WO2016082253A1 - 用于出入境管理的三维人脸识别方法 - Google Patents

用于出入境管理的三维人脸识别方法 Download PDF

Info

Publication number
WO2016082253A1
WO2016082253A1 PCT/CN2014/093554 CN2014093554W WO2016082253A1 WO 2016082253 A1 WO2016082253 A1 WO 2016082253A1 CN 2014093554 W CN2014093554 W CN 2014093554W WO 2016082253 A1 WO2016082253 A1 WO 2016082253A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
face recognition
face
entry
recognition method
Prior art date
Application number
PCT/CN2014/093554
Other languages
English (en)
French (fr)
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 WO2016082253A1 publication Critical patent/WO2016082253A1/zh

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
    • G06V40/168—Feature extraction; Face representation
    • 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
    • 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 present invention relates to the field of face recognition technology, and in particular to a three-dimensional face recognition method for entry and exit management.
  • the three-dimensional face recognition technology is mainly used in the field of attendance and admission.
  • the original ID card and its copy are generally required, which is quite troublesome.
  • a three-dimensional face recognition method for entry and exit management is proposed.
  • the object of the present invention is to overcome the above problems, and to provide a three-dimensional face recognition method which is more accurate in recognition, helps to quickly locate a criminal suspect, and is in a standby state when the three-dimensional face recognition instrument is not in use.
  • the technical solution adopted by the present invention is: a three-dimensional face recognition method for entry and exit management, which comprises the following steps:
  • Image acquisition collecting the dynamic contour of the face image and the images of the eyes, nose, mouth, eyebrows, forehead and sending to the image preprocessing chip and the memory chip;
  • Image preprocessing filtering and sharpening the face image
  • Image feature extraction image information is extracted into block features and a histogram is constructed
  • the decision tree classifier is used to compare the extracted block features with the face feature database.
  • the above-described three-dimensional face recognition method for entry and exit management is characterized in that, in step 1), the infrared receiver is disposed at a side of the face recognition device.
  • the foregoing three-dimensional face recognition method for entry and exit management is characterized in that, in step 2), the memory chip inputs and stores face image information.
  • the foregoing three-dimensional face recognition method for entry and exit management is characterized in that, in step 3), the filtering process adopts a high-pass filtering algorithm.
  • the foregoing three-dimensional face recognition method for entry and exit management is characterized in that, in step 4), the segment feature extraction is divided into an eye, a nose, a mouth, and an eyebrow portion.
  • the foregoing three-dimensional face recognition method for entry and exit management is characterized in that the face feature library is located in a memory chip.
  • the invention has the beneficial effects that the three-dimensional face recognition method is convenient for entry and exit management, which helps to quickly locate criminal suspects, does not need to carry identity documents, and is convenient and increases reliability, and intelligent identification is also more accurate; infrared receiving is adopted.
  • the device intelligently activates the 3D face recognition machine, and the system automatically stays in standby when not in use, saving energy.
  • a three-dimensional face recognition method for entry and exit management comprising the following steps:
  • Image acquisition collecting the dynamic contour of the face image and the images of the eyes, nose, mouth, eyebrows, forehead and sending to the image preprocessing chip and the memory chip;
  • Image preprocessing filtering and sharpening the face image
  • Image feature extraction image information is extracted into block features and a histogram is constructed
  • the decision tree classifier is used to compare the extracted block features with the face feature database.
  • step 1) the infrared receiver is disposed at a side of the face recognition device.
  • step 2) the memory chip inputs and stores face image information.
  • step 3 the filtering process employs a high pass filtering algorithm.
  • step 4 the segment feature extraction is divided into an eye, a nose, a mouth, and an eyebrow portion.
  • the face feature library is located in the memory chip.
  • the 3D face recognition method is convenient for entry and exit management, which helps to quickly locate suspects without carrying identity documents, and is more convenient and more reliable, and intelligent identification is more accurate; using infrared receiver to intelligently launch 3D face recognition The machine automatically stays in standby when not in use, saving energy.

Landscapes

  • Engineering & Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及人脸识别技术领域，具体涉及一种用于出入境管理的三维人脸识别方法,包括如下步骤：由红外接收器接收人脸发出的红外射线，接收到人脸红外射线时启动图像采集；图像采集：采集人脸图像的动态轮廓以及眼睛、鼻子、嘴巴、眉毛、额头的图像并发送至图像预处理芯片和记忆芯片；图像预处理：对人脸图像进行过滤及锐化处理；图像特征提取：将图像信息进行分块特征提取并构建直方图；采用决策树分类器将提取的分块特征与人脸特征库对比。本发明的有益效果是：采用三维人脸识别法方便出入境管理，有助于快速定位犯罪嫌疑人，增加了可靠性，智能识别也较为精准；采用红外接收器启动三维人脸识别机器，不用时系统自动处于待机状态，节约能源。

