WO2017113286A1 - 一种认证方法及装置 - Google Patents

一种认证方法及装置 Download PDF

Info

Publication number
WO2017113286A1
WO2017113286A1 PCT/CN2015/100100 CN2015100100W WO2017113286A1 WO 2017113286 A1 WO2017113286 A1 WO 2017113286A1 CN 2015100100 W CN2015100100 W CN 2015100100W WO 2017113286 A1 WO2017113286 A1 WO 2017113286A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
dimensional image
authentication
facial features
feature points
Prior art date
Application number
PCT/CN2015/100100
Other languages
English (en)
French (fr)
Inventor
宋展
董玉明
Original Assignee
深圳先进技术研究院
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 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Priority to CN201580001264.1A priority Critical patent/CN107182218A/zh
Priority to PCT/CN2015/100100 priority patent/WO2017113286A1/zh
Publication of WO2017113286A1 publication Critical patent/WO2017113286A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
    • G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
    • G03B35/00—Stereoscopic photography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/36—User authentication by graphic or iconic representation

Definitions

  • the invention belongs to the field of safety certification, and particularly relates to an authentication method and device.
  • the mobile phone unlocking authentication usually requires the user to input an unlocking password. If other people know the unlocking password of the mobile phone user, it is easy to read the content in the user's mobile phone, and setting the unlocking password cannot guarantee that the mobile phone is used by the user alone. It brings security risks to the content of the user's mobile phone.
  • Another example is the existing access control authentication, which usually requires the user to input a password or obtain a user image, but the acquired user image is usually a two-dimensional image, and there is a certain security risk in using the user image for security authentication, and the malicious attacker can use the user's photo. Certify.
  • the present invention provides an authentication method and apparatus for preventing two-dimensional photo attacks, which are used to solve the problem of security risks in two-dimensional image authentication in the prior art.
  • the present invention provides an authentication method, including
  • the three-dimensional image of the user is matched with the three-dimensional image pre-stored by the user, and after the matching is passed, the three-dimensional image of the user is authenticated.
  • the invention further provides an authentication device, including
  • An acquiring module configured to: open an optical projection module to project a structural light pattern according to an authentication system startup instruction, and obtain a user image with a structured light pattern obtained by the camera module;
  • a processing module configured to calculate a three-dimensional image of the user according to a user image with a structured light pattern and calibration parameters of the camera module and the optical projection module;
  • the matching module is configured to match the three-dimensional image of the user with the three-dimensional image pre-stored by the user, and after the matching is passed, the three-dimensional image of the user is authenticated.
  • the authentication method and device provided by the invention can obtain the user's three-dimensional image by collecting the user image with the structured light pattern of the user, and matching the three-dimensional image of the user with the three-dimensional image pre-stored by the user, thereby ensuring the security of the authentication. Prevent attacks from 2D images.
  • the present invention can be applied to an authentication process of a mobile terminal, an authentication process such as an Alipay transaction, an access authentication process, and the like.
  • FIG. 1 is a flowchart of an authentication method according to an embodiment of the present invention.
  • FIG. 2 is a structural diagram of an optical projection module according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of a process of matching a three-dimensional image of a user with a three-dimensional image pre-stored by a user according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of a feature point of a facial facial feature of a user rotated to a horizontal direction according to an embodiment of the present invention
  • FIG. 5 is a structural diagram of an authentication apparatus according to an embodiment of the present invention.
  • FIG. 6 is a flowchart of a process for unlocking an authentication of a mobile phone according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of an authentication method according to an embodiment of the present invention.
  • the user image of the user with the structured light pattern is collected, and the three-dimensional image of the user is calculated and analyzed, and the three-dimensional image of the user is matched with the three-dimensional image pre-stored by the user, thereby ensuring the security of the authentication and preventing the attack of the two-dimensional image.
  • the authentication method described in this implementation includes:
  • Step 101 Turn on the optical projection module to project the structural light pattern according to the authentication system startup instruction, and turn on the camera module to acquire the user image with the structured light pattern;
  • Step 102 Calculate a three-dimensional image of the user according to a user image with a structured light pattern and calibration parameters of the camera module and the optical projection module;
