WO2016082252A1 - Airport security check method through three-dimensional face recognition based on cloud server - Google Patents

Airport security check method through three-dimensional face recognition based on cloud server Download PDF

Info

Publication number
WO2016082252A1
WO2016082252A1 PCT/CN2014/093552 CN2014093552W WO2016082252A1 WO 2016082252 A1 WO2016082252 A1 WO 2016082252A1 CN 2014093552 W CN2014093552 W CN 2014093552W WO 2016082252 A1 WO2016082252 A1 WO 2016082252A1
Authority
WO
WIPO (PCT)
Prior art keywords
cloud server
dimensional face
dimensional
face
image
Prior art date
Application number
PCT/CN2014/093552
Other languages
French (fr)
Chinese (zh)
Inventor
张会林
孙利华
Original Assignee
苏州福丰科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州福丰科技有限公司 filed Critical 苏州福丰科技有限公司
Publication of WO2016082252A1 publication Critical patent/WO2016082252A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces

Definitions

  • the invention belongs to the field of airport intelligent security inspection, and particularly relates to a three-dimensional face recognition airport security inspection method based on a cloud server.
  • the airport security check only confirms the passenger information through the ID card information, and cannot accurately determine whether the passenger and the ID card are the same person, and the security performance is low.
  • the three-dimensional face recognition is generally based on a neural network or a mathematical prior test. Probability for image extraction, computational complexity, long computing time, can not be promoted in the field of smart payment.
  • the present invention provides a three-dimensional face recognition airport security detection method based on a cloud server, which has high computational configuration efficiency and can quickly retrieve data information on a cloud server, and calculation and registration are performed on the cloud server side. , high efficiency, correspondingly fast, can promote the application.
  • the technical solution adopted by the present invention is: a cloud server-based three-dimensional face recognition airport security inspection method, comprising the following steps,
  • the cloud server establishes a face recognition standard library
  • the image capturing terminal of the airport establishes a network connection with the cloud server, and the three-dimensional face scanner acquires a three-dimensional image of the face;
  • the cloud server receives the three-dimensional face image and the identity authentication request sent by the image collection terminal.
  • Step S03 After receiving the three-dimensional face image sent by the image collection terminal, the cloud server converts the three-dimensional face image into a series of data and transmits the data to the computing unit of the cloud server, where the computing unit performs three-dimensional face image preprocessing and three-dimensional face processing. Extract and 3D face registration.
  • Step S04 three-dimensional face image preprocessing specifically includes the following steps:
  • Step S05 specifically includes the following steps:
  • Grid cropping The face-based pre-registration method converts the face to the frontal state, and then uses a rectangle to crop the face on the XOY plane.
  • Step S06 specifically includes the following steps:
  • the Shape Index is calculated by fitting the quadratic surface to the neighborhood of the point to obtain the robust feature
  • Step S07 specifically includes the following steps: the cloud server searches for the face standard sample in the face recognition standard library, and registers the flag points after the step S06 to achieve rough registration based on the marker points; when the three-dimensional face image flag region When lost, the marker point cannot be stably extracted, and the three-dimensional face registration is performed by the coarse registration method based on the spindle analysis.
  • the cloud server returns the result of the identity verification to the airport identity terminal.
  • the beneficial effects of the present invention include:
  • the invention provides a three-dimensional face recognition airport security detection method based on a cloud server, which has high computational configuration efficiency and can quickly retrieve data information on the cloud server, and the calculation and registration are performed on the cloud server end, and the efficiency is high and correspondingly fast. Can promote the application.
  • Cloud server-based 3D face recognition airport security inspection method including the following steps,
  • the cloud server establishes a face recognition standard library
  • the image capturing terminal of the airport establishes a network connection with the cloud server, and the three-dimensional face scanner acquires a three-dimensional image of the face;
  • the cloud server receives the three-dimensional face image and the identity authentication request sent by the image collection terminal.
  • Step S03 After receiving the three-dimensional face image sent by the image collection terminal, the cloud server converts the three-dimensional face image into a series of data and transmits the data to the computing unit of the cloud server, where the computing unit performs three-dimensional face image preprocessing and three-dimensional face processing. Extract and 3D face registration.
  • Step S04 three-dimensional face image preprocessing specifically includes the following steps:
  • Step S05 specifically includes the following steps:
  • Grid cropping The face-based pre-registration method converts the face to the frontal state, and then uses a rectangle to crop the face on the XOY plane.
  • Step S06 specifically includes the following steps:
  • the Shape Index is calculated by fitting the quadratic surface to the neighborhood of the point to obtain the robust feature
  • Step S07 specifically includes the following steps: the cloud server searches for the face standard sample in the face recognition standard library, and registers the flag points after the step S06 to achieve rough registration based on the marker points; when the three-dimensional face image flag region When lost, the marker point cannot be stably extracted, and the three-dimensional face registration is performed by the coarse registration method based on the spindle analysis.
  • the cloud server returns the result of the identity verification to the airport identity terminal.

