meet social requirements. In such a context, people turn their attention to biometrics—using the inherent physiological or behavioral characteristics of the human body to identify or confirm identity. In the prior art, common biometric recognition technologies include, for example, fingerprint recognition, face recognition, etc., fingerprint recognition may be subject to many restrictions, and the sudden change of the finger skin may affect the effect of fingerprint recognition. In addition, some people or certain groups Fingerprints are difficult to image because of fewer features, and fingerprint wear or finger contamination causes accuracy to be affected. In addition, the shape of the face is unstable, and people can generate many expressions through changes in the face, and at different viewing angles. The visual images of the face are also very different. In addition, facial recognition is also subject to lighting conditions (such as day and night, indoor and outdoor, etc.), many coverings of the face (such as masks, sunglasses, hair, beards, etc.), age, etc. The impact of factors. Face recognition has little difference between different individuals. The structure of all faces is similar. Even the structural shapes of facial organs are similar, which is unfavorable for distinguishing human subjects by face.
在上述生物特征识别技术的基础上发展的手指静脉认证技术近年开始出现,其是一种新的生物特征识别技术,它利用手指内的静脉分布图像来进行身份识别。识别时接触少甚至无须接触,不会有手指表面特征被第三者恶意复制的危险;***获取的是手指活体时才存在的特征,非活体的手指是得不到静脉图像特征的,从而也就无法造假但手背静脉仍可能随着年龄和生理的变化而发生变化,永久性尚未得到证实,虽然可能性较小,但仍然存在无法成功注册登记的可能。另外,通常情况下女性的手指静脉血液是少于男性,这使得采集到的静脉图像包含的静脉特征较少且对比度较低。因而从目前的认证方法来看,存在认证度不高,导致不安全或其它问题的出现。并且手指表面的损伤、磨损、干燥或太湿等也会带来识别障碍,使得认证的精度和准确度受到影响。The finger vein authentication technology developed on the basis of the above biometric recognition technology has appeared in recent years, and it is a new biometric recognition technology, which uses the vein distribution image in the finger to perform identity recognition. There is little or no contact during identification, and there is no danger that the surface features of the finger will be maliciously copied by the third party; the system acquires the characteristics that exist only when the finger is in the living body, and the non-living finger does not have the characteristics of the vein image, and thus It is impossible to make a fake, but the dorsal vein of the hand may still change with age and physiology. The permanentness has not been confirmed. Although the possibility is small, there is still the possibility that it cannot be successfully registered. In addition, in general, women's finger vein blood is less than male, which makes the collected vein image contain fewer vein features and lower contrast. Therefore, from the current authentication method, there is a low degree of authentication, resulting in insecurity or other problems. And the damage, wear, dryness or too wet of the surface of the finger can also cause recognition obstacles, which makes the accuracy and accuracy of the certification affected.
另外现有技术中没有考虑手指角度对认证带来的影响,使得认证过程存在精度和准确性受到影响。In addition, the influence of the finger angle on the authentication is not considered in the prior art, so that the accuracy and accuracy of the authentication process are affected.
发明内容 Summary of the invention
本发明旨在解决上述的技术问题,提出一种具有克服目前生物特征识别技术的缺点,使得生物体认证装置和认证方法能够具有更高的防伪性和实用性,并提高认证的精度。本发明为了解决上述技术问题,可以通过以下的方式实现。The present invention aims to solve the above technical problems, and proposes a shortcoming that overcomes the current biometric identification technology, so that the biometric authentication device and the authentication method can have higher anti-counterfeiting and practicability, and improve the accuracy of authentication. The present invention can be achieved in the following manner in order to solve the above technical problems.
本发明提供的手指静脉识别与面部静脉识别相结合的认证装置包括:手指静脉特征信息采集装置和与其连接的面部静脉特征信息采集装置,另外该认证装置还包括特征信息保存部、数据处理部、匹配特征信息比对部、控制器以及输入输出接口。其中手指静脉特征信息采集装置负责采集手指静脉识别需要的信息,面部静脉特征信息采集装置采集面部静脉识别需要的信息,上述手指静脉特征信息采集装置采集的手指静脉识别需要的信息和面部静脉特征信息采集装置采集的面部静脉识别需要的信息保存到特征信息保存部,特征信息比对部从上述特征信息保存部调取相应的生物特征信息进行比对,该特征信息比对部包括图像提取单元和样本数据存储单元,图像提取单元其将实时接收的手指静脉特征信息、面部静脉特征信息并进行分析处理,提取出认证者的特征值,样本数据存储单元存储有通过输入输出接口获得的预先采集的认证者的手指静脉特征信息和面部静脉特征信息,另外,手指静脉特征信息采集装置中的特征信息比对部可以独立的将上述提取出的认证者的特征值与预先采集的认证者的手指静脉特征信息和面部静脉特征信息进行比对,并将比对的结果发送至第一控制器;第一控制器与特征信息比对部相连接,第一控制器根据特征信息比对部的比对结果信号控制本发明的手指静脉识别与面部静脉识别相结合的认证装置发出或显示比对结果,以告知是否通过认证;另外,上述的输入输出接口也可以与网络连接,以进一步的与远程的主服务器连接,进行数据信息的传输或认证信息的验证,可定期备份,可以与WIS数据库无缝衔接。The authentication device combined with the finger vein recognition and the facial vein recognition includes: a finger vein feature information collecting device and a facial vein feature information collecting device connected thereto, and the authentication device further includes a feature information storage unit and a data processing unit. Matching feature information comparison, controller, and input and output interfaces. The finger vein feature information collecting device is responsible for collecting information required for finger vein recognition, and the facial vein feature information collecting device collects information required for facial vein recognition, and the finger vein identification information and facial vein feature information collected by the finger vein feature information collecting device are collected. The information required for facial vein recognition collected by the collection device is stored in the feature information storage unit, and the feature information comparison unit compares the corresponding biometric information from the feature information storage unit, and the feature information comparison unit includes an image extraction unit and a sample data storage unit, wherein the image extraction unit analyzes the finger vein feature information and the facial vein feature information received in real time, and extracts a feature value of the authenticator, and the sample data storage unit stores the pre-acquired obtained through the input/output interface. The finger vein characteristic information and the facial vein feature information of the authenticator, and the feature information comparison unit in the finger vein feature information collecting device can independently separate the extracted feature value of the authenticator from the pre-acquired authenticator's hand Comparing the vein characteristic information and the facial vein characteristic information, and transmitting the result of the comparison to the first controller; the first controller is connected with the characteristic information comparison portion, and the ratio of the first controller according to the characteristic information comparison portion The result signal control The authentication device of the finger vein recognition of the present invention combined with the facial vein recognition sends or displays the comparison result to inform whether the authentication is passed; in addition, the above-mentioned input/output interface can also be connected to the network to further and remotely The main server is connected for data information transmission or authentication information verification, which can be backed up regularly and can be seamlessly connected with the WIS database.
上述手指静脉特征信息采集装置包括壳体、红外成像光源、红外成像装置、手指位置传感器、手指角度传感器、手指放置座;其中壳体上设有电源开关,当认证者需要进行特征信息认证时,可通过打开开关的方式进行,也可设置人体感测器,当认证人靠近该装置时,认证装置自动进入开机状态,壳体的中间部分设置有一个用于伸入手指的半圆形孔,半圆形孔内顶部中间正对手指放置座的位置上设置有多排红外成像光源,当入射光波长在720nm到1100nm时,能够较好的穿透骨骼和肌肉,凸现出血管结构,该波长范围属于近红外光线。通过若干组不同波长的红外光源的比对试验,我们发现波长为810nm的红外光具有更好的造影效果,图像更为清晰。在方案选取中,优选使用两组波长都为810nm,并且都能够分组控制,亮度连续可调的红外发光二极管作为静脉图像的打光光源,为了获得较好的图像质量,可以将红外LED发光管头部截成平面并打磨,采用散光片加装在红外光源前, 以获得均匀的离散红外光;在半圆形孔内侧壁的两侧分别设置有两个手指角度传感器,在与手指放置座平齐的水平位置的两侧各设置一个手指角度传感器,在与手指放置座平齐的水平位置成45度角处的两侧各设置一个手指角度传感。通过所述的手指角度传感器来检测伸入到半圆形孔壳体内的手指的放置角度,测试的方法为通过四个手指角度传感器来检测手指指甲的角度,即通过四个手指角度传感器来检测指甲弧度的最顶部与水平面的角度,通过该角度来确定手指相对于手指放置座水平面的放置角度,来判断伸入到半圆形孔壳体内的手指的具***置信息,在判定了手指相对于手指放置座水平面的放置角度后,再进行手指静脉特征信息的采集,所述红外成像光源用于手指静脉的照明,红外成像装置前设有一个红外滤光片和一个反红外滤光片、用于反射红外光并透射可见红光;计算机处理***通过数据传输接口与所述的红外成像装置连接,从红外成像装置输出的图像中提取的带有手指角度的手指静脉特征信息的特征量,并将上述特征量输入到与数据处理部中。