  • the image coordinates of the coded feature points are extracted from the user image with the structured light pattern, and the coded values of the coded feature points are detected.
  • the process is closely related to the coding rules of the structured light patterns, and different structural light correspondences are used. Different coding algorithms and decoding algorithms should be designed accordingly, and this application does not limit this.
  • the three-dimensional coordinates of the coded feature points are calculated by combining the calibration parameters of the camera module and the optical projection module, and the three-dimensional model of the user is obtained by combining the point cloud processing and the network processing.
  • the calibration of the camera module and the optical projection module can be implemented by using an existing method, which is not described in detail in this application.
  • Step 103 Match the three-dimensional image of the user with the three-dimensional image pre-stored by the user, and after the matching is passed, the three-dimensional image authentication of the user passes.
  • the optical projection module of the present application includes a light source 201, a structured light grating 202, and an optical lens group 203.
  • the light emitted by the light source is irradiated to the user through the structured light grating and the optical lens group.
  • the light source 201 type is preferably an array of LEDs in order to reduce the size of the optical projection module, providing high brightness light while increasing illumination uniformity.
  • Another light source may be a visible light source or a near-infrared light source. If a near-infrared light source is used, an infrared filter is attached to the outside of the camera module.
  • the pattern design of the structured light grating 202 is preferably binary geometric coding, that is, the entire pattern is formed by different geometric figures (elements) according to the principle of pseudo-random matrix. According to the pseudo-random coding principle, the pattern has a unique window characteristic, that is, a combination order of several elements. Only appears once in the entire pattern.
  • the coding mode described in this embodiment can improve the stability of decoding and improve the success rate of subsequent decoding.
  • the optical lens group 203 adopts a miniature optical lens group to reduce the size of the optical projection module, and the optical lens group can design a lens system according to the distance and range (viewing angle) required for shooting.
  • the authentication system startup instruction is an unlocking instruction issued by the mobile terminal, and the unlocking is performed by pressing a button, or double-clicking the screen, or sliding the screen, or inputting information, and the user's three-dimensional image is authenticated and displayed after being unlocked. screen.
  • the authentication system startup instruction is a transaction authentication instruction, such as authentication at the payment of Alipay, and the three-dimensional image of the user is sent to the remote server, and the remote server determines the three-dimensional image of the user and the three-dimensional image pre-stored by the user. Whether it matches, the user's 3D image is authenticated and continues to trade.
  • the authentication system startup command is an access control authentication command
  • the user's three-dimensional image authentication is passed after the access control door is opened.
  • the authentication method provided by the present invention is applied to mobile terminal unlocking, Alipay transaction authentication and access control authentication, and can prevent malicious attacks by others and ensure the security of authentication.
  • FIG. 3 is a flowchart of a process of matching a three-dimensional image of a user with a three-dimensional image pre-stored by a user according to an embodiment of the present invention. Specifically, matching the three-dimensional image of the user with the three-dimensional image pre-stored by the user further includes:
  • Step 301 Determine a feature point of the facial features of the user according to the three-dimensional image of the user;
  • Step 302 Obtain a rotation angle of the user according to a feature point of the facial features of the user's face
  • FIG. 4 is a schematic diagram in which feature points are vertically mapped on the same horizontal plane, and reference numerals A, B, and C in FIG. 4 are positions of feature points of the facial features of the user face relative to the reference plane N
  • the reference plane N is the plane in which the eyes are located when the user is photographing the front side. It is assumed that the feature points A and B are the positions where the eyes are mapped to the horizontal plane, and the feature points C are the positions where the nose is mapped to the horizontal plane. If the user is facing the lens when shooting, the feature points A and B should be on the reference plane N, As can be seen from FIG. 4, the user does not face the lens when shooting, and it can be determined that the user is rotated by ⁇ when shooting according to the feature points A, B and the reference plane N.
  • Step 303 Determine a relative height between feature points of the facial features of the user according to the rotation angle
  • the feature points of all the facial features of the user may be uniformly rotated by a point from the origin, and then the relative height between the feature points of the facial features of the user's face may be determined after rotation, as shown in FIG. 4A'.
  • B' and C' are the feature point positions after rotation.
  • the relative height between the feature points of the facial features of the user's face is directly calculated according to the angle of rotation.