Abstract

An airport security check method through three-dimensional face recognition based on a cloud server. The method comprises the following steps: S01, a cloud server creates a face recognition standard library; S02, an airport image acquisition terminal establishes a network connection with the cloud server; S03, the cloud server receives a three-dimensional face image and an identity authentication request sent by the image acquisition terminal; S04, pre-process the three-dimensional face image; S05, extract the three-dimensional face, and separate the head and the shoulders from an original three-dimensional curved surface; S06, position facial feature points; S07, register the three-dimensional face; and S08, the cloud server returns the result of identity authentication to an airport identity recognition terminal. According to this application, the computing configuration is highly efficient, data information in the cloud server can be quickly retrieved, and the computing and the registration are performed in the cloud server; therefore, the method is high in efficiency, quick in response, and capable of being popularized.

Description

基于云服务器的三维人脸识别机场安检方法3D face recognition airport security inspection method based on cloud server 技术领域Technical field
本发明属机场智能安检领域，尤其涉及一种基于云服务器的三维人脸识别机场安检方法。The invention belongs to the field of airport intelligent security inspection, and particularly relates to a three-dimensional face recognition airport security inspection method based on a cloud server.
背景技术Background technique
目前，机场安检仅通过身份证信息核实乘机人员信息，不能够准确的确定是否乘机人与身份证上是同一人，安全性能低，现有技术，三维人脸识别一般基于神经网络或者数学先验概率进行图像提取，计算复杂，运算时间长，在智能支付领域不能够推广应用。At present, the airport security check only confirms the passenger information through the ID card information, and cannot accurately determine whether the passenger and the ID card are the same person, and the security performance is low. In the prior art, the three-dimensional face recognition is generally based on a neural network or a mathematical prior test. Probability for image extraction, computational complexity, long computing time, can not be promoted in the field of smart payment.
发明内容Summary of the invention
为了解决现有技术问题，本发明提供了一种基于云服务器的三维人脸识别机场安检方法，计算配置效率高，能够快速的检索云服务器上的数据信息，计算和配准在云服务器端进行，效率高，相应快，能够推广应用。In order to solve the prior art problem, the present invention provides a three-dimensional face recognition airport security detection method based on a cloud server, which has high computational configuration efficiency and can quickly retrieve data information on a cloud server, and calculation and registration are performed on the cloud server side. , high efficiency, correspondingly fast, can promote the application.
本发明采用的技术方案为：基于云服务器的三维人脸识别机场安检方法，包括以下步骤，The technical solution adopted by the present invention is: a cloud server-based three-dimensional face recognition airport security inspection method, comprising the following steps,
S01，云服务器建立人脸识别标准库；S01, the cloud server establishes a face recognition standard library;
S02，机场图像采集终端与云服务器建立网络连接，三维人脸扫描仪获取人脸三维图像；S02, the image capturing terminal of the airport establishes a network connection with the cloud server, and the three-dimensional face scanner acquires a three-dimensional image of the face;
S03，云服务器接收图像采集终端发送的三维人脸图像及身份认证请求；S03. The cloud server receives the three-dimensional face image and the identity authentication request sent by the image collection terminal.
步骤S03，云服务器接收图像采集终端发送的三维人脸图像后，将三维人脸图像转换成一系列数据传递至云服务器的计算单元，所述计算单元进行三维人脸图像预处理、三维人脸的提取和三维人脸配准。Step S03: After receiving the three-dimensional face image sent by the image collection terminal, the cloud server converts the three-dimensional face image into a series of data and transmits the data to the computing unit of the cloud server, where the computing unit performs three-dimensional face image preprocessing and three-dimensional face processing. Extract and 3D face registration.
S04，三维人脸图像预处理：对三维人脸图像进行噪声预处理方法； S04, 3D face image preprocessing: a noise preprocessing method for 3D face images;
步骤S04三维人脸图像预处理具体包括以下步骤：Step S04 three-dimensional face image preprocessing specifically includes the following steps:
(401)对三维人脸图像进行去噪处理，采用基于点云数据的三角曲面插值方法，对三维人脸图像点云数据进行曲面拟合和优化重构；(401) Denoising the 3D face image, using the triangular surface interpolation method based on point cloud data to perform surface fitting and optimization reconstruction on the 3D face image point cloud data;
(402)使用拉普拉斯平滑和Taubin方法对模型进行平滑处理；(402) smoothing the model using Laplacian smoothing and Taubin methods;
(403)对人脸图像进行网格切割并姿态归一化处理，获取三维人脸模型。(403) Perform mesh cutting on the face image and normalize the posture to obtain a three-dimensional face model.
S05，三维人脸的提取,从原始三维曲面中分离出头部和肩部；S05, the extraction of the three-dimensional face, separating the head and the shoulder from the original three-dimensional surface;
步骤S05具体包括以下步骤：Step S05 specifically includes the following steps:
(501)从原始三维曲面中分离出头部和肩部，使用PCA方法获取姿态的估计，去掉肩部区域；(501) Separating the head and shoulder from the original three-dimensional surface, using the PCA method to obtain an estimate of the posture, and removing the shoulder region;
(502)网格裁剪：基于标志点的预配准方法将人脸转换到正面状态，然后在XOY平面上使用一个矩形裁剪人脸。(502) Grid cropping: The face-based pre-registration method converts the face to the frontal state, and then uses a rectangle to crop the face on the XOY plane.
S06，脸部标志点定位；S06, facial landmark positioning;
步骤S06具体包括以下步骤：Step S06 specifically includes the following steps:
(601)定位两个内眼角、两个外眼角和鼻尖点；(601) locating two inner corners of the eye, two outer corners of the eye, and a tip of the nose;
(602)进行坐标映射，获取五个标志点(两个内眼角、两个外眼角和鼻尖点)的坐标位置；(602) performing coordinate mapping to obtain coordinate positions of five marker points (two inner corners, two outer corners, and nose tips);
(603)基于连续Shape Index和几何约束的标志点定位方法，基于三角网格格式的三维数据，通过对点的邻域拟合二次曲面，计算Shape Index，获取鲁棒特征；(603) Based on the continuous Shape Index and geometric constraint marker point localization method, based on the three-dimensional data of the triangular mesh format, the Shape Index is calculated by fitting the quadratic surface to the neighborhood of the point to obtain the robust feature;
(604)通过几何约束，实现姿态无关的标志点定位。(604) Gesture-independent landmark positioning is achieved by geometric constraints.
S07，三维人脸配准；S07, three-dimensional face registration;
步骤S07具体包括以下步骤：云服务器检索所述人脸识别标准库中的人脸标准样本，配准步骤S06定位后的标志点，实现基于标志点的粗配准；当三维人脸图像标志区域丢失时，标志点无法稳定提取时，通过基于主轴分析的粗配准方法进行三维人脸配准。 Step S07 specifically includes the following steps: the cloud server searches for the face standard sample in the face recognition standard library, and registers the flag points after the step S06 to achieve rough registration based on the marker points; when the three-dimensional face image flag region When lost, the marker point cannot be stably extracted, and the three-dimensional face registration is performed by the coarse registration method based on the spindle analysis.
S08，云服务器将身份认证的结果返回机场身份识别终端。S08, the cloud server returns the result of the identity verification to the airport identity terminal.
与现有技术相比，本发明有益效果包括：Compared with the prior art, the beneficial effects of the present invention include:
本发明提供了一种基于云服务器的三维人脸识别机场安检方法，计算配置效率高，能够快速的检索云服务器上的数据信息，计算和配准在云服务器端进行，效率高，相应快，能够推广应用。The invention provides a three-dimensional face recognition airport security detection method based on a cloud server, which has high computational configuration efficiency and can quickly retrieve data information on the cloud server, and the calculation and registration are performed on the cloud server end, and the efficiency is high and correspondingly fast. Can promote the application.
具体实施方式detailed description
下面结合具体实施例对本发明作更进一步的说明。The present invention will be further described below in conjunction with specific embodiments.
基于云服务器的三维人脸识别机场安检方法，包括以下步骤，Cloud server-based 3D face recognition airport security inspection method, including the following steps,
S01，云服务器建立人脸识别标准库；S01, the cloud server establishes a face recognition standard library;
S02，机场图像采集终端与云服务器建立网络连接，三维人脸扫描仪获取人脸三维图像；S02, the image capturing terminal of the airport establishes a network connection with the cloud server, and the three-dimensional face scanner acquires a three-dimensional image of the face;