The finger vein characteristic information collecting device includes a housing, an infrared imaging light source, an infrared imaging device, a finger position sensor, a finger angle sensor, and a finger placement seat; wherein the housing is provided with a power switch, and when the authenticator needs to perform the feature information authentication, The human body sensor can be arranged by opening the switch. When the authenticator approaches the device, the authentication device automatically enters the power-on state, and the middle portion of the housing is provided with a semi-circular hole for extending into the finger. The top of the semicircular hole is provided with a plurality of rows of infrared imaging light sources at the position of the finger placement seat. When the incident light wavelength is between 720 nm and 1100 nm, the bone and muscle can be better penetrated, and the blood vessel structure is highlighted. The range is near infrared light. Through the comparison test of several sets of infrared light sources with different wavelengths, we found that infrared light with a wavelength of 810 nm has better contrast effect and the image is clearer. In the scheme selection, it is preferable to use two sets of infrared light-emitting diodes with wavelengths of 810 nm and capable of group control and continuously adjustable brightness as a light source of the vein image. In order to obtain better image quality, the infrared LED tube can be used. The head is cut into a plane and polished, and a diffuser is attached to the infrared light source. Obtaining uniform discrete infrared light; two finger angle sensors are respectively disposed on two sides of the inner wall of the semicircular hole, and one finger angle sensor is disposed on each side of the horizontal position flush with the finger placement seat, Place a flat finger at a horizontal position at a 45-degree angle to set a finger angle sensing on each side. The angle of the finger extending into the semicircular hole housing is detected by the finger angle sensor, and the test method is to detect the angle of the finger nail by using four finger angle sensors, that is, detecting by four finger angle sensors. The angle between the top of the nail curvature and the horizontal plane, by which the angle of the finger relative to the horizontal plane of the finger placement seat is determined to determine the specific position information of the finger extending into the semicircular aperture housing, and the finger is determined relative to After the finger is placed at the horizontal plane of the seat, the finger vein characteristic information is collected, and the infrared imaging light source is used for illumination of the finger vein. The infrared imaging device is provided with an infrared filter and an anti-infrared filter. Reflecting infrared light and transmitting visible red light; the computer processing system is connected to the infrared imaging device through a data transmission interface, and extracts a feature quantity of the finger vein characteristic information with a finger angle extracted from an image output by the infrared imaging device, and The above feature amount is input to the data processing unit.
面部静脉特征信息采集装置与手指静脉特征信息的采集装置连接,其中面部静脉特征信息采集装置包括外壳、第二红外成像光源、第二红外成像装置、面部位置传感器、头部位置判断装置、语音提示装置、面部静脉特征信息比对装置及数据传输接口。外壳包括左侧板、右侧板和正面板,左侧板、右侧板互相平行的设置在正面板的两端且分别与正面板垂直,其中左侧板、右侧板及正面形成的空间区域为头部静脉特征信息采集;在左侧板上设置有两排第二红外成像光源,在右侧板上设置有第二红外成像装置,在正面板上设置有面部位置传感器,同时正面板上还可设置有人体感测器,当认证人体头部能够靠近该装置时,认证装置自动进入开机状态。当入射光波长在720nm到1100nm时,能够较好的穿透骨骼和面部肌肉,凸现出面部血管结构,该波长范围属于近红外光线。通过若干组不同波长的红外光源的比对试验,我们发现波长为850nm的红外光具有更好的造影效果,面部静脉图像更为清晰。在方案选取中,优选使用两组波长都为850nm,并且都能够分组控制,亮度连续可调的红外发光二极管作为静脉图像的打光光源,为了获得较好的图像质量,可以将红外LED发光管头部截成平面并打磨,采用散光片加装在红外光源前,以获得均匀的离散红外光。所述第二红外成像装置采用的是热感成像摄像头,对用户的面部进行红外扫描;面部位置传感器设置在正面板上,当认证者进入感应区域而使得面部静脉特征信息采集装置进入工作状态时,通过面部位置传感器拍摄的图像判断头部是否正面面对正面板,即判断头部位置是否相对于正面板有偏转或者有低头、歪头现象发生,如果经过面部位置传感器拍摄的图像判断为认证者的头部没有正面面对正面板,则头部位置判断装置向语音提示装置发出信号,控制语音提示装置发出声音告知认证者移动头部位置,然后面部位置传感器重新拍摄认证者 的头部照片,再次经过头部位置判断装置的判断,直至判断结果为头部正面面对正面板时,语音提示装置发出提示,提醒认证者停止头部动作,开始进行面部静脉特征信息采集。述红外成像光源用于面部静脉的照明,红外成像装置前设有一个红外滤光片和一个反红外滤光片、用于反射红外光并透射可见红光;计算机处理***通过数据传输接口与所述的红外成像装置连接,从红外成像装置输出的图像中提取的带有面部静脉特征信息的特征量,并将上述特征量也输入到与数据处理部中。在本发明的手指静脉识别与面部静脉识别相结合的认证装置中,此面部静脉特征信息采集认证者的特征值可单独的与预先采集的认证者的手指静脉特征信息和面部静脉特征信息进行比对,并将比对的结果发送至第二控制器;第二控制器与特征信息比对部相连接,第二控制器根据特征信息比对部的比对结果信号控制本发明的手指静脉识别与面部静脉识别相结合的认证装置发出或显示比对结果,以告知是否通过认证;另外,上述的输入输出接口也可以与网络连接,以进一步的与远程的主服务器连接,进行数据信息的传输或认证信息的验证,可定期备份,可以与WIS数据库无缝衔接。The facial vein feature information collecting device is connected to the collecting device of the finger vein feature information, wherein the facial vein feature information collecting device comprises a casing, a second infrared imaging light source, a second infrared imaging device, a face position sensor, a head position determining device, and a voice prompt Device, facial vein feature information comparison device and data transmission interface. The outer casing comprises a left side plate, a right side plate and a front side plate. The left side plate and the right side plate are arranged parallel to each other at opposite ends of the front panel and respectively perpendicular to the front panel, wherein the left side plate, the right side plate and the front side form a space area For collecting cephalic vein feature information; two rows of second infrared imaging light sources are disposed on the left side plate, a second infrared imaging device is disposed on the right side plate, and a face position sensor is disposed on the front panel, and the front panel is provided on the front panel A human body sensor can also be provided, and when the authentication human head can be close to the device, the authentication device automatically enters a power-on state. When the incident light wavelength is between 720nm and 1100nm, it can penetrate the bone and facial muscles better, and the facial vascular structure is highlighted. The wavelength range belongs to near-infrared light. Through the comparison test of several sets of infrared light sources with different wavelengths, we found that infrared light with a wavelength of 850 nm has better contrast effect and the facial vein image is clearer. In the scheme selection, it is preferred to use two sets of infrared light-emitting diodes with wavelengths of 850 nm and capable of group control and continuously adjustable brightness as a light source of the vein image. In order to obtain better image quality, the infrared LED tube can be used. The head is cut into a plane and polished, and a diffuser is attached to the front of the infrared source to obtain uniform discrete infrared light. The second infrared imaging device adopts a thermal imaging camera to perform infrared scanning on the user's face; the facial position sensor is disposed on the front panel, and when the authenticator enters the sensing area, the facial vein characteristic information collecting device enters the working state. The image taken by the face position sensor determines whether the head faces the front panel, that is, whether the head position is deflected relative to the front panel or has a bow or a head phenomenon, and if the image taken by the face position sensor is judged as authentication If the head of the person does not face the front panel, the head position determining device sends a signal to the voice prompting device, and the voice prompting device controls the voice prompting device to notify the authenticator to move the head position, and then the face position sensor re-photographs the authenticator. The photo of the head is again judged by the head position judging device until the judgment result is that the front side of the head faces the front panel, and the voice prompting device issues a prompt to remind the authenticator to stop the head movement and start collecting the facial vein feature information. The infrared imaging light source is used for illumination of the facial vein. The infrared imaging device is provided with an infrared filter and an anti-infrared filter for reflecting infrared light and transmitting visible red light; the computer processing system transmits the data through the interface. The infrared imaging device is connected to extract a feature amount with facial vein feature information extracted from an image output from the infrared imaging device, and the feature amount is also input to the data processing unit. In the authentication device combining the finger vein recognition and the facial vein recognition of the present invention, the feature value of the facial vein feature information collection authenticator can be separately compared with the pre-acquired authenticator's finger vein feature information and facial vein feature information. Pairing, and transmitting the result of the comparison to the second controller; the second controller is connected with the feature information comparison portion, and the second controller controls the finger vein recognition of the present invention according to the comparison result signal of the feature information comparison portion The authentication device combined with the facial vein recognition sends or displays the comparison result to inform whether the authentication is passed; in addition, the above input and output interface can also be connected to the network to further connect with the remote main server for data information transmission. Or the verification of the authentication information can be backed up regularly and can be seamlessly connected with the WIS database.