  • Step 304 Match the relative height of the feature points of the facial features of the user to the relative heights of the feature points of the facial features of the user in the three-dimensional image pre-stored by the user.
  • This embodiment can speed up the authentication process of the user's three-dimensional image, consider the feature points of the facial features that embody the user features, and correct the angle of the user's rotation to the same horizontal plane before matching, which can improve the matching precision.
  • the authentication method provided by the invention collects the user image with the structured light pattern of the user, calculates and analyzes the three-dimensional image of the user, and matches the three-dimensional image of the user with the three-dimensional image pre-stored by the user, thereby ensuring the security of the authentication and preventing the two-dimensional image. Image attack.
  • the present invention can be applied to an authentication process of a mobile terminal, an authentication process such as an Alipay transaction, an access authentication process, and the like.
  • FIG. 5 is a structural diagram of an authentication apparatus according to an embodiment of the present invention.
  • the device can be implemented by a logic circuit or a chip, or installed in an existing high-performance computing terminal, such as a mobile phone, a tablet computer, a computer, or the like, or the functions of the components can be implemented by software in a functional module manner.
  • the authentication device includes
  • the obtaining module 501 is configured to: open an optical projection module to project a structural light pattern according to an authentication system startup instruction, and obtain a user image with a structured light pattern obtained by the camera module;
  • the processing module 502 is configured to calculate a three-dimensional image of the user according to a user image with a structured light pattern and calibration parameters of the camera module and the optical projection module;
  • the matching module 503 is configured to match the three-dimensional image of the user with the three-dimensional image pre-stored by the user, and after the matching is passed, the three-dimensional image of the user is authenticated.
  • the acquiring module uses an unlocking command issued by the mobile terminal as an authentication system startup command, and displays the unlocked screen after the user's three-dimensional image authentication passes.
  • the acquiring module uses the transaction authentication command as the authentication system startup command, and the user continues to trade after the three-dimensional image authentication is passed.
  • the acquiring module uses the access control authentication command as the authentication system startup command, and the user's three-dimensional image authentication passes to open the access control door.
  • the matching module 503 is specifically configured to:
  • the relative heights of the feature points of the facial features of the user are matched with the relative heights of the feature points of the facial features of the user in the three-dimensional image pre-stored by the user.
  • the authentication method device can obtain the user's three-dimensional image by collecting the user image with the structured light pattern of the user, and matching the three-dimensional image of the user with the three-dimensional image pre-stored by the user, thereby ensuring the security of the authentication and preventing Attack of 2D images.
  • the present invention can be applied to an authentication process of a mobile terminal, an authentication process such as an Alipay transaction, an access authentication process, and the like.
  • the detailed process of unlocking the mobile phone includes:
  • Step 601 Start unlocking by double-clicking the mobile phone screen, and at the same time, start the optical projection module to project the structural light pattern, and activate the camera module to acquire the user's face image with the structured light pattern.
  • Step 602 Extract image coordinates of the encoded feature points from the user face image with the structured light pattern, and detect the encoded value of the encoded feature points.
  • Step 603 The encoded value of the feature point is combined with the calibration parameters of the camera module and the optical projection module to calculate the three-dimensional coordinates at the coding feature point, and the three-dimensional image of the user face is obtained according to the three-dimensional coordinates of the feature point.
  • Step 604 Determine a feature point of the facial features of the user according to the three-dimensional image of the user's face.
  • Step 605 Obtain a rotation angle of the user according to the feature points of the facial features of the user.
  • Step 606 Rotate the feature points of the facial features of the user according to the rotation angle to determine the relative heights of the feature points of the facial features of the user after the rotation.
  • Step 607 Matching the relative heights of the feature points of the rotated facial features of the user to the relative heights of the feature points of the facial features of the user in the three-dimensional image pre-stored by the user, when the feature points satisfying the matching condition reach a certain threshold , the matching is passed, the user is unlocked, and the unlocked screen is displayed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Collating Specific Patterns (AREA)
  • Telephone Function (AREA)
  • Lock And Its Accessories (AREA)

