CN109033988A - A kind of library's access management system based on recognition of face - Google Patents
A kind of library's access management system based on recognition of face Download PDFInfo
- Publication number
- CN109033988A CN109033988A CN201810706892.5A CN201810706892A CN109033988A CN 109033988 A CN109033988 A CN 109033988A CN 201810706892 A CN201810706892 A CN 201810706892A CN 109033988 A CN109033988 A CN 109033988A
- Authority
- CN
- China
- Prior art keywords
- image
- library
- face
- recognition
- central controller
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
- G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Abstract
A kind of library's access management system based on recognition of face, it include: image capture module, face detection module, central controller, server, library's sluice gate, library's alarm, described image acquisition module are connect with face detection module, and central controller is connect with face detection module, server, library's sluice gate, library's alarm, the system can accurately identify the identity of visitor, and have the characteristics that accuracy height, strong real-time, have a safety feature;It can be identified for different angle facial image, and recognition accuracy with higher.
Description
Technical field
The present invention relates to a kind of library's access management system based on recognition of face, belongs to technical field of face recognition.
Background technique
With the development of the times, room entry/exit management technology has become increasingly popular to be applied in daily life.Current figure
Book shop access management system mainly carries out identification to the personnel for entering and leaving library by identity recognition device, realizes people
The discrepancy of member.Existing library's access management system mostly uses greatly the technologies such as RFID, IC card, and disengaging personnel only need gently to brush
Card can complete identification, and there are certain drawbacks for aforesaid way, if internal staff forgets to carry IC card, can not just lead to
It crosses and swipes the card into library, to bring inconvenience to life.
With the development of face recognition technology and the progress of room entry/exit management technology, to develop the discrepancy pipe based on recognition of face
Reason system provides condition, still, few library's access management systems based on recognition of face currently on the market;In addition,
Due to the difference of face shooting angle, cause the recognition accuracy of face not high.
Summary of the invention
To overcome the shortcomings of that above-mentioned technology, the present invention provide a kind of library's access management system based on recognition of face,
It can accurately identify the identity of visitor, and have the characteristics that accuracy height, strong real-time, have a safety feature;It can be directed to
Different angle facial image is identified, and recognition accuracy with higher.
A kind of library's access management system based on recognition of face, comprising:
Image capture module is used to acquire the image in library sluice gate region, sends an image to Face datection mould
Block;
Face detection module is used to judge in image with the presence or absence of human face region, if it is not, then returning to Image Acquisition mould
Block resurveys image;If it is, sending an image to central controller;
Central controller is connect with server, library's sluice gate, library's alarm, and central controller sends out image
Server is given, carries out recognition of face by face recognition algorithms, and matched with the face database in server, if
Successful match, then library's sluice gate automatically opens under the control of central controller;If it fails to match, library's alarm
Audio alert is issued under the control of central controller, and library's sluice gate will not automatically open;
The face database is used to store the facial image of registered mistake;
The face recognition algorithms specifically: assuming that the facial image size of input is M*N;
(1) it calculates and cuts scale indices=[0 M-N]+1;
(2) according to indices value, [1,1] is taken by circulation respectively, [1, M-N+1], [M-N+1,1], [M-N+1, M-N+
It 1] is the starting point coordinate of image cut, interception obtains the 4 width sample images and other 4 width mirror image of N*N size from input picture
Sample image;
(3) [[(M-N)/2+1, (M-N)/2+1] is shearing starting point coordinate, obtains front and last 2 width of its mirror image for acquirement
Image;
(4) 10 samples pictures will finally be obtained, data set to be identified is added;
(5) using the deep learning network in Caffe platform, the similarity score of the 40*10 dimension of data to be identified is obtained
Matrix scores;Then to the score matrix of this 10 samples average operation obtain 40*1 dimension score matrix score, finally
Acquire the similarity score maxScore and corresponding label maxlabe1 of maximum probability in score, the then knowledge of the facial image
The corresponding label of other identity is maxlabe1+1, and identification is completed.
The system also includes human face data database management module is used to new user's facial image being added to face
Face database is removed in database or by user's facial image of failure.
Deep learning network in Caffe platform includes convolutional neural networks or deepness belief network or circulation nerve
Network.
Detailed description of the invention
Fig. 1 is a kind of library's access management system frame diagram based on recognition of face provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.