S03，云服务器接收图像采集终端发送的三维人脸图像及身份认证请求；S03. The cloud server receives the three-dimensional face image and the identity authentication request sent by the image collection terminal.
步骤S03，云服务器接收图像采集终端发送的三维人脸图像后，将三维人脸图像转换成一系列数据传递至云服务器的计算单元，所述计算单元进行三维人脸图像预处理、三维人脸的提取和三维人脸配准。Step S03: After receiving the three-dimensional face image sent by the image collection terminal, the cloud server converts the three-dimensional face image into a series of data and transmits the data to the computing unit of the cloud server, where the computing unit performs three-dimensional face image preprocessing and three-dimensional face processing. Extract and 3D face registration.
S04，三维人脸图像预处理：对三维人脸图像进行噪声预处理方法；S04, 3D face image preprocessing: a noise preprocessing method for 3D face images;
步骤S04三维人脸图像预处理具体包括以下步骤：Step S04 three-dimensional face image preprocessing specifically includes the following steps:
(401)对三维人脸图像进行去噪处理，采用基于点云数据的三角曲面插值方法，对三维人脸图像点云数据进行曲面拟合和优化重构；(401) Denoising the 3D face image, using the triangular surface interpolation method based on point cloud data to perform surface fitting and optimization reconstruction on the 3D face image point cloud data;
(402)使用拉普拉斯平滑和Taubin方法对模型进行平滑处理；(402) smoothing the model using Laplacian smoothing and Taubin methods;
(403)对人脸图像进行网格切割并姿态归一化处理，获取三维人脸模型。(403) Perform mesh cutting on the face image and normalize the posture to obtain a three-dimensional face model.
S05，三维人脸的提取,从原始三维曲面中分离出头部和肩部；S05, the extraction of the three-dimensional face, separating the head and the shoulder from the original three-dimensional surface;
步骤S05具体包括以下步骤：Step S05 specifically includes the following steps:
(501)从原始三维曲面中分离出头部和肩部，使用PCA方法获取姿态的估计，去掉肩部区域； (501) Separating the head and shoulder from the original three-dimensional surface, using the PCA method to obtain an estimate of the posture, and removing the shoulder region;
(502)网格裁剪：基于标志点的预配准方法将人脸转换到正面状态，然后在XOY平面上使用一个矩形裁剪人脸。(502) Grid cropping: The face-based pre-registration method converts the face to the frontal state, and then uses a rectangle to crop the face on the XOY plane.
S06，脸部标志点定位；S06, facial landmark positioning;
步骤S06具体包括以下步骤：Step S06 specifically includes the following steps:
(601)定位两个内眼角、两个外眼角和鼻尖点；(601) locating two inner corners of the eye, two outer corners of the eye, and a tip of the nose;
(602)进行坐标映射，获取五个标志点(两个内眼角、两个外眼角和鼻尖点)的坐标位置；(602) performing coordinate mapping to obtain coordinate positions of five marker points (two inner corners, two outer corners, and nose tips);
(603)基于连续Shape Index和几何约束的标志点定位方法，基于三角网格格式的三维数据，通过对点的邻域拟合二次曲面，计算Shape Index，获取鲁棒特征；(603) Based on the continuous Shape Index and geometric constraint marker point localization method, based on the three-dimensional data of the triangular mesh format, the Shape Index is calculated by fitting the quadratic surface to the neighborhood of the point to obtain the robust feature;
(604)通过几何约束，实现姿态无关的标志点定位。(604) Gesture-independent landmark positioning is achieved by geometric constraints.
S07，三维人脸配准；S07, three-dimensional face registration;
步骤S07具体包括以下步骤：云服务器检索所述人脸识别标准库中的人脸标准样本，配准步骤S06定位后的标志点，实现基于标志点的粗配准；当三维人脸图像标志区域丢失时，标志点无法稳定提取时，通过基于主轴分析的粗配准方法进行三维人脸配准。Step S07 specifically includes the following steps: the cloud server searches for the face standard sample in the face recognition standard library, and registers the flag points after the step S06 to achieve rough registration based on the marker points; when the three-dimensional face image flag region When lost, the marker point cannot be stably extracted, and the three-dimensional face registration is performed by the coarse registration method based on the spindle analysis.
S08，云服务器将身份认证的结果返回机场身份识别终端。S08, the cloud server returns the result of the identity verification to the airport identity terminal.
以上仅是本发明的优选实施方式，应当指出：对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。 The above is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can also make several improvements and retouchings without departing from the principles of the present invention. These improvements and retouchings should also be considered. It is the scope of protection of the present invention.