Abstract

本发明提供了一种认证方法及装置，认证方法包括：根据认证系统启动指令开启光学投射模块投射结构光图案，开启摄像模块获取带有结构光图案的用户图像；根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；将所述用户的三维图像与所述用户预存的三维图像进行匹配，匹配通过后，用户的三维图像认证通过。本发明通过采集用户的带有结构光图案的用户图像，计算分析得到用户的三维图像，将用户的三维图像与用户预存的三维图像匹配，能够保证认证的安全性，防止二维图像的攻击。

Description

一种认证方法及装置 技术领域
本发明属于安全认证领域，特别涉及一种认证方法及装置。
背景技术
现有技术中，手机解锁认证通常需要用户输入解锁密码，若其他人知晓手机用户的解锁密码，很容易读取用户手机中的内容，设置解锁密码的方式不能保证手机为用户一人所使用，这就给用户手机中的内容带来了安全隐患。
又如现有门禁认证，通常是需要用户输入密码，或获取用户图像，但获取的用户图像通常为二维图像，使用用户图像进行安全认证存在一定的安全隐患，恶意攻击者可使用用户的照片进行认证。
发明内容
本发明提供一种防止二维照片攻击的认证方法及装置，用于解决现有技术中二维图像认证存在安全隐患的问题。
为了解决上述技术问题，本发明提供一种认证方法，包括，
根据认证系统启动指令开启光学投射模块投射结构光图案，开启摄像模块获取带有结构光图案的用户图像；
根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
将所述用户的三维图像与所述用户预存的三维图像进行匹配，匹配通过后，用户的三维图像认证通过。
本发明另提供一种认证装置，包括，
获取模块，用于根据认证系统启动指令开启光学投射模块投射结构光图案，获取摄像模块得到的带有结构光图案的用户图像；
处理模块，用于根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
匹配模块，用于将用户的三维图像与所述用户预存的三维图像匹配，匹配通过后，用户的三维图像认证通过。
本发明提供的认证方法及装置，通过采集用户的带有结构光图案的用户图像，计算分析得到用户的三维图像，将用户的三维图像与用户预存的三维图像匹配，能够保证认证的安全性，防止二维图像的攻击。本发明可应用于移动终端的解锁、支付宝等交易时的认证过程、门禁认证过程等。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明一实施例的认证方法流程图；
图2为本发明一实施例的光学投射模块结构图；
图3为本发明一实施例的用户的三维图像与用户预存的三维图像匹配过程的流程图；
图4为本发明一实施例的用户脸部五官的特征点旋转至水平方向的示意图；
图5为本发明一实施例的认证装置结构图；
图6为本发明一实施例的手机解锁认证过程流程图。
具体实施方式
为了使本发明的技术特点及效果更加明显，下面结合附图对本发明的技术方案做进一步说明，本发明也可有其他不同的具体实例来加以说明或实施，任何本领域技术人员在权利要求范围内做的等同变换均属于本发明的保护范畴。
如图1所示，图1为本发明一实施例的认证方法流程图。
本实施例通过采集用户的带有结构光图案的用户图像，计算分析得到用户的三维图像，将用户的三维图像与用户预存的三维图像匹配，能够保证认证的安全性，防止二维图像的攻击。
具体的，本实施所述的认证方法包括：
步骤101：根据认证系统启动指令开启光学投射模块投射结构光图案，开启摄像模块获取带有结构光图案的用户图像；
步骤102：根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