利用本发明的手指静脉识别与面部静脉识别相结合的认证装置进行认证的方法包括下述内容:The method for authenticating using the authentication device of the finger vein recognition and facial vein recognition of the present invention includes the following contents:
首先是认证者身份登记过程,最初将需要认证的特定人员的手指静脉特征信息和面部静脉特征信息登记入库,在此登记过程中采集的手指静脉特征信息包括手指多个角度的信息,在登记时让手指转动,采集连续多个角度手指静脉特征信息,并将上述含有角度信息的手指静脉特征信息输入到特征信息保存部;在此登记过程中同时采集的面部静脉特征信息包括通过认证者正面面对的正面板上的面部位置传感器确定的正面角度时采集的面部静脉特征信息,在语音提示装置提示位置正确后进行面部静脉特征信息的采集,并将上述采集的面部静脉特征信息输入到特征信息保存部;在上述两种特征信息采集结束后,在特征信息保存部将采集获取的手指静脉特征信息和面部静脉特征信息在数据处理部形成实时的手指静脉特征信息和面部静脉特征信息匹配组,该匹配组包括了带有角度信息的手指静脉特征信息以及同时采集的面部静脉特征信息,形成匹配组的方法包括了手指静脉的形状、方向以及面部静脉特征的形状,为了提高匹配精度,在数据融合之前,通过下面的数据标准化方法对这些数据进行匹配信息的标准化:The first is the authenticator identity registration process, which initially registers the finger vein feature information and the facial vein feature information of the specific person who needs to be authenticated, and the finger vein feature information collected during the registration process includes information of multiple angles of the finger, and is registered. When the finger is rotated, the finger vein characteristic information of the plurality of angles is continuously collected, and the finger vein characteristic information containing the angle information is input to the feature information storage unit; the facial vein feature information collected simultaneously during the registration process includes the front face of the authenticator. The face vein feature information collected when the face position sensor on the front panel determines the frontal angle is obtained, and the facial vein feature information is collected after the voice prompting device prompts the correct position, and the collected facial vein feature information is input into the feature. After the collection of the two kinds of feature information is completed, the feature information storage unit forms the real-time finger vein feature information and the facial vein feature information matching group in the data processing unit by collecting and acquiring the finger vein feature information and the facial vein feature information. The horse The group includes finger vein feature information with angle information and facial vein feature information collected at the same time. The method of forming a matching group includes the shape and direction of the finger vein and the shape of the facial vein feature. In order to improve the matching precision, before data fusion Standardize the matching information for these data by the following data normalization methods:
a’=(a-c)/σa’=(a-c)/σ
其中a是静脉形状、方向特征的匹配分数,c和σ代表匹配分数a的均值和方差,然后将得到的标准化数据a’作为融合方法的输入数据。Where a is the matching score of the vein shape and the directional characteristic, c and σ represent the mean and variance of the matching score a, and the obtained normalized data a' is then used as the input data of the fusion method.
其中利用上述数据标准化方法将手指静脉特征和面部静脉特征进行数据标准化,获 得手指静脉特征标准数据和面部静脉特征标准数据,然后将两种静脉特征标准数据通过加权融合法形成特征信息匹配组,The data standardization method is used to standardize finger vein features and facial vein features. The finger vein characteristic standard data and the facial vein feature standard data are obtained, and then the two vein feature standard data are formed into a feature information matching group by weighted fusion method.
其次是认证过程,在认证者需要进行特征信息认证时,可通过打开开关或通过人体感测器的方式使认证装置自动进入开机状态,手指伸入壳体的半圆形孔,手指静脉特征信息的采集部分进入手指静脉特征信息采集过程,同时,面部静脉特征信息采集部分也进入面部静脉特征信息采集过程,首先,通过所述的手指角度传感器来检测伸入到半圆形孔壳体内的手指的放置信息,即通过四个手指角度传感器来检测指甲弧度的最顶部与水平面的角度,通过该角度来确定手指相对于手指放置座水平面的放置角度信息,同时,通过面部位置传感器拍摄的图像判断头部是否正面面对正面板,即判断头部位置是否相对于正面板有偏转或者有低头、歪头现象发生,如果经过面部位置传感器拍摄的图像判断为认证者的头部没有正面面对正面板,则头部位置判断装置向语音提示装置发出信号,控制语音提示装置发出声音告知认证者移动头部位置,然后面部位置传感器重新拍摄认证者的头部照片,再次经过头部位置判断装置的判断,直至判断结果为头部正面面对正面板时,语音提示装置发出提示,提醒认证者停止头部动作;然后,手指静脉特征信息的采集部分的第一红外成像光源和面部静脉特征信息采集部分的第二红外成像光源发出光线,手指静脉特征信息的采集部分的第一红外成像装置和面部静脉特征信息采集部分的第二红外成像装置将采集得到的手指静脉特征和面部静脉征输入到特征信息保存部,其中手特征信息包括了手指静脉的形状、方向以及面部静脉特征的形状;特征信息保存部将上述特征信息输入到数据处理部进行融合,先通过下面的数据标准化方法对这些数据进行匹配信息的标准化:Followed by the authentication process, when the authenticator needs to perform the feature information authentication, the authentication device can be automatically turned on by opening the switch or by the human body sensor, and the finger extends into the semicircular hole of the housing, and the finger vein characteristic information The collecting part enters the finger vein characteristic information collecting process, and at the same time, the facial vein characteristic information collecting part also enters the facial vein characteristic information collecting process. First, the finger extending into the semicircular hole shell is detected by the finger angle sensor. The placement information, that is, the angle between the topmost portion of the nail curvature and the horizontal plane is detected by four finger angle sensors, and the angle of the finger relative to the horizontal plane of the finger placement seat is determined by the angle, and the image taken by the face position sensor is judged Whether the head faces the front panel positively, that is, whether the head position is deflected relative to the front panel or has a head bow or a hoe phenomenon, and if the image taken by the face position sensor is judged to be that the certifier's head is not facing the front face positively Panel, the head position judging device is directed to the voice The display device sends a signal to control the voice prompting device to send a sound to inform the authenticator to move the head position, and then the face position sensor re-photographs the photo of the authenticator's head, and then passes the judgment of the head position determining device again until the judgment result is the front side of the head. When the front panel is aligned, the voice prompting device issues a prompt to remind the authenticator to stop the head movement; then, the first infrared imaging light source of the collecting portion of the finger vein characteristic information and the second infrared imaging light source of the facial vein characteristic information collecting portion emit light, The first infrared imaging device of the acquisition portion of the finger vein feature information and the second infrared imaging device of the facial vein feature information acquisition portion input the collected finger vein feature and facial vein sign into the feature information storage unit, wherein the hand feature information includes The shape, direction, and shape of the facial vein feature of the finger vein; the feature information storage unit inputs the feature information to the data processing unit for fusion, and first normalizes the matching information by the following data normalization method:
a’=(a-c)/σa’=(a-c)/σ
其中a是静脉形状、方向特征的匹配分数,c和σ代表匹配分数a的均值和方差,然后将得到的标准化数据a’作为融合方法的输入数据,获得手指静脉特征标准数据和面部静脉特征标准数据后,将两种静脉特征标准数据通过加权融合法形成特征信息匹配组;随后上述特征信息匹配组被输入到匹配特征信息比对部,在匹配特征信息比对部中将将认证者当前认证的特征信息匹配组与身份登记时的特征信息匹配组进行比对,该比对包括了手指静脉的形状、方向以及面部静脉特征的形状信息的特征信息匹配组的比对,比如根据当前认证的特征信息匹配组根据相应的手指静脉的形状、方向以及面部静脉特征的形状的特征在匹配特征信息比对部搜索与该特征最相近的预先登记的特征信息匹配组进行比对;根据上述比对的结果进行身份鉴定,确认身份。Where a is the matching score of the vein shape and direction feature, c and σ represent the mean and variance of the matching score a, and then the obtained normalized data a' is used as the input data of the fusion method to obtain the standard data of the finger vein feature and the standard of the facial vein feature. After the data, the two types of vein characteristic standard data are formed into a feature information matching group by a weighted fusion method; then the above-mentioned feature information matching group is input to the matching feature information comparison portion, and the authenticator is currently authenticated in the matching feature information comparison portion. The feature information matching group is compared with the feature information matching group at the time of identity registration, and the comparison includes the matching of the shape information of the shape and direction of the finger vein and the shape information of the facial vein feature, such as according to the current authentication. The feature information matching group compares the matching feature information matching group with the pre-registered feature information matching group closest to the feature according to the shape, the direction of the corresponding finger vein, and the shape of the facial vein feature; according to the above comparison The results are identified and identified.