As shown in Figure 1, the present embodiment discloses a kind of library's access management system based on recognition of face, system includes:
Image capture module is used to acquire the image in library sluice gate region, sends an image to Face datection mould
Block;
Face detection module is used to judge in image with the presence or absence of human face region, if it is not, then returning to Image Acquisition mould
Block resurveys image;If it is, sending an image to central controller;
Central controller is connect with server, library's sluice gate, library's alarm, and central controller sends out image
Server is given, carries out recognition of face by face recognition algorithms, and matched with the face database in server, if
Successful match, then library's sluice gate automatically opens under the control of central controller;If it fails to match, library's alarm
Audio alert is issued under the control of central controller, and library's sluice gate will not automatically open;
The face database is used to store the facial image of registered mistake;
The face recognition algorithms specifically: assuming that the facial image size M*N of input;
(1) it calculates and cuts scale indices=[0 M-N]+1;
(2) according to indices value, [1,1] is taken by circulation respectively, [1, M-N+1], [M-N+1,1], [M-N+1, M-N+
It 1] is the starting point coordinate of image cut, interception obtains the 4 width sample images and other 4 width mirror image of N*N size from input picture
Sample image;
(3) [[(M-N)/2+1, (M-N)/2+1] is shearing starting point coordinate, obtains front and last 2 width of its mirror image for acquirement
Image;
(4) 10 samples pictures will finally be obtained, data set to be identified is added;
(5) using the deep learning network in Caffe platform, the similarity score of the 40*10 dimension of data to be identified is obtained
Matrix scores;Then to the score matrix of this 10 samples average operation obtain 40*1 dimension score matrix score, finally
Acquire the similarity score maxScore and corresponding label maxlabe1 of maximum probability in score, the then knowledge of the facial image
The corresponding label of other identity is maxlabe1+1, and identification is completed.
The system also includes human face data database management module is used to new user's facial image being added to face
Face database is removed in database or by user's facial image of failure.
Deep learning network in Caffe platform includes convolutional neural networks or deepness belief network or circulation nerve
Network.
Due to the difference of facial image shooting angle, the effect of recognition of face is influenced whether, for these problems, to every
Picture shearing 10 samples of sampling, compared with the prior art, the face recognition algorithms of the present embodiment can be directed to different angle people
Face image is identified, and recognition accuracy with higher.
Deep learning frame Caffe is the deep learning tool of the technical grade of first mainstream, computer vision tool
Packet is abundant, and operation is simple, realizes recognition of face using Caffe platform in the present embodiment.
The convolutional neural networks include improved convolutional neural networks, improved convolutional neural networks are as follows: due to convolution
The full articulamentum of neural network occupies the quantity of parameters of the network, and full articulamentum it is not necessary to, therefore propose to remove
One full articulamentum of former network, and it is longitudinally split at 7x7 and 5x5 convolution by the Conv 1_1 to former 11x11 convolution kernel size
Two layers of core size laterally splits into 1x1 to 1_2 layers of the Conv of former 5x5 convolution kernel size, 3x3 and 5x5 convolution kernel size
Three layers of mode improves network structure.
Preferably, further include in face recognition algorithms extract human face region feature, the feature include: LBP feature,
Haar feature, HOG feature.
It will be understood by those skilled in the art that each unit in Installation practice can be combined into a unit, and
Furthermore they can be divided into multiple subelements.In addition to such feature and/or at least some of process or unit are mutual
Mutually repel place, can using any combination to all features disclosed in this specification and so disclosed any method or
All process or units of person's equipment are combined.Unless expressly stated otherwise, each feature disclosed in this specification can be with
An alternative feature that provides the same, equivalent, or similar purpose replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize some of some or all components according to an embodiment of the present invention
Or repertoire.The present invention is also implemented as some or all equipment for executing method as described herein
Or program of device (for example, computer program and computer program product).
Although the embodiments of the invention are described in conjunction with the attached drawings, but those skilled in the art can not depart from this hair
Various modifications and variations are made in the case where bright spirit and scope, such modifications and variations are each fallen within by appended claims
Within limited range.