具体的，先从带有结构光图案的用户图像中提取出编码特征点的图像坐标，以及检测编码特征点的编码值，该过程与结构光图案的编码规则密切相关，采用不同的结构光对应不同的编码算法，解码算法要做相应的设计，本申请对此不做限制。
得到编码特征点及特征点的编码值后，结合摄像模块与光学投射模块的标定参数计算出编码特征点处的三维坐标，结合点云处理和网络化处理获取用户的三维模型。其中，摄像模块及光学投射模块的标定可采用现有方法实现，本申请对此不再进行详细的说明。
步骤103：将所述用户的三维图像与所述用户预存的三维图像进行匹配，匹配通过后，用户的三维图像认证通过。
如图2所示，本申请所述的光学投射模块包括光源201、结构光光栅202及光学镜头组203，光源发出的光通过结构光光栅及光学镜头组照射至用户上。
光源201类型优选LED阵列，以便减小光学投射模块的尺寸，提供高亮度光，同时增加光照均匀性。另光源可采用可见光光源或近红外光源，若选用近红外光源，则在相机模块外侧加装一红外滤光片。
结构光光栅202的图案设计优选二值几何编码，即由不同的几何图形(元素)按照伪随机矩阵原理构成整个图案，根据伪随机编码原理，图案存在唯一窗口特性，即若干个元素的组合顺序在整个图案中只出现一次。
一实施例中，采用8种不同的几何图形，利用本原多项式为h(x)＝x4+x+a3生成伪随机序列，通过折叠处理，得到65X63的图形矩阵，每个矩阵元素为一个几何图形，根据图形矩阵选定编码点，由编码点周围的几何图形组成编码值，根据编码值即可确定编码点的位置。本实施例所述的编码方式能够提高解码的稳定性，提高后续解码的成功率。
光学镜头组203采用微型光学镜头组，以便减小光学投射模块的尺寸，光学镜头组可根据所需拍摄的距离及范围(视角)，有针对性的设计镜头系统。
本发明一实施例中，所述认证系统启动指令为移动终端发出的解锁指令，通过按压按键，或双击屏幕，或滑动屏幕，或输入信息启动解锁，用户的三维图像认证通过后显示解锁后的屏幕。
本发明一实施例中，所述认证系统启动指令为交易认证指令，如支付宝付款时的认证，将用户的三维图像发送至远端服务器，远端服务器确定用户的三维图像与用户预存的三维图像是否匹配，用户的三维图像认证通过后继续交易。
本发明一实施例中，所述认证系统启动指令为门禁认证指令，用户的三维图像认证通过后打开门禁门。
本发明提供的认证方法应用于移动终端解锁、支付宝交易认证及门禁认证中，能够防止他人的恶意攻击，保证认证的安全。
如图3所示，图3为本发明一实施例的用户的三维图像与用户预存的三维图像匹配过程的流程图。具体的，将所述用户的三维图像与所述用户预存的三维图像进行匹配进一步包括，
步骤301：根据用户的三维图像确定用户脸部五官的特征点；
步骤302：根据用户脸部五官的特征点得到用户的旋转角度；
详细的说，如图4所示，图4为特征点垂直映射于同一水平平面上的示意图，图4中的标号A、B、C为用户脸部五官的特征点相对基准面N的位置，基准面N为用户正面拍摄时眼睛所在的平面。假设特征点A、B为眼睛映射到水平平面的位置，特征点C为鼻子映射到水平平面的位置，如果用户拍摄时为正对镜头，则特征点A、B应在基准面N上，由图4可知，用户拍摄时未正对镜头，根据特征点A、B及基准面N可确定用户拍摄时旋转了α。
步骤303：根据所述旋转角度确定用户脸部五官的特征点之间的相对高度；
具体实施时，一实施例中，可采用将所有用户脸部五官的特征点以一点为原点统一旋转α，旋转后再确定用户脸部五官的特征点之间的相对高度，如图4A’、B’、C’为旋转后的特征点位置。
另一实施例中，根据旋转角度直接计算用户脸部五官的特征点之间的相对高度。