通过本发明的手指静脉识别与面部静脉识别相结合的认证装置认证方法,通过一定的 特征信息的数据处理,获得了手指静脉特征标准数据和面部静脉特征的特征信息匹配组,能够消除现有技术的生物特征验证可能随着年龄和生理的变化而发生变化而带来的验证不准确的问题,并且此方法利用手指静脉和面部静脉的特征信息的匹配组进行认证,大大提升安全领域身份认证的准确度和可靠性。The authentication device authentication method combined with the finger vein recognition and the facial vein recognition of the present invention passes a certain The data processing of the feature information obtains the feature information matching group of the finger vein feature standard data and the facial vein feature, which can eliminate the inaccurate verification caused by the change of the prior art biometric feature with age and physiological changes. The problem is that the method uses the matching group of the characteristic information of the finger vein and the facial vein to authenticate, which greatly improves the accuracy and reliability of the identity authentication in the security field.
手指角度的不同会对最终采集到的手指静脉特征信息,而现有技术中并没有考虑手指角度的影响,本发明中为了消除手指角度的不同而带来的验证准确度的影响,在提取手指静脉特征信息时,会结合手指角度传感器测定的手指的角度,然后再进行特征信息的匹配。The difference in finger angle will be the final collected finger vein feature information, but the influence of the finger angle is not considered in the prior art. In the present invention, in order to eliminate the influence of the verification accuracy caused by the difference of the finger angle, the finger is extracted. When the vein characteristic information is combined, the angle of the finger measured by the finger angle sensor is combined, and then the feature information is matched.
附图说明DRAWINGS
图1是本发明的手指静脉识别与面部静脉识别相结合的认证装置结构示意图。1 is a schematic structural view of an authentication device combining finger vein recognition and facial vein recognition of the present invention.
图2是本发明的手指静脉识别与面部静脉识别相结合的认证装置的手指静脉识别部分的结构示意图。2 is a schematic view showing the structure of a finger vein recognition portion of the authentication device in combination with the finger vein recognition and the facial vein recognition of the present invention.
图3是本发明的手指静脉识别与面部静脉识别相结合的认证装置的面部静脉识别部分的结构示意图。Fig. 3 is a view showing the structure of a facial vein recognition portion of the authentication device in combination with the finger vein recognition and the facial vein recognition of the present invention.
具体实施方式detailed description
下面结合附图,通过对具体实施实例的描述,对本发明的具体实施方式如所涉及的各构件的形状、构造、各部分之间的相互位置及连接关系、各部分的作用及工作原理等作进一步的详细说明,并对本发明的认证方法进行详细的说明。The specific embodiments of the present invention, such as the shape and structure of the components involved, the mutual position and connection relationship between the parts, the functions and working principles of the parts, etc., are described below with reference to the accompanying drawings. The detailed description of the authentication method of the present invention will be described in detail.
图1-3是本发明的手指静脉识别与面部静脉识别相结合的认证装置1的结构示意图,根据相应的附图可知,其包括手指静脉特征信息采集装置2和与其连接的面部静脉特征信息采集装置3,另外该认证装置还包括台体4,其中特征信息保存部、数据处理部、匹配特征信息比对部、控制器均设置于该台体4的内部,在该台体4的侧部设置有输入输出接口5,在该台体4的前部设置有输入键盘6。手指静脉特征信息采集装置2设置在台体4的表面上,包括壳体21、第一红外成像光源22、第一红外成像装置23、手指角度传感器24、手指放置座25,其中壳体上设有电源开关或人体感测器,当认证人靠近该装置时,认证装置自动进入开机状态,壳体21的中间部分设置有一个用于伸入手指的半圆形孔,手指放置座25设置在上述半圆形孔内,半圆形孔内顶部中间正对手指放置座的位置上设置有多排第一红外成像光源22,在半圆形孔内侧壁的第一红外成像光源22两侧的每一侧分别设置有两个手指角度传感器24,每一侧的两个手指角度传感器的设置方式为在与手指放置座25平齐的水平位置的两侧各设置一个手指角度传感器,在与手指放置座平齐的水平位置成45度角处的两 侧各设置一个手指角度传感;壳体21底部设置有与台体4内的特征信息保存部、数据处理部、匹配特征信息比对部、控制器相连接的传输装置。面部静脉特征信息采集装置3的底座31可滑动的设置在台体4的表面上靠近手指静脉特征信息采集装置2处,使得认证者可同时进行手指静脉特征信息和面部静脉特征信息的采集,在该底座31上设置有可以转动的和折叠的机械臂32,面部静脉特征信息采集的构件33设置在机械臂32的顶端,其包括外壳34、第二红外成像光源35、第二红外成像装置36、面部位置传感器37、头部位置判断装置38、语音提示装置39。外壳34包括左侧板、右侧板和正面板,左侧板、右侧板互相平行的设置在正面板的两端且分别与正面板垂直,其中左侧板、右侧板及正面形成的空间区域为头部静脉特征信息采集;在左侧板上设置有两排第二红外成像光源35,在右侧板上设置有第二红外成像装置36,在正面板上设置有面部位置传感器37,同时正面板上还设置有感知认证者是否靠近的人体感测器,另外底座内设置有与台体4内的特征信息保存部、数据处理部、匹配特征信息比对部、控制器相连接的传输装置。1-3 is a schematic structural diagram of an authentication device 1 combined with finger vein recognition and facial vein recognition according to the present invention. According to the corresponding drawings, the finger vein feature information collecting device 2 and the facial vein feature information connected thereto are collected. In addition, the authentication device further includes a table body 4, wherein the feature information storage unit, the data processing unit, the matching feature information comparison unit, and the controller are disposed inside the table body 4 at the side of the table body 4. An input/output interface 5 is provided, and an input keyboard 6 is provided at the front of the table 4. The finger vein feature information collecting device 2 is disposed on the surface of the table body 4, and includes a housing 21, a first infrared imaging light source 22, a first infrared imaging device 23, a finger angle sensor 24, and a finger placement seat 25, wherein the housing is provided There is a power switch or a human body sensor. When the authenticator approaches the device, the authentication device automatically enters the power-on state, and the middle portion of the housing 21 is provided with a semi-circular hole for extending into the finger, and the finger placement seat 25 is disposed at In the semicircular hole, a plurality of rows of first infrared imaging light sources 22 are disposed at a position of the top of the semicircular holes in the middle of the finger placement seat, and two sides of the first infrared imaging light source 22 on the inner side wall of the semicircular hole Two finger angle sensors 24 are respectively disposed on each side, and two finger angle sensors on each side are disposed in such a manner that a finger angle sensor is disposed on both sides of the horizontal position flush with the finger placement seat 25, with the finger Place the seat in a horizontal position at a 45 degree angle One finger angle sensor is provided on each side; a bottom portion of the casing 21 is provided with a transmission device that is connected to the feature information storage unit, the data processing unit, the matching feature information comparison unit, and the controller in the table body 4. The base 31 of the facial vein feature information collecting device 3 is slidably disposed on the surface of the table body 4 near the finger vein feature information collecting device 2, so that the authenticator can simultaneously collect the finger vein feature information and the facial vein feature information. The base 31 is provided with a rotatable and folded mechanical arm 32. The facial vein characteristic information collecting member 33 is disposed at the top end of the mechanical arm 32, and includes a housing 34, a second infrared imaging light source 35, and a second infrared imaging device 36. The face position sensor 37, the head position determining device 38, and the voice presenting device 39. The outer casing 34 includes a left side panel, a right side panel and a front panel. The left side panel and the right side panel are disposed parallel to each other at opposite ends of the front panel and respectively perpendicular to the front panel, wherein the left side panel, the right side panel and the front side form a space formed by the front panel The area is the head vein feature information collection; two rows of second infrared imaging light sources 35 are disposed on the left side plate, a second infrared imaging device 36 is disposed on the right side plate, and a face position sensor 37 is disposed on the front panel. At the same time, the front panel is further provided with a human body sensor that senses whether the authenticator is close, and the base is provided with a characteristic information storage unit, a data processing unit, a matching feature information comparison unit, and a controller connected in the base 4. Transmission device.
另外,本发明的手指静脉识别与面部静脉识别相结合的认证装置1的输入输出接口5和输入键盘6可以来进行内外信息的传输,并且上述的输入输出接口5也可以与网络连接,以进一步的与远程的主服务器连接,进行数据信息的传输或认证信息的验证,可定期备份,可以与WIS数据库无缝衔接。In addition, the input/output interface 5 and the input keyboard 6 of the authentication device 1 combined with the finger vein recognition of the present invention can perform internal and external information transmission, and the above-mentioned input/output interface 5 can also be connected to the network to further It is connected with the remote main server to transmit data information or verify the authentication information. It can be backed up regularly and can be seamlessly connected with the WIS database.
本发明的手指静脉识别与面部静脉识别相结合的认证装置进行认证的方法的认证的过程包括下述内容:The process of authenticating the authentication method of the authentication device combined with the finger vein recognition and the facial vein recognition of the present invention includes the following contents:
首先是认证者身份登记过程,最初将需要认证的特定人员的手指静脉特征信息和面部静脉特征信息登记入库,在此登记过程中采集的手指静脉特征信息包括手指多个角度的信息,在登记时让手指转动,采集连续多个角度手指静脉特征信息,并将上述含有角度信息的手指静脉特征信息输入到特征信息保存部;在此登记过程中同时采集的面部静脉特征信息包括通过认证者正面面对的正面板上的面部位置传感器确定的正面角度时采集的面部静脉特征信息,在语音提示装置提示位置正确后进行面部静脉特征信息的采集,并将上述采集的面部静脉特征信息输入到特征信息保存部;在上述两种特征信息采集结束后,在特征信息保存部将采集获取的手指静脉特征信息和面部静脉特征信息在数据处理部形成实时的手指静脉特征信息和面部静脉特征信息匹配组,该匹配组包括了带有角度信息的手指静脉特征信息以及同时采集的面部静脉特征信息,形成匹配组的方法包括了手指静脉的形状、方向以及面部静脉特征的形状,为了提高匹配精度,在数据融合之前,通过下面的数据标准化方法对这些数据进行匹配信息的标准化: The first is the authenticator identity registration process, which initially registers the finger vein feature information and the facial vein feature information of the specific person who needs to be authenticated, and the finger vein feature information collected during the registration process includes information of multiple angles of the finger, and is registered. When the finger is rotated, the finger vein characteristic information of the plurality of angles is continuously collected, and the finger vein characteristic information containing the angle information is input to the feature information storage unit; the facial vein feature information collected simultaneously during the registration process includes the front face of the authenticator. The face vein feature information collected when the face position sensor on the front panel determines the frontal angle is obtained, and the facial vein feature information is collected after the voice prompting device prompts the correct position, and the collected facial vein feature information is input into the feature. After the collection of the two kinds of feature information is completed, the feature information storage unit forms the real-time finger vein feature information and the facial vein feature information matching group in the data processing unit by collecting and acquiring the finger vein feature information and the facial vein feature information. The horse The group includes finger vein feature information with angle information and facial vein feature information collected at the same time. The method of forming a matching group includes the shape and direction of the finger vein and the shape of the facial vein feature. In order to improve the matching precision, before data fusion Standardize the matching information for these data by the following data normalization methods:
a’=(a-c)/σa’=(a-c)/σ
其中a是静脉形状、方向特征的匹配分数,c和σ代表匹配分数a的均值和方差,然后将得到的标准化数据a’作为融合方法的输入数据。Where a is the matching score of the vein shape and the directional characteristic, c and σ represent the mean and variance of the matching score a, and the obtained normalized data a' is then used as the input data of the fusion method.
其中利用上述数据标准化方法将手指静脉特征和面部静脉特征进行数据标准化,获得手指静脉特征标准数据和面部静脉特征标准数据,然后将两种静脉特征标准数据通过加权融合法形成特征信息匹配组,The data standardization method is used to standardize the finger vein feature and the facial vein feature, and the finger vein feature standard data and the facial vein feature standard data are obtained, and then the two vein feature standard data are formed into a feature information matching group by weighted fusion method.
其次是认证过程,在认证者需要进行特征信息认证时,可通过打开开关或通过人体感测器的方式使认证装置自动进入开机状态,手指伸入壳体的半圆形孔,手指静脉特征信息的采集部分进入手指静脉特征信息采集过程,同时,面部静脉特征信息采集部分也进入面部静脉特征信息采集过程,首先,通过所述的手指角度传感器来检测伸入到半圆形孔壳体内的手指的放置信息,即通过四个手指角度传感器来检测指甲弧度的最顶部与水平面的角度,通过该角度来确定手指相对于手指放置座水平面的放置角度信息,同时,通过面部位置传感器拍摄的图像判断头部是否正面面对正面板,即判断头部位置是否相对于正面板有偏转或者有低头、歪头现象发生,如果经过面部位置传感器拍摄的图像判断为认证者的头部没有正面面对正面板,则头部位置判断装置向语音提示装置发出信号,控制语音提示装置发出声音告知认证者移动头部位置,然后面部位置传感器重新拍摄认证者的头部照片,再次经过头部位置判断装置的判断,直至判断结果为头部正面面对正面板时,语音提示装置发出提示,提醒认证者停止头部动作;然后,手指静脉特征信息的采集部分的第一红外成像光源和面部静脉特征信息采集部分的第二红外成像光源发出光线,手指静脉特征信息的采集部分的第一红外成像装置和面部静脉特征信息采集部分的第二红外成像装置将采集得到的手指静脉特征和面部静脉征输入到特征信息保存部,其中手特征信息包括了手指静脉的形状、方向以及面部静脉特征的形状;特征信息保存部将上述特征信息输入到数据处理部进行融合,先通过下面的数据标准化方法对这些数据进行匹配信息的标准化:Followed by the authentication process, when the authenticator needs to perform the feature information authentication, the authentication device can be automatically turned on by opening the switch or by the human body sensor, and the finger extends into the semicircular hole of the housing, and the finger vein characteristic information The collecting part enters the finger vein characteristic information collecting process, and at the same time, the facial vein characteristic information collecting part also enters the facial vein characteristic information collecting process. First, the finger extending into the semicircular hole shell is detected by the finger angle sensor. The placement information, that is, the angle between the topmost portion of the nail curvature and the horizontal plane is detected by four finger angle sensors, and the angle of the finger relative to the horizontal plane of the finger placement seat is determined by the angle, and the image taken by the face position sensor is judged Whether the head faces the front panel positively, that is, whether the head position is deflected relative to the front panel or has a head bow or a hoe phenomenon, and if the image taken by the face position sensor is judged to be that the certifier's head is not facing the front face positively Panel, the head position judging device is directed to the voice The display device sends a signal to control the voice prompting device to send a sound to inform the authenticator to move the head position, and then the face position sensor re-photographs the photo of the authenticator's head, and then passes the judgment of the head position determining device again until the judgment result is the front side of the head. When the front panel is aligned, the voice prompting device issues a prompt to remind the authenticator to stop the head movement; then, the first infrared imaging light source of the collecting portion of the finger vein characteristic information and the second infrared imaging light source of the facial vein characteristic information collecting portion emit light, The first infrared imaging device of the acquisition portion of the finger vein feature information and the second infrared imaging device of the facial vein feature information acquisition portion input the collected finger vein feature and facial vein sign into the feature information storage unit, wherein the hand feature information includes The shape, direction, and shape of the facial vein feature of the finger vein; the feature information storage unit inputs the feature information to the data processing unit for fusion, and first normalizes the matching information by the following data normalization method:
a’=(a-c)/σa’=(a-c)/σ
其中a是静脉形状、方向特征的匹配分数,c和σ代表匹配分数a的均值和方差,然后将得到的标准化数据a’作为融合方法的输入数据,获得手指静脉特征标准数据和面部静脉特征标准数据后,将两种静脉特征标准数据通过加权融合法形成特征信息匹配组;随后上述特征信息匹配组被输入到匹配特征信息比对部,在匹配特征信息比对部中将将认证者当前认证的特征信息匹配组与身份登记时的特征信息匹配组进行比对,该比对包括了手指静脉的形状、方向以及面部静脉特征的形状信息的特征信息匹配组的比对,比如根据当前认证的特征信息 匹配组根据相应的手指静脉的形状、方向以及面部静脉特征的形状的特征在匹配特征信息比对部搜索与该特征最相近的预先登记的特征信息匹配组进行比对;根据上述比对的结果进行身份鉴定,确认身份。Where a is the matching score of the vein shape and direction feature, c and σ represent the mean and variance of the matching score a, and then the obtained normalized data a' is used as the input data of the fusion method to obtain the standard data of the finger vein feature and the standard of the facial vein feature. After the data, the two types of vein characteristic standard data are formed into a feature information matching group by a weighted fusion method; then the above-mentioned feature information matching group is input to the matching feature information comparison portion, and the authenticator is currently authenticated in the matching feature information comparison portion. The feature information matching group is compared with the feature information matching group at the time of identity registration, and the comparison includes the matching of the shape information of the shape and direction of the finger vein and the shape information of the facial vein feature, such as according to the current authentication. Characteristic information The matching group compares the matching feature information matching group with the pre-registered feature information matching group closest to the feature according to the shape, the direction of the corresponding finger vein, and the shape of the facial vein feature; according to the result of the comparison Authenticate and confirm identity.
上述实施例为本发明较佳的实施方式,但本发明的实施方式并不受上述实施例的限制,其他的任何未背离本发明的精神实质与原理下所作的改变、修饰、替代、组合、简化,均应为等效的置换方式,都包含在本发明的保护范围之内。 The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and combinations thereof may be made without departing from the spirit and scope of the invention. Simplifications should all be equivalent replacements and are included in the scope of the present invention.