Claims (3)
1. a kind of library's access management system based on recognition of face characterized by comprising
Image capture module is used to acquire the image in library sluice gate region, sends an image to face detection module;
Face detection module is used to judge in image with the presence or absence of human face region, if it is not, then returning to image capture module weight
New acquisition image;If it is, sending an image to central controller;
Central controller is connect with server, library's sluice gate, library's alarm, and central controller is sent an image to
Server carries out recognition of face by face recognition algorithms, and is matched with the face database in server, if matching
Success, then library's sluice gate automatically opens under the control of central controller;If it fails to match, library's alarm is in
It entreats and issues audio alert under the control of controller, and library's sluice gate will not automatically open;
The face database is used to store the facial image of registered mistake;
The face recognition algorithms specifically: assuming that the facial image size of input is M*N;
(1) it calculates and cuts scale indices=[0 M-N]+1;
(2) according to indices value, [1,1] is taken by circulation respectively, [1, M-N+1], [M-N+1,1], [M-N+1, M-N+1] is
The starting point coordinate of image cut, interception obtains the 4 width sample images and other 4 width mirror image sample of N*N size from input picture
Image;
(3) [[(M-N)/2+1, (M-N)/2+1] is shearing starting point coordinate, obtains front and the last 2 width figure of its mirror image for acquirement
Picture;
(4) 10 samples pictures will finally be obtained, data set to be identified is added;
(5) using the deep learning network in Caffe platform, the similarity score matrix of the 40*10 dimension of data to be identified is obtained
scores;Then to the score matrix of this 10 samples average operation obtain 40*1 dimension score matrix score, finally acquire
The similarity score maxScore of maximum probability and corresponding label max1abe1 in score, then the identification body of the facial image
The corresponding label of part is max1abe1+1, and identification is completed.
2. system according to claim 1, it is characterised in that: the system also includes, human face data database management module,
For new user's facial image to be added in face database or user's facial image of failure is removed human face data
Library.
3. system according to claim 1, it is characterised in that: the deep learning network in Caffe platform includes convolution mind
Through network or deepness belief network or Recognition with Recurrent Neural Network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810706892.5A CN109033988A (en) | 2018-06-29 | 2018-06-29 | A kind of library's access management system based on recognition of face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810706892.5A CN109033988A (en) | 2018-06-29 | 2018-06-29 | A kind of library's access management system based on recognition of face |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109033988A true CN109033988A (en) | 2018-12-18 |
Family
ID=65522217
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810706892.5A Pending CN109033988A (en) | 2018-06-29 | 2018-06-29 | A kind of library's access management system based on recognition of face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109033988A (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036557A (en) * | 2013-03-06 | 2014-09-10 | 中国科学技术大学苏州研究院 | B/S architecture based distributed face recognition attendance system and attendance checking method thereof |
CN105354902A (en) * | 2015-11-10 | 2016-02-24 | 深圳市商汤科技有限公司 | Security management method and system based on face identification |
CN105868695A (en) * | 2016-03-24 | 2016-08-17 | 北京握奇数据系统有限公司 | Human face recognition method and system |
CN106023372A (en) * | 2016-05-23 | 2016-10-12 | 三峡大学 | Library access management system based on face recognition |
CN106056064A (en) * | 2016-05-26 | 2016-10-26 | 汉王科技股份有限公司 | Face recognition method and face recognition device |
CN106156702A (en) * | 2015-04-01 | 2016-11-23 | 北京市商汤科技开发有限公司 | Identity identifying method and equipment |
CN106228048A (en) * | 2016-07-15 | 2016-12-14 | 北京光年无限科技有限公司 | A kind of login method for intelligent robot product and device |
CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
CN106803301A (en) * | 2017-03-28 | 2017-06-06 | 广东工业大学 | A kind of recognition of face guard method and system based on deep learning |
CN107578007A (en) * | 2017-09-01 | 2018-01-12 | 杭州电子科技大学 | A kind of deep learning face identification method based on multi-feature fusion |
CN107729890A (en) * | 2017-11-30 | 2018-02-23 | 华北理工大学 | Face identification method based on LBP and deep learning |
CN107871103A (en) * | 2016-09-23 | 2018-04-03 | 北京眼神科技有限公司 | Face authentication method and device |