步骤304：将用户脸部五官的特征点的相对高度与所述用户预存的三维图像中用户脸部五官的特征点的相对高度进行匹配。
具体实施时，考虑到误差的存在，当用户脸部五官的特征点的相对高度与用户预存的三维图像中用户脸部五官的特征点的相对高度在一预定范围内时，则认为匹配。
本实施例能够加快用户三维图像的认证过程，考虑体现用户特征的五官处的特征点，在匹配前，将用户旋转的角度矫正到同一水平面上，能够提高匹配的精度。
本发明提供的认证方法通过采集用户的带有结构光图案的用户图像，计算分析得到用户的三维图像，将用户的三维图像与用户预存的三维图像匹配，能够保证认证的安全性，防止二维图像的攻击。本发明可应用于移动终端的解锁、支付宝等交易时的认证过程、门禁认证过程等。
如图5所示，图5为本发明一实施例的认证装置结构图。该装置可以通过逻辑电路或者芯片实现，或者安装于现有的高性能计算终端，例如手机、平板电脑、计算机等设备中，或者以功能模块的方式由软件实现各部件的功能。
具体的，该认证装置包括，
获取模块501，用于根据认证系统启动指令开启光学投射模块投射结构光图案，获取摄像模块得到的带有结构光图案的用户图像；
处理模块502，用于根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
匹配模块503，用于将用户的三维图像与所述用户预存的三维图像匹配，匹配通过后，用户的三维图像认证通过。
本发明一实施例中，所述获取模块将移动终端发出的解锁指令作为认证系统启动指令，用户的三维图像认证通过后显示解锁后的屏幕。
本发明一实施例中，所述获取模块将交易认证指令作为认证系统启动指令，用户的三维图像认证通过后继续交易。
本发明一实施例中，所述获取模块将门禁认证指令作为认证系统启动指令，用户的三维图像认证通过后打开门禁门。
详细的说，本发明一实施例中，所述匹配模块503具体用于，
根据用户的三维图像确定用户脸部五官的特征点；
根据用户脸部五官的特征点得到用户的旋转角度；
根据所述旋转角度确定用户脸部五官的特征点的相对高度；
将用户脸部五官的特征点的相对高度与所述用户预存的三维图像中用户脸部五官的特征点的相对高度进行匹配。
本发明提供的认证方法装置，通过采集用户的带有结构光图案的用户图像，计算分析得到用户的三维图像，将用户的三维图像与用户预存的三维图像匹配，能够保证认证的安全性，防止二维图像的攻击。本发明可应用于移动终端的解锁、支付宝等交易时的认证过程、门禁认证过程等。
为了更清楚说明本申请的技术方案，下面以手机解锁为例进行详细的说明。
如图6所示，手机解锁认证的详细流程包括：
步骤601：通过双击手机屏幕启动解锁，于此同时启动光学投射模块投射结构光图案，启动摄像模块获取带有结构光图案的用户脸部图像。
步骤602：从带有结构光图案的用户脸部图像中提取出编码特征点的图像坐标，检测编码特征点的编码值。
步骤603：特征点的编码值结合摄像模块与光学投射模块的标定参数计算出编码特征点处的三维坐标，根据特征点的三维坐标得到用户脸部三维图像。
步骤604：根据用户脸部三维图像确定用户脸部五官的特征点。
步骤605：根据用户脸部五官的特征点得到用户的旋转角度。
步骤606：根据旋转角度旋转用户脸部五官的特征点，确定旋转后的用户脸部五官的特征点的相对高度。
步骤607：将旋转后的用户脸部五官的特征点的相对高度与所述用户预存的三维图像中用户脸部五官的特征点的相对高度进行匹配，当满足匹配条件的特征点达到一定阈值时，匹配通过，实现用户解锁，显示解锁后的屏幕。
以上所述仅用于说明本申请的技术方案，任何本领域普通技术人员均可在不违背本发明的精神及范畴下，对上述实施例进行修饰与改变。因此，本发明的权利保护范围应视权利要求范围为准。