Description

用于出入境管理的三维人脸识别方法 技术领域
本发明涉及人脸识别技术领域，具体涉及一种用于出入境管理的三维人脸识别方法。
背景技术
目前三维人脸识别技术主要用于考勤、准入领域，而在公积金开户时，一般需要身份证原件及其复印件，比较麻烦，现提出一种用于出入境管理的三维人脸识别方法。
发明内容
本发明的目的在于克服上述问题，提供一种识别较为精准、有助于快速定位犯罪嫌疑人、不用时三维人脸识别仪器处于待机状态的三维人脸识别方法。
为了实现上述目的，本发明所采用的技术方案为：用于出入境管理的三维人脸识别方法，其特征在于，包括如下步骤：
1)由红外接收器接收人脸发出的红外射线，接收到人脸红外射线时启动图像采集；
2)图像采集：采集人脸图像的动态轮廓以及眼睛、鼻子、嘴巴、眉毛、额头的图像并发送至图像预处理芯片和记忆芯片；
3)图像预处理：对人脸图像进行过滤及锐化处理；
4)图像特征提取：将图像信息进行分块特征提取并构建直方图；
5)采用决策树分类器将提取的分块特征与人脸特征库对比。
前述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤1)中，所述的红外接收器设置于人脸识别装置的侧部。
前述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤2)中，所述的记忆芯片录入和储存人脸图像信息。
前述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤3)中，所述的过滤处理采用高通滤波算法。
前述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤4)中，分块特征提取分为眼睛、鼻子、嘴、眉毛部分。
前述的用于出入境管理的三维人脸识别方法，其特征在于，所述的人脸特征库位于记忆芯片内。
本发明的有益效果是：采用三维人脸识别方法方便出入境管理，有助于快速定位犯罪嫌疑人，无需携带身份证件，且比较方便还增加了可靠性，智能识别也较为精准；采用红外接收器智能启动三维人脸识别机器，不用时系统自动处于待机状态，节约能源。
具体实施方式
下面结合具体实施例对本发明作进一步说明。
用于出入境管理的三维人脸识别方法，其特征在于，包括如下步骤：
1)由红外接收器接收人脸发出的红外射线，接收到人脸红外射线时启动图像采集；
2)图像采集：采集人脸图像的动态轮廓以及眼睛、鼻子、嘴巴、眉毛、额头的图像并发送至图像预处理芯片和记忆芯片；
3)图像预处理：对人脸图像进行过滤及锐化处理；
4)图像特征提取：将图像信息进行分块特征提取并构建直方图；
5)采用决策树分类器将提取的分块特征与人脸特征库对比。
在步骤1)中，所述的红外接收器设置于人脸识别装置的侧部。在步骤2)中，所述的记忆芯片录入和储存人脸图像信息。在步骤3)中，所述的过滤处理采用高通滤波算法。在步骤4)中，分块特征提取分为眼睛、鼻子、嘴、眉毛部分。所述的人脸特征库位于记忆芯片内。
采用三维人脸识别方法方便出入境管理，有助于快速定位犯罪嫌疑人，无需携带身份证件，且比较方便还增加了可靠性，智能识别也较为精准；采用红外接收器智能启动三维人脸识别机器，不用时系统自动处于待机状态，节约能源。
上述实施例不以任何形式限制本发明，凡采用等同替换或等效变换的方式所获得的技术方案，均落在本发明的保护范围。

Claims (6)

  1. 用于出入境管理的三维人脸识别方法，其特征在于，包括如下步骤：
    1)由红外接收器接收人脸发出的红外射线，接收到人脸红外射线时启动图像采集；
    2)图像采集：采集人脸图像的动态轮廓以及眼睛、鼻子、嘴巴、眉毛、额头的图像并发送至图像预处理芯片和记忆芯片；
    3)图像预处理：对人脸图像进行过滤及锐化处理；
    4)图像特征提取：将图像信息进行分块特征提取并构建直方图；
    5)采用决策树分类器将提取的分块特征与人脸特征库对比。
  2. 根据权利要求1所述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤1)中，所述的红外接收器设置于人脸识别装置的侧部。
  3. 根据权利要求1所述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤2)中，所述的记忆芯片录入和储存人脸图像信息。
  4. 根据权利要求1所述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤3)中，所述的过滤处理采用高通滤波算法。
  5. 根据权利要求2所述的用于出入境管理的三维人脸识别方法，其特征在于，在步骤4)中，分块特征提取分为眼睛、鼻子、嘴、眉毛部分。
  6. 根据权利要求2所述的用于出入境管理的三维人脸识别方法，其特征在于，所述的人脸特征库位于记忆芯片内。
PCT/CN2014/093554 2014-11-26 2014-12-11 用于出入境管理的三维人脸识别方法 WO2016082253A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410688733.9A CN104408420A (zh) 2014-11-26 2014-11-26 用于出入境管理的三维人脸识别方法
CN201410688733.9 2014-11-26

