CN107293002B - A kind of intelligent access control system based on recognition of face - Google Patents

A kind of intelligent access control system based on recognition of face Download PDF

Info

Publication number
CN107293002B
CN107293002B CN201710290067.7A CN201710290067A CN107293002B CN 107293002 B CN107293002 B CN 107293002B CN 201710290067 A CN201710290067 A CN 201710290067A CN 107293002 B CN107293002 B CN 107293002B
Authority
CN
China
Prior art keywords
face
image
face image
face information
access control
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.)
Expired - Fee Related
Application number
CN201710290067.7A
Other languages
Chinese (zh)
Other versions
CN107293002A (en
Inventor
贾华淇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN201710290067.7A priority Critical patent/CN107293002B/en
Publication of CN107293002A publication Critical patent/CN107293002A/en
Application granted granted Critical
Publication of CN107293002B publication Critical patent/CN107293002B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Landscapes

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

Abstract

The invention provides a kind of intelligent access control system based on recognition of face, including face identification device, face information database, access controller and entrance guard device, the face identification device communicates to connect with face information database, access controller, access controller and the entrance guard device communication connection；The face identification device is used to handle the facial image being taken on site, and the face information extracted in facial image is compared with the permission gate inhibition's opener's face information recorded in face information database, generates face information result of determination；The access controller generates the gate-control signal switched for access control device according to face information result of determination.The present invention realizes recognition of face and comparison, instead of and swipes the card and Password Input with recognition of face, improves the security of gate control system.