Claims (10)

  1. 一种认证方法，其特征在于，包括，
    根据认证系统启动指令开启光学投射模块投射结构光图案，开启摄像模块获取带有结构光图案的用户图像；
    根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
    将所述用户的三维图像与所述用户预存的三维图像进行匹配，匹配通过后，用户的三维图像认证通过。
  2. 如权利要求1所述的认证方法，其特征在于，所述认证系统启动指令为移动终端发出的解锁指令，用户的三维图像认证通过后显示解锁后的屏幕。
  3. 如权利要求1所述的认证方法，其特征在于，所述认证系统启动指令为交易认证指令，用户的三维图像认证通过后继续交易。
  4. 如权利要求1所述的认证方法，其特征在于，所述认证系统启动指令为门禁认证指令，用户的三维图像认证通过后打开门禁门。
  5. 如权利要求1至4任一项所述的认证方法，其特征在于，将所述用户的三维图像与所述用户预存的三维图像进行匹配进一步包括，
    根据用户的三维图像确定用户脸部五官的特征点；
    根据用户脸部五官的特征点得到用户的旋转角度；
    根据所述旋转角度确定用户脸部五官的特征点之间的相对高度；
    将用户脸部五官的特征点的相对高度与所述用户预存的三维图像中用户脸部五官的特征点的相对高度进行匹配。
  6. 一种认证装置，其特征在于，包括，
    获取模块，用于根据认证系统启动指令开启光学投射模块投射结构光图案，获取摄像模块得到的带有结构光图案的用户图像；
    处理模块，用于根据带有结构光图案的用户图像及摄像模块与光学投射模块的标定参数计算得到所述用户的三维图像；
    匹配模块，用于将用户的三维图像与所述用户预存的三维图像匹配，匹配通过后，用户的三维图像认证通过。
  7. 如权利要求6所述的认证装置，其特征在于，所述获取模块将移动终端发出的解锁指令作为认证系统启动指令，用户的三维图像认证通过后显示解锁后的屏幕。
  8. 如权利要求6所述的认证装置，其特征在于，所述获取模块将交易认证指令作为认证系统启动指令，用户的三维图像认证通过后继续交易。
  9. 如权利要求6所述的认证装置，其特征在于，所述获取模块将门禁认证指令作为认证系统启动指令，用户的三维图像认证通过后打开门禁门。
  10. 如权利要求6至9任一项所述的认证装置，其特征在于，所述匹配模块具体用于，
    根据用户的三维图像确定用户脸部五官的特征点；
    根据用户脸部五官的特征点得到用户的旋转角度；
    根据所述旋转角度确定用户脸部五官的特征点的相对高度；
    将用户脸部五官的特征点的相对高度与所述用户预存的三维图像中用户脸部五官的特征点的相对高度进行匹配。
PCT/CN2015/100100 2015-12-31 2015-12-31 一种认证方法及装置 WO2017113286A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201580001264.1A CN107182218A (zh) 2015-12-31 2015-12-31 一种认证方法及装置
PCT/CN2015/100100 WO2017113286A1 (zh) 2015-12-31 2015-12-31 一种认证方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/100100 WO2017113286A1 (zh) 2015-12-31 2015-12-31 一种认证方法及装置

Publications (1)

Publication Number Publication Date
WO2017113286A1 true WO2017113286A1 (zh) 2017-07-06

Family

ID=59224105

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/100100 WO2017113286A1 (zh) 2015-12-31 2015-12-31 一种认证方法及装置

Country Status (2)