Claims (4)

  1. 一种手指静脉识别与面部静脉识别相结合的认证装置,其特征在于包括手指静脉特征信息采集装置和与其连接的面部静脉特征信息采集装置,所述认证装置还包括台体,其中特征信息保存部、数据处理部、匹配特征信息比对部、控制器均设置于该台体的内部,在该台体的侧部设置有输入输出接口,在该台体的前部设置有输入键盘;手指静脉特征信息采集装置设置在台体的表面上,包括壳体、第一红外成像光源、第一红外成像装置、手指角度传感器、手指放置座,其中壳体上设有电源开关或人体感测器,当认证人靠近该装置时,认证装置自动进入开机状态,壳体的中间部分设置有一个用于伸入手指的半圆形孔,手指放置座设置在上述半圆形孔内,半圆形孔内顶部中间正对手指放置座的位置上方设置有多排第一红外成像光源,在半圆形孔内侧壁的第一红外成像光源两侧的每一侧分别设置有两个手指角度传感器,上述两个手指角度传感器的设置方式为在与手指放置座平齐的水平位置的两侧各设置一个手指角度传感器,在与手指放置座平齐的水平位置成45度角处的两侧各设置一个手指角度传感;壳体底部设置有与台体内的特征信息保存部、数据处理部、匹配特征信息比对部、控制器相连接的传输装置;面部静脉特征信息采集装置的底座可滑动的设置在台体的表面上靠近手指静脉特征信息采集装置处,使得认证者可同时进行手指静脉特征信息和面部静脉特征信息的采集,在该底座上设置有可以转动和折叠的机械臂,面部静脉特征信息采集的构件设置在机械臂的顶端,其包括面部静脉特征信息采集装置的外壳、第二红外成像光源、第二红外成像装置、面部位置传感器、头部位置判断装置、语音提示装置,面部静脉特征信息采集装置的外壳包括左侧板、右侧板和正面板,左侧板、右侧板互相平行的设置在正面板的两端且分别与正面板垂直,其中左侧板、右侧板及正面形成的空间区域为头部静脉特征信息采集;在左侧板上设置有两排第二红外成像光源,在右侧板上设置有第二红外成像装置,在正面板上设置有面部位置传感器,同时正面板上还设置有感知认证者是否靠近的人体感测器,底座内设置有与台体内的特征信息保存部、数据处理部、匹配特征信息比对部、控制器相连接的传输装置。An authentication device combining finger vein recognition and facial vein recognition, comprising: a finger vein feature information collecting device and a facial vein feature information collecting device connected thereto, the authentication device further comprising a table body, wherein the feature information holding unit a data processing unit, a matching feature information comparison unit, and a controller are disposed inside the table body, and an input/output interface is disposed at a side of the table body, and an input keyboard is disposed at a front portion of the table body; a finger vein The feature information collecting device is disposed on the surface of the table body, and includes a housing, a first infrared imaging light source, a first infrared imaging device, a finger angle sensor, and a finger placement seat, wherein the housing is provided with a power switch or a human body sensor, When the authenticator approaches the device, the authentication device automatically enters the power-on state, and the middle portion of the housing is provided with a semi-circular hole for extending into the finger, and the finger placement seat is disposed in the semi-circular hole, the semi-circular hole A plurality of rows of first infrared imaging light sources are disposed above the position of the finger placement seat in the middle of the inner top, and the first side wall of the semicircular hole Each of the two sides of the external imaging light source is respectively provided with two finger angle sensors, and the two finger angle sensors are arranged in such a manner that a finger angle sensor is disposed on each side of the horizontal position flush with the finger placement seat, The horizontal position of the finger placement seat is set at a 45-degree angle on each side of the table to provide a finger angle sensing; the bottom of the housing is provided with a feature information storage unit, a data processing unit, a matching feature information comparison unit, and a control a connecting device connected to the device; the base of the facial vein feature information collecting device is slidably disposed on the surface of the table body near the finger vein feature information collecting device, so that the authenticator can simultaneously perform finger vein feature information and facial vein feature information Collecting, a mechanical arm that can be rotated and folded is disposed on the base, and a component for collecting facial vein characteristic information is disposed at a top end of the mechanical arm, and includes a casing of the facial vein characteristic information collecting device, a second infrared imaging light source, and a second infrared Imaging device, face position sensor, head position determining device, voice prompting device The outer casing of the facial vein characteristic information collecting device comprises a left side plate, a right side plate and a front side plate, and the left side plate and the right side plate are arranged parallel to each other at both ends of the front panel and respectively perpendicular to the front panel, wherein the left side plate and the right side plate respectively The spatial area formed by the side panel and the front surface is the head vein characteristic information collection; two rows of second infrared imaging light sources are disposed on the left side panel, and a second infrared imaging device is disposed on the right side panel, and the front panel is provided with The face position sensor is further provided with a human body sensor that senses whether the authenticator is close to the front panel, and the base is provided with a feature information storage unit, a data processing unit, a matching feature information comparison unit, and a controller. Transmission device.
  2. 根据权利要求1所述的手指静脉识别与面部静脉识别相结合的认证装置,其特征在于所述的输入输出接口和输入键盘可以来进行内外信息的传输,上述的输入输出接口也可以与网络连接,以进一步的与远程的主服务器连接,进行数据信息的传输或认证信息的验证、定期备份,可以与数据库无缝衔接。The authentication device of the finger vein recognition and the facial vein recognition according to claim 1, wherein the input/output interface and the input keyboard can transmit internal and external information, and the input/output interface can also be connected to the network. To further connect with the remote main server, perform data information transmission or authentication information verification, regular backup, and seamlessly connect with the database.
  3. 一种利用权利要求1所述的手指静脉识别与面部静脉识别相结合的认证装置进行认证的方法,认证的过程包括下述内容:A method for authenticating by using an authentication device combined with finger vein recognition and facial vein recognition according to claim 1, the authentication process comprising the following contents:
    首先是认证者身份登记过程,最初将需要认证的特定人员的手指静脉特征信息和面部静脉特 征信息登记入库,在此登记过程中采集的手指静脉特征信息包括手指多个角度的信息,在登记时让手指转动,采集连续多个角度手指静脉特征信息,并将含有角度信息的手指静脉特征信息输入到特征信息保存部;在此登记过程中同时采集的面部静脉特征信息包括通过认证者正面面对的正面板上的面部位置传感器确定的正面角度时采集的面部静脉特征信息,在语音提示装置提示位置正确后进行面部静脉特征信息的采集,并将上述采集的面部静脉特征信息输入到特征信息保存部;在上述两种特征信息采集结束后,在特征信息保存部将采集获取的手指静脉特征信息和面部静脉特征信息在数据处理部形成实时的手指静脉特征信息和面部静脉特征信息匹配组,该匹配组包括了带有角度信息的手指静脉特征信息以及同时采集的面部静脉特征信息,形成的匹配组包括了手指静脉的形状、方向以及面部静脉特征的形状,在数据融合之前,通过数据标准化方法对这些数据进行匹配信息的标准化,获得手指静脉特征标准数据和面部静脉特征标准数据,然后将两种静脉特征标准数据通过加权融合法形成特征信息匹配组;The first is the Authenticator Identity Registration process, which will initially require the identification of the finger vein characteristics of a particular person and facial veins. The information of the sign is stored in the library. The finger vein feature information collected during the registration process includes information of multiple angles of the finger, and the finger is rotated during registration, and the finger vein characteristic information of multiple angles is collected continuously, and the finger vein containing the angle information is collected. The feature information is input to the feature information storage unit; the facial vein feature information acquired simultaneously during the registration process includes facial vein feature information collected when the frontal angle determined by the face position sensor on the front panel facing the front face of the authenticator is in the voice After the prompting device prompts the position, the facial vein feature information is collected, and the collected facial vein feature information is input to the feature information storage unit; after the two types of feature information are collected, the acquired feature finger is collected in the feature information storage unit. The vein feature information and the facial vein feature information form a real-time finger vein feature information and a facial vein feature information matching group in the data processing portion, the matching group includes finger vein feature information with angle information and facial vein feature information collected at the same time, Matching group The shape and direction of the finger vein and the shape of the facial vein feature are included. Before the data fusion, the matching information of the data is normalized by the data normalization method, and the finger vein characteristic standard data and the facial vein characteristic standard data are obtained, and then two types are obtained. The venous feature standard data is formed into a feature information matching group by a weighted fusion method;