Description

Intelligent access control system based on face recognition
Technical Field
The invention relates to the technical field of entrance guard, in particular to an intelligent entrance guard system based on face recognition.
Background
In the related art, the card swiping access control means that a card swiping access control machine is placed at an entrance of the access control by using a non-contact Integrated Circuit (IC) card, and when a user enters, the user needs to lightly contact or approach a card reader like sitting in a bus for swiping a card, so that card information can be read, and the card swiping operation is performed.
The above-mentioned card-swiping access control method needs to prepare and deliver an IC card containing personal identification information to a user in advance, and if the user loses or misses the IC card, the user may not enter the meeting place, and there is a risk that the user pretends to enter the meeting place.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent access control system based on face recognition.
The purpose of the invention is realized by adopting the following technical scheme:
the intelligent access control system based on face recognition comprises a face recognition device, a face information database, an access controller and an access control device, wherein the face recognition device is in communication connection with the face information database and the access controller; the face recognition device is used for processing a face image shot on site, extracting face information in the face image, and comparing and analyzing the face information with face information which is recorded in a face information database and allows access control to be opened to generate a face information judgment result; and the access controller generates a door control signal for controlling the opening and closing of the access control device according to the face information judgment result.
The invention has the beneficial effects that: the face recognition and comparison are realized, the card swiping and password input are replaced by the face recognition, and the safety of the access control system is improved.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a block diagram schematic of the present invention;
fig. 2 is a block diagram of the face recognition apparatus of the present invention.
Reference numerals are as follows:
the system comprises a face recognition device 1, a face information database 2, an access controller 3, an access control device 4, a face image acquisition module 10, a face image detection module 20 and a face image processing module 30.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the intelligent access control system based on face recognition provided by this embodiment includes a face recognition device 1, a face information database 2, an access controller 3, and an access control device 4, where the face recognition device 1 is in communication connection with the face information database 2 and the access controller 3, and the access controller 3 is in communication connection with the access control device 4; the face recognition device 1 is used for processing a face image shot on site, extracting face information in the face image, and comparing and analyzing the face information recorded in the face information database 2 and allowing the entrance guard to open to generate a face information judgment result; and the access controller 3 generates a gating signal for controlling the opening and closing of the access control device 4 according to the judgment result of the face information.
Preferably, the access controller 3 is in communication connection with the access device 4 through a network, bluetooth, a serial communication interface or a relay.
Furthermore, the intelligent access control system further comprises a face image effective detection device for performing living body detection on the face image shot on site, the face image effective detection device is connected with the face recognition device 1, and the face recognition device 1 only operates when the living body detection is successful.
The embodiment of the invention realizes face recognition and comparison, replaces card swiping and password input with face recognition, and improves the security of the access control system.
Preferably, as shown in fig. 2, the face recognition device 1 includes a face image acquisition module 10, a face image detection module 20, and a face image processing module 30, which are connected in sequence; the face image processing module 30 is connected with the gate inhibition controller 3; the face image acquisition module 10 is used for acquiring a plurality of face images shot on site; the face image detection module 20 is used for performing quality detection on the collected face images and deleting the face images with unqualified quality detection results; the face image processing module 30 is configured to perform image processing on the face image output by the face image detection module 20, extract face information in the face image, compare and analyze the face information with face information, which is recorded in the face information database 2 and allows access control to be opened, generate a face information determination result, and send the face information determination result to the access control controller 3.
Preferably, when the facial image detection module 20 performs quality detection on the acquired facial image, the quality detection formula is defined as:
W i ＝(ξ i -ρ 1 )(λ i -ρ 2 ),＝1,…,
in the formula, W i Indicating the quality detection result, ξ, of the ith human face image i Is the gray value with the maximum probability of the gray histogram of the ith human face image, lambda i Is the mean square error of the gray level histogram of the ith human face image, m is the number of the human face images, rho 1 、ρ 2 Is a set threshold;
if W i If the quality detection result is more than 0, the quality detection result of the face image is qualified, and if W is greater than 0, the quality detection result of the face image is qualified i And if the quality detection result is less than or equal to 0, the quality detection result of the face image is unqualified, and the face image is deleted.
The preferred embodiment performs image quality detection calculation on the face image through a user-defined quality detection formula, is simple and quick, selects the image with qualified quality detection of the face image as the image for face recognition processing, lays a foundation for better extracting face information, and further improves the speed of face image processing.
The image processing of the face image output by the face image detection module 20 includes: filtering the face image to weaken the influence of image noise of the face image; carrying out image segmentation on the filtered face image, and extracting face information of the face image; the image segmentation is performed on the filtered face image, and specifically includes:
(1) Reducing the pixels of the face image to 400 multiplied by 600 according to the set image size adjustment proportion;
(2) Global segmentation threshold estimation is carried out on the face image by adopting an OTSU algorithm to obtain an optimal global segmentation threshold, the optimal global segmentation threshold is adjusted, the adjusted optimal global segmentation threshold is used for segmenting the face image to obtain a segmented image containing a face characteristic region, and the segmented image is averagely divided into 4 sub-images;
(3) Performing local segmentation threshold estimation on the sub-images by adopting an OTSU algorithm to obtain an optimal local segmentation threshold of each sub-image;
(4) The method comprises the following steps of segmenting different sub-images by using different segmentation thresholds, wherein a calculation formula for defining the segmentation thresholds of the sub-images is as follows:
in the formula, G i As a segmentation threshold for the ith sub-image, q i Is the preferred local segmentation threshold of the ith sub-image, H represents the gray variance of the whole face image, H i Representing the gray variance, δ, of the ith sub-image i Expressing the gray average value of the ith sub-image, delta expressing the gray average value of the whole face image, D is a set weight factor, and 0D is less than 1;
(5) Extracting coordinates of the face feature area obtained by dividing each subimage, and reducing the coordinates of the face feature area to original image coordinates according to a set image size adjustment ratio;
(6) And splicing the face characteristic areas obtained by segmenting each subimage to finish the segmentation of the current face image.
The preferred embodiment uses the maximum inter-class variance (OTSU) algorithm when segmenting the face image. The maximum between class variance (OTSU) algorithm is a dynamic threshold segmentation algorithm proposed by Ostu in 1979, determines a region segmentation threshold according to a gray level histogram of an image and an inter-class distance maximum criterion, and has a good effect on both single-peak and double-peak images. The principle of segmenting an image by using an inter-class variance (OTSU) algorithm is that the image is divided into a target area and a background area according to the gray characteristic of the image, and the maximum value of the inter-class variance between the target area and the background area is the segmentation threshold of the image;
when the preferred embodiment segments the face image, a two-step segmentation method is adopted for processing:
firstly, reducing the size of an image, and then performing global threshold segmentation on a face image by adopting an OTSU algorithm to obtain an approximate face characteristic region of the face image;
secondly, dividing the obtained approximate human face feature region to form 4 sub-images and then segmenting the sub-images;
compared with the global direct segmentation, the two-step segmentation method of the preferred embodiment has the advantages that the subimages obtained after the segmentation in advance have better binomial distribution characteristics, and the size and the content of each subimage are greatly reduced, so that the difficulty of face image segmentation is reduced, the speed of face image processing is further improved, and the working efficiency of an access control system is ensured.
Preferably, the adjusting the preferred global segmentation threshold specifically includes:
setting a preferable global segmentation threshold as T, setting an adjusting factor as zeta, and epsilon [0.90,1.10], wherein the adjusted preferable global segmentation threshold is zeta T;
wherein, the optimal value of the adjustment factor is selected according to the following mode:
(1) Several preferred values of the adjustment factor ζ are set, the preferred values ranging from [0.90,1.10];
(2) Processing the face image by using a Sobel boundary detection operator to obtain a face characteristic region boundary S (I) of the face image;
(3) Obtaining a corresponding adjusted optimal global segmentation threshold according to the set optimal value of the adjustment factor zeta, segmenting the face image by using the adjusted optimal global segmentation threshold, and obtaining the face feature area boundary S of the face image corresponding to each adjustment factor ζ＝x (I)；
(4) Calculating the boundaries S (I) and S of the two face characteristic regions ζ＝x (I) Selecting an adjustment factor value corresponding to the maximum boundary contact ratio as an optimal value of the adjustment factor, wherein a calculation formula for defining the boundary contact ratio is as follows:
in the formula, E ζ＝x Indicates the boundary contact ratio between the boundary of the face feature region of the face image obtained by the corresponding method and the boundary S (I) of the face feature region when the adjustment factor is zeta = x, "-d" indicates the intersection operation, x is the preferred value of the set adjustment factor,
the preferred embodiment adopts a Sobel boundary detection operator which can effectively detect the regional boundary with larger gray change, carries out boundary contact ratio calculation according to the detected human face characteristic regional boundary and the human face characteristic regional boundary obtained by adopting the adjusted preferred global segmentation threshold segmentation, selects the adjustment factor value corresponding to the larger boundary contact ratio as the final value, and realizes the correction of the preferred global segmentation threshold;
the preferred embodiment segments the face image by using the adjusted preferred global segmentation threshold, so that the more accurate contour of the face characteristic region can be obtained, the accuracy and the stability of segmentation of the face image are improved, a good foundation is laid for further face identification, and the working precision of an access control system is ensured.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (3)