Publications (1)

Publication Number Publication Date
WO2016082253A1 true WO2016082253A1 (zh) 2016-06-02

Family

ID=52646051

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/093554 WO2016082253A1 (zh) 2014-11-26 2014-12-11 用于出入境管理的三维人脸识别方法

Country Status (2)

Country Link
CN (1) CN104408420A (zh)
WO (1) WO2016082253A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109697417A (zh) * 2018-12-14 2019-04-30 江阴弘远新能源科技有限公司 一种用于变桨系统柜的生产管理系统
US10475309B1 (en) 2018-06-11 2019-11-12 Sray-Tech Image Co., Ltd. Operation method of smart warning device for security
CN111325078A (zh) * 2018-12-17 2020-06-23 航天信息股份有限公司 一种人脸识别方法、装置及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156887A (zh) * 2011-03-28 2011-08-17 湖南创合制造有限公司 一种基于局部特征学习的人脸识别方法
CN102956050A (zh) * 2011-08-24 2013-03-06 苏州飞锐智能科技有限公司 智能门禁控制系统
CN103020599A (zh) * 2012-12-12 2013-04-03 山东神思电子技术股份有限公司 基于人脸的身份认证方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101320484B (zh) * 2008-07-17 2012-01-04 清华大学 一种人脸虚图像生成的方法及一种三维人脸识别方法
CN101639891B (zh) * 2008-07-28 2012-05-02 汉王科技股份有限公司 一种双摄像头人脸识别装置和方法
CN102955933A (zh) * 2011-08-24 2013-03-06 苏州飞锐智能科技有限公司 基于人脸识别的家居门禁控制方法
CN103902960A (zh) * 2012-12-28 2014-07-02 北京计算机技术及应用研究所 一种实时人脸识别系统及其方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156887A (zh) * 2011-03-28 2011-08-17 湖南创合制造有限公司 一种基于局部特征学习的人脸识别方法
CN102956050A (zh) * 2011-08-24 2013-03-06 苏州飞锐智能科技有限公司 智能门禁控制系统
CN103020599A (zh) * 2012-12-12 2013-04-03 山东神思电子技术股份有限公司 基于人脸的身份认证方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10475309B1 (en) 2018-06-11 2019-11-12 Sray-Tech Image Co., Ltd. Operation method of smart warning device for security
TWI680439B (zh) * 2018-06-11 2019-12-21 視銳光科技股份有限公司 智慧安全警示系統的運作方法
CN109697417A (zh) * 2018-12-14 2019-04-30 江阴弘远新能源科技有限公司 一种用于变桨系统柜的生产管理系统
CN111325078A (zh) * 2018-12-17 2020-06-23 航天信息股份有限公司 一种人脸识别方法、装置及存储介质

Also Published As

Publication number Publication date
CN104408420A (zh) 2015-03-11

Similar Documents

Publication Publication Date Title
WO2018001092A1 (zh) 一种人脸识别方法及装置
CN103914686B (zh) 一种基于证件照与采集照的人脸比对认证方法及系统
CN100481112C (zh) 一种人脸识别系统与识别方法
WO2019090769A1 (zh) 一种人脸脸型识别方法、装置和智能终端
CN105930709A (zh) 人脸识别技术应用于人证一致性检验的方法及装置
US9990538B2 (en) Face recognition apparatus and method using physiognomic feature information
CN104376250A (zh) 基于音型像特征的真人活体身份验证方法
CN104361326A (zh) 一种判别活体人脸的方法
CN105184235A (zh) 一种基于特征融合的二代身份证识别方法
CN104102903A (zh) 一种基于src的二次人脸识别方法
CN107862298B (zh) 一种基于红外摄像装置下眨眼的活体检测方法
WO2016082253A1 (zh) 用于出入境管理的三维人脸识别方法
CN103258190A (zh) 一种用于移动终端的人脸识别方法
CN104915590A (zh) 一种用于计算机加密的人脸识别系统及方法
Rossant et al. Iris identification and robustness evaluation of a wavelet packets based algorithm
CN104715228A (zh) 一种在线智能验证身份系统
Zhang et al. Finger vein recognition based on Gabor filter
Patel et al. Human identification by partial iris segmentation using pupil circle growing based on binary integrated edge intensity curve
CN104463143A (zh) 一种基于图像处理的身份识别系统
WO2023158408A1 (en) Face recognition method
CN202694370U (zh) 一种基于数字图像处理的多人脸识别系统
El-Said et al. Geometrical face recognition after plastic surgery
CN104599265A (zh) 一种人脸识别中三维人脸检测与姿态校正方法
Lateef et al. Face Recognition-Based Automatic Attendance System in a Smart Classroom
Zhao et al. Co-lda: A semi-supervised approach to audio-visual person recognition

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: 14906750

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: 14906750

Country of ref document: EP

Kind code of ref document: A1