Claims (7)

  1. 基于云服务器的三维人脸识别机场安检方法，其特征在于，包括以下步骤，A three-dimensional face recognition airport security detection method based on a cloud server, characterized in that it comprises the following steps,
    S01，云服务器建立人脸识别标准库；S01, the cloud server establishes a face recognition standard library;
    S02，机场图像采集终端与云服务器建立网络连接，三维人脸扫描仪获取人脸三维图像；S02, the image capturing terminal of the airport establishes a network connection with the cloud server, and the three-dimensional face scanner acquires a three-dimensional image of the face;
    S03，云服务器接收图像采集终端发送的三维人脸图像及身份认证请求；S03. The cloud server receives the three-dimensional face image and the identity authentication request sent by the image collection terminal.
    S04，三维人脸图像预处理：对三维人脸图像进行噪声预处理方法；S04, 3D face image preprocessing: a noise preprocessing method for 3D face images;
    S05，三维人脸的提取,从原始三维曲面中分离出头部和肩部；S05, the extraction of the three-dimensional face, separating the head and the shoulder from the original three-dimensional surface;
    S06，脸部标志点定位；S06, facial landmark positioning;
    S07，三维人脸配准；S07, three-dimensional face registration;
    S08，云服务器将身份认证的结果返回机场身份识别终端。S08, the cloud server returns the result of the identity verification to the airport identity terminal.
  2. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法，其特征在于，The cloud server-based three-dimensional face recognition airport security method according to claim 1, wherein
    步骤S03，云服务器接收图像采集终端发送的三维人脸图像后，将三维人脸图像转换成一系列数据传递至云服务器的计算单元，所述计算单元进行三维人脸图像预处理、三维人脸的提取和三维人脸配准。Step S03: After receiving the three-dimensional face image sent by the image collection terminal, the cloud server converts the three-dimensional face image into a series of data and transmits the data to the computing unit of the cloud server, where the computing unit performs three-dimensional face image preprocessing and three-dimensional face processing. Extract and 3D face registration.
  3. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法，其特征在于，The cloud server-based three-dimensional face recognition airport security method according to claim 1, wherein
    步骤S04三维人脸图像预处理具体包括以下步骤：Step S04 three-dimensional face image preprocessing specifically includes the following steps:
    (401)对三维人脸图像进行去噪处理，采用基于点云数据的三角曲面插值方法，对三维人脸图像点云数据进行曲面拟合和优化重构；(401) Denoising the 3D face image, using the triangular surface interpolation method based on point cloud data to perform surface fitting and optimization reconstruction on the 3D face image point cloud data;
    (402)使用拉普拉斯平滑和Taubin方法对模型进行平滑处理；(402) smoothing the model using Laplacian smoothing and Taubin methods;
    (403)对人脸图像进行网格切割并姿态归一化处理，获取三维人脸模型。(403) Perform mesh cutting on the face image and normalize the posture to obtain a three-dimensional face model.
  4. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法， 其特征在于，The cloud server-based three-dimensional face recognition airport security detection method according to claim 1, It is characterized in that