1. An intelligent access control system based on face recognition is characterized by comprising a face recognition device, a face information database, an access controller and an access control device, wherein the face recognition device is in communication connection with the face information database and the access controller; the face recognition device is used for processing a face image shot on site, extracting face information in the face image, and comparing and analyzing the face information with face information which is recorded in a face information database and allows access control to be opened to generate a face information judgment result; the entrance guard controller generates a door control signal for controlling the entrance guard device to be opened and closed according to the face information judgment result; the access controller is in communication connection with the access device through a network, bluetooth, a serial communication interface or a relay; the face recognition device comprises a face image acquisition module, a face image detection module and a face image processing module which are sequentially connected; the human face image processing module is connected with the access controller; the face image acquisition module is used for acquiring a plurality of face images shot in the field; the face image detection module is used for carrying out quality detection on the collected face image and deleting the face image with unqualified quality detection result; the human face image processing module is used for carrying out image processing on the human face image output by the human face image detection module, extracting human face information in the human face image, carrying out comparison analysis on the human face information which is recorded in the human face information database and allows the entrance guard to be opened, generating a human face information judgment result, and sending the human face information judgment result to the entrance guard controller; when the facial image detection module performs quality detection on the collected facial image, a quality detection formula is defined as follows:
W i ＝(ξ i -ρ 1 )(λ i -ρ 2 ),i＝1,…,m
in the formula, W i Indicating the quality detection result, ξ, of the ith human face image i Is the gray value with the maximum probability of the gray histogram of the ith human face image, lambda i Is the mean square error of the gray level histogram of the ith human face image, m is the number of the human face images, rho 1 、ρ 2 Is a set threshold value;
if W i &gt, 0, the quality detection result of the face image is qualified, and if W is the quality detection result of the face image i And if the quality detection result is less than or equal to 0, the quality detection result of the face image is unqualified, and the face image is deleted.
2. The intelligent access control system based on face recognition is characterized by further comprising a face image effective detection device for performing living body detection on a face image shot in the field, wherein the face image effective detection device is connected with the face recognition device, and the face recognition device is operated only when the living body detection is successful.
3. The intelligent access control system based on face recognition according to claim 1, wherein the image processing of the face image output by the face image detection module comprises: filtering the face image to weaken the influence of image noise of the face image; carrying out image segmentation on the filtered face image, and extracting face information of the face image; the image segmentation is performed on the filtered face image, and specifically includes:
(1) Reducing the pixels of the face image to 400 multiplied by 600 according to the set image size adjustment proportion;
(2) Global segmentation threshold estimation is carried out on the face image by adopting an OTSU algorithm to obtain an optimal global segmentation threshold, the optimal global segmentation threshold is adjusted, the adjusted optimal global segmentation threshold is used for segmenting the face image to obtain a segmented image containing a face feature region, and the segmented image is averagely divided into 4 sub-images;
(3) Performing local segmentation threshold estimation on the sub-images by adopting an OTSU algorithm to obtain an optimal local segmentation threshold of each sub-image;
(4) The method comprises the following steps of segmenting different sub-images by using different segmentation thresholds, wherein a calculation formula for defining the segmentation thresholds of the sub-images is as follows:
in the formula, G i As a segmentation threshold for the ith sub-image, q i Is the preferred local segmentation threshold of the ith sub-image, H represents the gray variance of the whole face image, H i Representing the gray variance, δ, of the ith sub-image i Expressing the gray level mean value of the ith sub-image, delta expressing the gray level mean value of the whole face image, D is a set weight factor, 0<D<1；
(5) Extracting coordinates of the face feature area obtained by dividing each subimage, and reducing the coordinates of the face feature area to original image coordinates according to a set image size adjustment ratio;
(6) And splicing the face characteristic areas obtained by segmenting each subimage to finish the segmentation of the current face image.
CN201710290067.7A 2017-04-27 2017-04-27 A kind of intelligent access control system based on recognition of face Expired - Fee Related CN107293002B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710290067.7A CN107293002B (en) 2017-04-27 2017-04-27 A kind of intelligent access control system based on recognition of face