    其次是认证过程,在认证者需要进行特征信息认证时,可通过打开开关或通过人体感测器的方式使认证装置自动进入开机状态,手指伸入壳体的半圆形孔,手指静脉特征信息的采集部分进入手指静脉特征信息采集过程,同时,面部静脉特征信息采集部分也进入面部静脉特征信息采集过程;首先,通过所述的手指角度传感器来检测伸入到半圆形孔壳体内的手指的放置信息,即通过四个手指角度传感器来检测指甲弧度的最顶部与水平面的角度,通过该角度来确定手指相对于手指放置座水平面的放置角度信息,同时,通过面部位置传感器拍摄的图像判断头部是否正面面对正面板,即判断头部位置是否相对于正面板有偏转或者有低头、歪头现象发生,如果经过面部位置传感器拍摄的图像判断为认证者的头部没有正面面对正面板,则头部位置判断装置向语音提示装置发出信号,控制语音提示装置发出声音告知认证者移动头部位置,然后面部位置传感器重新拍摄认证者的头部照片,再次经过头部位置判断装置的判断,直至判断结果为头部正面面对正面板时,语音提示装置发出提示,提醒认证者停止头部动作;然后,手指静脉特征信息的采集部分的第一红外成像光源和面部静脉特征信息采集部分的第二红外成像光源发出光线,手指静脉特征信息的采集部分的第一红外成像装置和面部静脉特征信息采集部分的第二红外成像装置将采集得到的手指静脉特征和面部静脉征输入到特征信息保存部,其中手特征信息包括了手指静脉的形状、方向以及面部静脉特征的形状;特征信息保存部将上述特征信息输入到数据处理部进行融合,先通过数据标准化方法对这些数据进行匹配信息的标准化,获得手指静脉特征标准数据和面部静脉特征标准数据后,将两种静脉特征标准数据通过加权融合法形成特征信息匹配组;随后上述特征信息匹配 组被输入到匹配特征信息比对部,在匹配特征信息比对部中将将认证者当前认证的特征信息匹配组与身份登记时的特征信息匹配组进行比对,该比对包括了手指静脉的形状、方向以及面部静脉特征的形状信息的特征信息匹配组的比对,比如根据当前认证的特征信息匹配组根据相应的手指静脉的形状、方向以及面部静脉特征的形状的特征在匹配特征信息比对部搜索与该特征最相近的预先登记的特征信息匹配组进行比对;根据上述比对的结果进行身份鉴定,确认身份。Followed by the authentication process, when the authenticator needs to perform the feature information authentication, the authentication device can be automatically turned on by opening the switch or by the human body sensor, and the finger extends into the semicircular hole of the housing, and the finger vein characteristic information The collecting part enters the finger vein characteristic information collecting process, and at the same time, the facial vein characteristic information collecting part also enters the facial vein characteristic information collecting process; firstly, the finger extending into the semicircular hole shell is detected by the finger angle sensor The placement information, that is, the angle between the topmost portion of the nail curvature and the horizontal plane is detected by four finger angle sensors, and the angle of the finger relative to the horizontal plane of the finger placement seat is determined by the angle, and the image taken by the face position sensor is judged Whether the head faces the front panel positively, that is, whether the head position is deflected relative to the front panel or has a head bow or a hoe phenomenon, and if the image taken by the face position sensor is judged to be that the certifier's head is not facing the front face positively Panel, the head position judging device is directed to the voice The display device sends a signal to control the voice prompting device to send a sound to inform the authenticator to move the head position, and then the face position sensor re-photographs the photo of the authenticator's head, and then passes the judgment of the head position determining device again until the judgment result is the front side of the head. When the front panel is aligned, the voice prompting device issues a prompt to remind the authenticator to stop the head movement; then, the first infrared imaging light source of the collecting portion of the finger vein characteristic information and the second infrared imaging light source of the facial vein characteristic information collecting portion emit light, The first infrared imaging device of the acquisition portion of the finger vein feature information and the second infrared imaging device of the facial vein feature information acquisition portion input the collected finger vein feature and facial vein sign into the feature information storage unit, wherein the hand feature information includes The shape, the direction of the finger vein, and the shape of the facial vein feature; the feature information storage unit inputs the feature information to the data processing unit for fusion, and first normalizes the matching information by using the data normalization method to obtain the standard number of the finger vein feature Wherein the facial vein and the standard data, the standard data of two vein feature information matching the group formed by weighting fusion method; then the characteristic information matches The group is input to the matching feature information comparison unit, and the matching feature information matching group compares the feature information matching group currently authenticated by the authenticator with the feature information matching group at the time of identity registration, and the comparison includes the finger vein The feature information of the shape, direction, and shape information of the facial vein feature matches the alignment of the group, for example, according to the currently authenticated feature information, the matching group matches the feature according to the shape, direction, and shape of the facial vein feature of the corresponding finger vein. The matching unit searches for the pre-registered feature information matching group closest to the feature for comparison; performs identity authentication according to the result of the comparison, and confirms the identity.
  4. 根据权利要求3所述的手指静脉识别与面部静脉识别相结合的认证方法,其特征在于所述的数据标准化方法通过下面的公式进行:The authentication method of the combination of finger vein recognition and facial vein recognition according to claim 3, wherein said data normalization method is performed by the following formula:
    a’=(a-c)/σa’=(a-c)/σ
    其中a是静脉形状、方向特征的匹配分数,c和σ代表匹配分数a的均值和方差,然后将得到的标准化数据a’作为融合方法的输入数据;Where a is the matching score of the vein shape and direction feature, c and σ represent the mean and variance of the matching score a, and then the obtained normalized data a' is used as the input data of the fusion method;
    利用上述数据标准化方法将手指静脉特征和面部静脉特征进行数据标准化,获得手指静脉特征标准数据和面部静脉特征标准数据,然后将两种静脉特征标准数据通过加权融合法形成特征信息匹配组。 The finger vein feature and the facial vein feature were normalized by the above data standardization method, and the finger vein feature standard data and the facial vein feature standard data were obtained, and then the two vein feature standard data were formed into the feature information matching group by the weighted fusion method.
PCT/CN2016/071412 2015-02-12 2016-01-20 Authentication device and method combining finger vein recognition and facial vein recognition WO2016127767A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510073525.2A CN104615993B (en) 2015-02-12 2015-02-12 The certification device and method that a kind of finger vena identification combines with face hand vein recognition
CN201510073525.2 2015-02-12