    步骤S05具体包括以下步骤：Step S05 specifically includes the following steps:
    (501)从原始三维曲面中分离出头部和肩部，使用PCA方法获取姿态的估计，去掉肩部区域；(501) Separating the head and shoulder from the original three-dimensional surface, using the PCA method to obtain an estimate of the posture, and removing the shoulder region;
    (502)网格裁剪：基于标志点的预配准方法将人脸转换到正面状态，然后在XOY平面上使用一个矩形裁剪人脸。(502) Grid cropping: The face-based pre-registration method converts the face to the frontal state, and then uses a rectangle to crop the face on the XOY plane.
  5. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法，其特征在于，The cloud server-based three-dimensional face recognition airport security method according to claim 1, wherein
    步骤S06具体包括以下步骤：Step S06 specifically includes the following steps:
    (601)定位两个内眼角、两个外眼角和鼻尖点；(601) locating two inner corners of the eye, two outer corners of the eye, and a tip of the nose;
    (602)进行坐标映射，获取五个标志点的坐标位置；(602) performing coordinate mapping to obtain coordinate positions of five marker points;
    (603)基于连续Shape Index和几何约束的标志点定位方法，基于三角网格格式的三维数据，通过对点的邻域拟合二次曲面，计算Shape Index，获取鲁棒特征；(603) Based on the continuous Shape Index and geometric constraint marker point localization method, based on the three-dimensional data of the triangular mesh format, the Shape Index is calculated by fitting the quadratic surface to the neighborhood of the point to obtain the robust feature;
    (604)通过几何约束，实现姿态无关的标志点定位。(604) Gesture-independent landmark positioning is achieved by geometric constraints.
  6. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法，其特征在于，The cloud server-based three-dimensional face recognition airport security method according to claim 1, wherein
    步骤S07具体包括以下步骤：云服务器检索所述人脸识别标准库中的人脸标准样本，配准步骤S06定位后的标志点，实现基于标志点的粗配准。Step S07 specifically includes the following steps: the cloud server searches for the face standard sample in the face recognition standard library, and registers the flag points after the step S06 to achieve coarse registration based on the marker points.
  7. 根据权利要求1所述的基于云服务器的三维人脸识别机场安检方法，其特征在于，步骤S07还包括：当三维人脸图像标志区域丢失时，标志点无法稳定提取通过基于主轴分析的粗配准方法进行三维人脸配准。 The cloud server-based three-dimensional face recognition airport security detection method according to claim 1, wherein the step S07 further comprises: when the three-dimensional face image flag area is lost, the marker point cannot be stably extracted through the coarse matching based on the spindle analysis. The quasi-method performs three-dimensional face registration.
PCT/CN2014/093552 2014-11-27 2014-12-11 Airport security check method through three-dimensional face recognition based on cloud server WO2016082252A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410694811.6A CN104392220A (en) 2014-11-27 2014-11-27 Three-dimensional face recognition airport security inspection method based on cloud server
CN201410694811.6 2014-11-27