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710290067.7A CN107293002B (en) 2017-04-27 2017-04-27 A kind of intelligent access control system based on recognition of face

Publications (2)

Publication Number Publication Date
CN107293002A CN107293002A (en) 2017-10-24
CN107293002B true CN107293002B (en) 2018-03-02

Family

ID=60093944

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710290067.7A Expired - Fee Related CN107293002B (en) 2017-04-27 2017-04-27 A kind of intelligent access control system based on recognition of face

Country Status (1)

Country Link
CN (1) CN107293002B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107945323B (en) * 2017-11-13 2020-10-30 安徽互联智库数据技术有限公司 Security and protection method based on smart campus
CN107948258B (en) * 2017-11-13 2020-10-16 安徽互联智库数据技术有限公司 Visitor identification system based on wisdom campus
CN108198295A (en) * 2017-12-26 2018-06-22 佛山市道静科技有限公司 A kind of cell intelligent access control system
CN108877009B (en) * 2018-07-04 2020-04-21 城云科技（中国）有限公司 Intelligent access control system based on face recognition
CN112766888A (en) * 2021-01-08 2021-05-07 尹晓东 Engineering project on-site bidding intelligent management system and cloud management platform based on big data internet
CN113903143A (en) * 2021-09-26 2022-01-07 深圳市爱深盈通信息技术有限公司 Electric vehicle monitoring method and system

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120148160A1 (en) * 2010-07-08 2012-06-14 Honeywell International Inc. Landmark localization for facial imagery
CN103258191A (en) * 2013-05-15 2013-08-21 苏州福丰科技有限公司 Community access control system based on face recognition
CN106204815B (en) * 2016-06-23 2018-08-24 江西洪都航空工业集团有限责任公司 A kind of access control system based on human face detection and recognition
CN106296950A (en) * 2016-09-30 2017-01-04 深圳市商汤科技有限公司 A kind of gate control system based on recognition of face

Also Published As

Publication number Publication date
CN107293002A (en) 2017-10-24

Similar Documents

Publication Publication Date Title
CN107293002B (en) A kind of intelligent access control system based on recognition of face
CN105956578B (en) A kind of face verification method of identity-based certificate information
CN103593598B (en) User&#39;s on-line authentication method and system based on In vivo detection and recognition of face
JP3469031B2 (en) Face image registration apparatus and method
US6661907B2 (en) Face detection in digital images
CN106557723B (en) Face identity authentication system with interactive living body detection and method thereof
CN103914686B (en) A kind of face alignment authentication method and system shone based on certificate photo with collection
US20100128938A1 (en) Method and apparatus for detecting forged face using infrared image
KR20100072772A (en) Method and apparatus for real-time face detection using stereo vision
CN102262727A (en) Method for monitoring face image quality at client acquisition terminal in real time
US8965068B2 (en) Apparatus and method for discriminating disguised face
KR20020072198A (en) Detector for identifying facial image
JP4521086B2 (en) Face image recognition apparatus and face image recognition method
CN108710841B (en) Human face living body detection device and method based on MEMs infrared array sensor
Bhanu et al. Face recognition from face profile using dynamic time warping
Abidin et al. Iris segmentation analysis using integro-differential and hough transform in biometric system
CN109409343A (en) A kind of face identification method based on In vivo detection
JP2007206898A (en) Face authentication device and access management device
CN113255802A (en) Intelligent skin tendering system based on infrared laser
JP5877678B2 (en) Face authentication database management method, face authentication database management apparatus, and face authentication database management program
CN106803307A (en) A kind of bank note face amount based on template matches is towards recognition methods
KR101703690B1 (en) Apparatus for recognizing iris and operating method thereof
KR101704717B1 (en) Apparatus for recognizing iris and operating method thereof
Amjed et al. Noncircular iris segmentation based on weighted adaptive hough transform using smartphone database
CN115019364A (en) Identity authentication method and device based on face recognition, electronic equipment and 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
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20180302

Termination date: 20190427