Country Link
CN (1) CN107182218A (zh)
WO (1) WO2017113286A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108521821A (zh) * 2018-04-18 2018-09-11 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置、和电子设备
CN108647636A (zh) * 2018-05-09 2018-10-12 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置及电子设备
CN108701228A (zh) * 2018-04-18 2018-10-23 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置、和电子设备
CN114743254A (zh) * 2022-06-13 2022-07-12 泽景(西安)汽车电子有限责任公司 脸部认证方法、装置、终端设备及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446638B (zh) * 2018-03-21 2021-08-24 Oppo广东移动通信有限公司 身份验证方法、装置、存储介质及电子设备
CN108513661A (zh) * 2018-04-18 2018-09-07 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置、和电子设备
CN109932828A (zh) * 2019-02-01 2019-06-25 杭州驭光光电科技有限公司 光投射方法及光投射装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1217328A1 (en) * 2000-12-20 2002-06-26 Olympus Optical Co., Ltd. 3d image acquisition apparatus and 3d image acquisition method
US20060120576A1 (en) * 2004-11-08 2006-06-08 Biomagnetic Imaging Llc 3D Fingerprint and palm print data model and capture devices using multi structured lights and cameras
CN102622588A (zh) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 双验证人脸防伪方法及装置
CN102848786A (zh) * 2012-07-20 2013-01-02 中国科学院上海光学精密机械研究所 三维身份证及其制备方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101339607B (zh) * 2008-08-15 2012-08-01 北京中星微电子有限公司 人脸识别方法及系统、人脸识别模型训练方法及系统
CN102663361B (zh) * 2012-04-01 2014-01-01 北京工业大学 一种面向整体特征分析的人脸图像可逆几何归一化方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1217328A1 (en) * 2000-12-20 2002-06-26 Olympus Optical Co., Ltd. 3d image acquisition apparatus and 3d image acquisition method
US20060120576A1 (en) * 2004-11-08 2006-06-08 Biomagnetic Imaging Llc 3D Fingerprint and palm print data model and capture devices using multi structured lights and cameras
CN102622588A (zh) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 双验证人脸防伪方法及装置
CN102848786A (zh) * 2012-07-20 2013-01-02 中国科学院上海光学精密机械研究所 三维身份证及其制备方法

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108521821A (zh) * 2018-04-18 2018-09-11 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置、和电子设备
CN108701228A (zh) * 2018-04-18 2018-10-23 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置、和电子设备
CN108647636A (zh) * 2018-05-09 2018-10-12 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置及电子设备
CN108647636B (zh) * 2018-05-09 2024-03-05 深圳阜时科技有限公司 身份鉴权方法、身份鉴权装置及电子设备
CN114743254A (zh) * 2022-06-13 2022-07-12 泽景(西安)汽车电子有限责任公司 脸部认证方法、装置、终端设备及存储介质

Also Published As

Publication number Publication date
CN107182218A (zh) 2017-09-19

Similar Documents

Publication Publication Date Title
WO2017113286A1 (zh) 一种认证方法及装置
CN110889320B (zh) 眼周面部识别切换
US9985963B2 (en) Method and system for authenticating liveness face, and computer program product thereof
EP2842075B1 (en) Three-dimensional face recognition for mobile devices
KR102655949B1 (ko) 3d 영상 기반의 얼굴 인증 방법 및 장치
US20150186708A1 (en) Biometric identification system
KR20200032206A (ko) 얼굴인식 잠금해제 방법 및 장치, 기기, 매체
CN107277053A (zh) 身份验证方法、装置及移动终端
KR101810190B1 (ko) 얼굴 인식을 이용한 사용자 인증 방법 및 그 장치
CN107111704A (zh) 基于生物识别系统在虹膜内欺骗检测的系统和方法
CN110895689B (zh) 用于面部识别认证的混合模式照明
KR101444538B1 (ko) 3차원 얼굴 인식 시스템 및 그의 얼굴 인식 방법
WO2019216091A1 (ja) 顔認証装置、顔認証方法および顔認証システム
US20160125240A1 (en) Systems and methods for secure biometric processing
JP2022105583A (ja) 顔生体検出方法、装置、電子機器、記憶媒体及びコンピュータプログラム
US20200366670A1 (en) A system and method for authenticating a user
TWI585607B (zh) 結合臉部認證的視線軌跡認證系統、方法、電腦可讀取紀錄媒體及電腦程式產品
WO2019200572A1 (zh) 身份鉴权方法、身份鉴权装置、和电子设备
KR20130133676A (ko) 카메라를 통한 얼굴인식을 이용한 사용자 인증 방법 및 장치
EP3913575A1 (en) Authentication system, authentication device, and authentication method
CN113033243A (zh) 一种人脸识别方法、装置及设备
WO2019102686A1 (ja) 生体認証装置および生体認証システム
WO2018179723A1 (ja) 顔認証処理装置、顔認証処理方法及び顔認証処理システム
US11507646B1 (en) User authentication using video analysis
TWI729679B (zh) 認證系統、認證裝置、及認證方法

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: 15911912

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: 15911912

Country of ref document: EP

Kind code of ref document: A1