Publications (1)

Publication Number Publication Date
WO2016082252A1 true WO2016082252A1 (en) 2016-06-02

Family

ID=52610121

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/093552 WO2016082252A1 (en) 2014-11-27 2014-12-11 Airport security check method through three-dimensional face recognition based on cloud server

Country Status (2)

Country Link
CN (1) CN104392220A (en)
WO (1) WO2016082252A1 (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106056104A (en) * 2016-07-07 2016-10-26 王飞 Security check door for human body three-dimensional data acquisition and identity identification, and method
WO2018037098A1 (en) 2016-08-24 2018-03-01 Danmarks Tekniske Universitet Method of improving methyltransferase activity
CN110163027A (en) * 2018-01-15 2019-08-23 郑州大学西亚斯国际学院 A kind of thermal imaging data analysis face identification system of electronic eyes
CN111046837A (en) * 2019-12-24 2020-04-21 深圳市奥富科数码科技有限公司 Face recognition equipment based on 5G framework
CN111079684A (en) * 2019-12-24 2020-04-28 河南中原大数据研究院有限公司 Three-dimensional face detection method based on rough-fine fitting
CN111145166A (en) * 2019-12-31 2020-05-12 北京深测科技有限公司 Safety monitoring method and system
CN111245812A (en) * 2020-01-07 2020-06-05 南京航空航天大学 Integrated airport security check verification system and data verification encryption transmission method thereof
CN111553970A (en) * 2020-05-19 2020-08-18 北京数字绿土科技有限公司 Point cloud real-time measurement method based on server
WO2020164284A1 (en) * 2019-02-12 2020-08-20 平安科技（深圳）有限公司 Method and apparatus for recognising living body based on planar detection, terminal, and storage medium
CN111788602A (en) * 2017-12-29 2020-10-16 菲力尔系统公司 Point cloud denoising system and method

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732216A (en) * 2015-03-26 2015-06-24 江苏物联网研究发展中心 Expression recognition method based on key points and local characteristics
CN106054278B (en) * 2016-07-07 2018-06-12 王飞 A kind of head three dimensional data collection and the detector gate and method of identification
CN106845368A (en) * 2016-12-30 2017-06-13 中国民航信息网络股份有限公司 Airport boarding safety check based on recognition of face confirms system and method again
CN108960102A (en) * 2018-06-22 2018-12-07 天和防务技术（北京）有限公司 The automatic detection cabin of Terahertz dangerous material and detection method
CN109655928A (en) * 2019-01-30 2019-04-19 成都智元汇信息技术股份有限公司 A kind of detector gate metal analysis system and method based on cloud processing
CN111985278A (en) * 2019-05-24 2020-11-24 中建材信息技术股份有限公司 Face recognition method based on deep learning in cloud computing scene
CN112016466A (en) * 2020-08-28 2020-12-01 中移（杭州）信息技术有限公司 Face recognition method, face recognition system, electronic device and computer storage medium
CN113160575A (en) * 2021-03-15 2021-07-23 超级视线科技有限公司 Traffic violation detection method and system for non-motor vehicles and drivers
CN115563396B (en) * 2022-12-06 2023-04-28 成都智元汇信息技术股份有限公司 Degradable centralized intelligent pushing method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040240711A1 (en) * 2003-05-27 2004-12-02 Honeywell International Inc. Face identification verification using 3 dimensional modeling
CN201904809U (en) * 2010-12-20 2011-07-20 惠州紫旭科技有限公司 Data service system based on cloud computing
CN102779269A (en) * 2012-06-13 2012-11-14 合肥工业大学 Human face identification algorithm based on image sensor imaging system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398886B (en) * 2008-03-17 2010-11-10 杭州大清智能技术开发有限公司 Rapid three-dimensional face identification method based on bi-eye passiveness stereo vision
CN103107886A (en) * 2013-01-17 2013-05-15 深圳市元征科技股份有限公司 Identification recognition system and method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040240711A1 (en) * 2003-05-27 2004-12-02 Honeywell International Inc. Face identification verification using 3 dimensional modeling
CN201904809U (en) * 2010-12-20 2011-07-20 惠州紫旭科技有限公司 Data service system based on cloud computing
CN102779269A (en) * 2012-06-13 2012-11-14 合肥工业大学 Human face identification algorithm based on image sensor imaging system