Publications (1)

Publication Number Publication Date
WO2016127767A1 true WO2016127767A1 (en) 2016-08-18

Family

ID=53150430

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/071412 WO2016127767A1 (en) 2015-02-12 2016-01-20 Authentication device and method combining finger vein recognition and facial vein recognition

Country Status (2)

Country Link
CN (1) CN104615993B (en)
WO (1) WO2016127767A1 (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104615993B (en) * 2015-02-12 2016-08-24 张丽琴 The certification device and method that a kind of finger vena identification combines with face hand vein recognition
CN106169062B (en) * 2016-06-08 2019-05-21 杭州电子科技大学 A kind of implementation method referring to vein fusion fuzzy vault
CN108090415A (en) * 2017-11-24 2018-05-29 江西智梦圆电子商务有限公司 A kind of identity comparison method identified based on face and vena metacarpea
JP7269711B2 (en) * 2018-10-03 2023-05-09 株式会社日立製作所 Biometric authentication system, biometric authentication method and program
CN112668554A (en) * 2021-01-18 2021-04-16 钧安科技(深圳)有限公司 Vein collection device and vein collection identification method
CN117437665A (en) * 2023-11-27 2024-01-23 江苏芯灵智能科技有限公司 Finger vein feature extraction method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009301120A (en) * 2008-06-10 2009-12-24 Glory Ltd Living body detection sensor
CN103699995A (en) * 2012-09-27 2014-04-02 ***股份有限公司 Payment authentication method based on fingerprints and finger veins
CN203673534U (en) * 2014-01-23 2014-06-25 山东科一力电气有限公司 Finger vein attendance machine
CN104598797A (en) * 2015-02-12 2015-05-06 张丽琴 Authentication device and authentication method with combination of face recognition, face vein authentication and finger vein authentication
CN104615993A (en) * 2015-02-12 2015-05-13 张丽琴 Finger vein reorganization and facial vein recognition combined authentication device and method
CN204423392U (en) * 2015-02-12 2015-06-24 张丽琴 Based on the authenticate device that finger vena identification combines with facial hand vein recognition

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4604117B2 (en) * 2008-11-10 2010-12-22 株式会社日立製作所 Personal authentication apparatus and method
CN101464947B (en) * 2009-01-16 2011-04-20 哈尔滨工程大学 Device for collecting bi-mode biology image based on fingerprint and finger vein
CN102542258B (en) * 2011-12-16 2013-11-20 天津理工大学 Imaging device based on finger biometric information and multimoding identity recognition method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009301120A (en) * 2008-06-10 2009-12-24 Glory Ltd Living body detection sensor
CN103699995A (en) * 2012-09-27 2014-04-02 ***股份有限公司 Payment authentication method based on fingerprints and finger veins
CN203673534U (en) * 2014-01-23 2014-06-25 山东科一力电气有限公司 Finger vein attendance machine
CN104598797A (en) * 2015-02-12 2015-05-06 张丽琴 Authentication device and authentication method with combination of face recognition, face vein authentication and finger vein authentication
CN104615993A (en) * 2015-02-12 2015-05-13 张丽琴 Finger vein reorganization and facial vein recognition combined authentication device and method
CN204423392U (en) * 2015-02-12 2015-06-24 张丽琴 Based on the authenticate device that finger vena identification combines with facial hand vein recognition

Also Published As

Publication number Publication date
CN104615993B (en) 2016-08-24
CN104615993A (en) 2015-05-13

Similar Documents

Publication Publication Date Title
WO2016127766A1 (en) Authentication device and authentication method combining face recognition, face vein authentication and finger vein authentication
WO2016127767A1 (en) Authentication device and method combining finger vein recognition and facial vein recognition
Adeoye A survey of emerging biometric technologies
JP4740251B2 (en) Method and apparatus for identification based on biometrics
US8265347B2 (en) Method and system for personal identification using 3D palmprint imaging
Jain et al. Biometric identification
WO2016127765A1 (en) Authentication device and authentication method combining finger vein recognition with wrist vein recognition and fingernail recognition
JP6005750B2 (en) Authentication apparatus and authentication method
TWI539386B (en) The use of a variety of physiological information mixed identification of the identity of the system and methods
US20040017934A1 (en) Method and apparatus for contactless hand recognition
CN108427944A (en) A kind of fingerprint recognition system and recognition methods
CN204440516U (en) A kind ofly various features identification is adopted to combine the aviation security inspection device of certification
US20110067822A1 (en) System and method for enhancing the safety of electrically operated folding partitions
CN204406402U (en) A kind ofly adopt face recognition, authenticate device that facial vena identification combines with finger vena identification
Sepasian et al. Vitality detection in fingerprint identification
CN204440570U (en) A kind ofly adopt finger vena identification and the type automatic teller machine of facial hand vein recognition in conjunction with certification
Manjunath et al. Analysis of unimodal and multimodal biometric system using iris and fingerprint
CN204423392U (en) Based on the authenticate device that finger vena identification combines with facial hand vein recognition
AnkurBansal et al. A Review Paper on FACIAL RECOGNITION‖
CN204406431U (en) A kind ofly adopt face recognition, facial vena identification and the automatic customs safety check apparatus of finger vena identification in conjunction with certification
Gupta Advances in multi modal biometric systems: a brief review
Sepasian et al. Liveness and spoofing in fingerprint identification: Issues and challenges
Garg et al. Performance Analysis of Uni-modal and Multimodal Biometric System
Satone KKWETC Indian face database
CN204406432U (en) A kind ofly adopt wrist hand vein recognition and the identity recognition device of nail identification in conjunction with certification

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: 16748568

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03/01/2018)

122 Ep: pct application non-entry in european phase

Ref document number: 16748568

Country of ref document: EP

Kind code of ref document: A1