CN107944395A (en) * | 2017-11-27 | 2018-04-20 | 浙江大学 | A kind of method and system based on neutral net verification testimony of a witness unification |
CN108021846A (en) * | 2016-11-01 | 2018-05-11 | 杭州海康威视数字技术股份有限公司 | A kind of face identification method and device |
CN108090402A (en) * | 2016-11-22 | 2018-05-29 | 上海银晨智能识别科技有限公司 | A kind of video face identification method and system based on Recognition with Recurrent Neural Network |
-
2018
- 2018-06-29 CN CN201810706892.5A patent/CN109033988A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104036557A (en) * | 2013-03-06 | 2014-09-10 | 中国科学技术大学苏州研究院 | B/S architecture based distributed face recognition attendance system and attendance checking method thereof |
CN106156702A (en) * | 2015-04-01 | 2016-11-23 | 北京市商汤科技开发有限公司 | Identity identifying method and equipment |
CN105354902A (en) * | 2015-11-10 | 2016-02-24 | 深圳市商汤科技有限公司 | Security management method and system based on face identification |
CN105868695A (en) * | 2016-03-24 | 2016-08-17 | 北京握奇数据系统有限公司 | Human face recognition method and system |
CN106023372A (en) * | 2016-05-23 | 2016-10-12 | 三峡大学 | Library access management system based on face recognition |
CN106056064A (en) * | 2016-05-26 | 2016-10-26 | 汉王科技股份有限公司 | Face recognition method and face recognition device |
CN106228048A (en) * | 2016-07-15 | 2016-12-14 | 北京光年无限科技有限公司 | A kind of login method for intelligent robot product and device |
CN107871103A (en) * | 2016-09-23 | 2018-04-03 | 北京眼神科技有限公司 | Face authentication method and device |
CN108021846A (en) * | 2016-11-01 | 2018-05-11 | 杭州海康威视数字技术股份有限公司 | A kind of face identification method and device |
CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
CN108090402A (en) * | 2016-11-22 | 2018-05-29 | 上海银晨智能识别科技有限公司 | A kind of video face identification method and system based on Recognition with Recurrent Neural Network |
CN106803301A (en) * | 2017-03-28 | 2017-06-06 | 广东工业大学 | A kind of recognition of face guard method and system based on deep learning |
CN107578007A (en) * | 2017-09-01 | 2018-01-12 | 杭州电子科技大学 | A kind of deep learning face identification method based on multi-feature fusion |
CN107944395A (en) * | 2017-11-27 | 2018-04-20 | 浙江大学 | A kind of method and system based on neutral net verification testimony of a witness unification |
CN107729890A (en) * | 2017-11-30 | 2018-02-23 | 华北理工大学 | Face identification method based on LBP and deep learning |
Non-Patent Citations (3)
Title |
---|
JEFF DONAHUE ET AL.: "Long-Term Recurrent Convolutional Networks for Visual Recognition and Description", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
何嘉利: "基于深度学习的表情识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
韦鹏飞: "基于改进CNN的人脸检测和识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105612533B (en) | Living body detection method, living body detection system, and computer program product | |
WO2015165365A1 (en) | Facial recognition method and system | |
CN109819208A (en) | A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring | |
CN111563480B (en) | Conflict behavior detection method, device, computer equipment and storage medium | |
WO2018188993A1 (en) | Person identification systems and methods | |
CN112115866A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
CN110751022A (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
US8130285B2 (en) | Automated searching for probable matches in a video surveillance system | |
CN109325462B (en) | Face recognition living body detection method and device based on iris | |
JP5959093B2 (en) | People search system | |
CN108108711B (en) | Face control method, electronic device and storage medium | |
CN107590473B (en) | Human face living body detection method, medium and related device | |
CN108171138B (en) | Biological characteristic information acquisition method and device | |
CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
CN105022999A (en) | Man code company real-time acquisition system | |
US20220189212A1 (en) | Authentication device, authentication method, and recording medium | |
CN112634561A (en) | Safety alarm method and system based on image recognition | |
CN111597910A (en) | Face recognition method, face recognition device, terminal equipment and medium | |
RU2315352C2 (en) | Method and system for automatically finding three-dimensional images | |
CN112241689A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
CN110175553B (en) | Method and device for establishing feature library based on gait recognition and face recognition | |
Abiyev et al. | Neural network based biometric personal identification with fast iris segmentation | |
EP3617993B1 (en) | Collation device, collation method and collation program | |
CN114187561A (en) | Abnormal behavior identification method and device, terminal equipment and storage medium | |
CN111444849B (en) | Person identification method, device, electronic equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
RJ01 | Rejection of invention patent application after publication |