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106056104A (en) * 2016-07-07 2016-10-26 王飞 Security check door for human body three-dimensional data acquisition and identity identification, and method
WO2018037098A1 (en) 2016-08-24 2018-03-01 Danmarks Tekniske Universitet Method of improving methyltransferase activity
CN111788602A (en) * 2017-12-29 2020-10-16 菲力尔系统公司 Point cloud denoising system and method
CN110163027A (en) * 2018-01-15 2019-08-23 郑州大学西亚斯国际学院 A kind of thermal imaging data analysis face identification system of electronic eyes
WO2020164284A1 (en) * 2019-02-12 2020-08-20 平安科技（深圳）有限公司 Method and apparatus for recognising living body based on planar detection, terminal, and storage medium
CN111046837A (en) * 2019-12-24 2020-04-21 深圳市奥富科数码科技有限公司 Face recognition equipment based on 5G framework
CN111079684A (en) * 2019-12-24 2020-04-28 河南中原大数据研究院有限公司 Three-dimensional face detection method based on rough-fine fitting
CN111079684B (en) * 2019-12-24 2023-04-07 陕西西图数联科技有限公司 Three-dimensional face detection method based on rough-fine fitting
CN111145166A (en) * 2019-12-31 2020-05-12 北京深测科技有限公司 Safety monitoring method and system
CN111145166B (en) * 2019-12-31 2023-09-01 北京深测科技有限公司 Security monitoring method and system
CN111245812A (en) * 2020-01-07 2020-06-05 南京航空航天大学 Integrated airport security check verification system and data verification encryption transmission method thereof
CN111553970A (en) * 2020-05-19 2020-08-18 北京数字绿土科技有限公司 Point cloud real-time measurement method based on server
CN111553970B (en) * 2020-05-19 2024-02-20 北京数字绿土科技股份有限公司 Point cloud real-time measurement method based on server

Also Published As

Publication number Publication date
CN104392220A (en) 2015-03-04

Similar Documents

Publication Publication Date Title
WO2016082252A1 (en) Airport security check method through three-dimensional face recognition based on cloud server
Munaro et al. One-shot person re-identification with a consumer depth camera
Colombo et al. Three-dimensional occlusion detection and restoration of partially occluded faces
Berretti et al. Matching 3D face scans using interest points and local histogram descriptors
WO2015165365A1 (en) Facial recognition method and system
Liang et al. Improved detection of landmarks on 3D human face data
KR101732898B1 (en) Image processing apparatus and method thereof
CN108009472B (en) Finger back joint print recognition method based on convolutional neural network and Bayes classifier
CN105184235B (en) A kind of China second-generation identity card recognition methods based on Fusion Features
WO2014107945A1 (en) Character recognition method
CN105138995B (en) The when constant and constant Human bodys' response method of view based on framework information
Thalji et al. Iris Recognition using robust algorithm for eyelid, eyelash and shadow avoiding
US8938132B2 (en) Image collation system, image collation method and computer program
Prakash et al. An efficient technique for ear detection in 3D: Invariant to rotation and scale
JP2013186546A (en) Person retrieval system
Kumar et al. Automatic ear detection for online biometric applications
Tharewal et al. Score-level fusion of 3D face and 3D ear for multimodal biometric human recognition
WO2016011640A1 (en) Identification method based on handprint imaging
Bagchi et al. A novel approach to nose-tip and eye corners detection using HK curvature analysis in case of 3D images
Prakash et al. A rotation and scale invariant technique for ear detection in 3D
CN104599265A (en) Three-dimensional face detection and posture correction method in face recognition
Alyuz et al. Adaptive registration for occlusion robust 3D face recognition
Sanchez-Gonzalez et al. A comparison of fused segmentation algorithms for iris verification
WO2016082253A1 (en) Three-dimensional face recognition method for entry and exit administration
Wlodarczyk et al. Evaluation of head pose estimation methods for a non-cooperative biometric system

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: 14906657

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 1205 DATED 10/10/2017)

122 Ep: pct application non-entry in european phase

Ref document number: 14906657

Country of ref document: EP

Kind code of ref document: A1