KR101529673B1 - 3d identification and security system - Google Patents

3d identification and security system Download PDF

Info

Publication number
KR101529673B1
KR101529673B1 KR1020140178509A KR20140178509A KR101529673B1 KR 101529673 B1 KR101529673 B1 KR 101529673B1 KR 1020140178509 A KR1020140178509 A KR 1020140178509A KR 20140178509 A KR20140178509 A KR 20140178509A KR 101529673 B1 KR101529673 B1 KR 101529673B1
Authority
KR
South Korea
Prior art keywords
image
subject
stereo
image information
information
Prior art date
Application number
KR1020140178509A
Other languages
Korean (ko)
Inventor
손관우
Original Assignee
손관우
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 손관우 filed Critical 손관우
Priority to KR1020140178509A priority Critical patent/KR101529673B1/en
Application granted granted Critical
Publication of KR101529673B1 publication Critical patent/KR101529673B1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The present invention relates to a three-dimensional identification security system, and more particularly, to a three-dimensional identification security system that acquires a pair of stereoscopic images having a visual difference at the same time point with respect to a subject from a 3D stereo camera and compares the stereoscopic images with image information The depth information of each feature point is added to the 2D image information by calculating a depth information of each feature point, thereby obtaining a real-time 3D object model The present invention relates to a three-dimensional identification security system capable of improving the recognition rate of a subject irrespective of whether wearing glasses or changing illumination.
A three-dimensional identity security system according to the present invention comprises: a 3D stereo camera for capturing a subject placed at regular intervals and acquiring a pair of stereo images having a visual difference at the same time; A database in which image information about a specific person is stored; An operation unit for analyzing a stereo image photographed by the 3D stereo camera and for comparing the image information of the analyzed subject with the image information stored in the database to confirm the identity of the subject; Wherein the database stores image information in which depth information of each feature point is matched to a plurality of feature points based on a 2D image of a specific person, A plurality of feature points are selected from the stereo image so as to acquire image information of the feature points, and the depth information of the selected feature points is calculated using the pair of stereo images having a difference.

Description

[0002] 3D IDENTIFICATION AND SECURITY SYSTEM [0003]

The present invention relates to a three-dimensional identification security system, and more particularly, to a three-dimensional identification security system that acquires a pair of stereoscopic images having a visual difference at the same time point with respect to a subject from a 3D stereo camera and compares the stereoscopic images with image information The depth information of each feature point is added to the 2D image information by calculating a depth information of each feature point, thereby obtaining a real-time 3D object model The present invention relates to a three-dimensional identification security system capable of improving the recognition rate of a subject irrespective of whether wearing glasses or changing illumination.

In recent years, face recognition technology has been utilized in various fields including a control device for passengers, and has a tendency to be more active as compared with other biometrics technologies such as fingerprint and iris recognition.

That is, in the case of fingerprint or iris recognition, in order for the user to be authenticated, it is necessary to take a predetermined action, for example, to contact the finger with the fingerprint recognition sensor in case of fingerprint recognition and close the eye to the iris recognition sensor in case of iris recognition .

On the other hand, since face recognition technology can perform the face recognition process when the face is caught by the camera image, the user does not need to take an unnatural action for authentication, and the face recognition technology It also has the advantage of authenticating the user through.

In the conventional two-dimensional face recognition technology, after inputting a two-dimensional face image of a specific person, characteristic two-dimensional face images are extracted and stored in a database based on color and contrast information, When a face image of a new person comes in, the similarity with the characteristic face information in the corresponding database is examined, and it is possible to perform the authentication to confirm the identity of the registered person and the registered person.

However, the conventional two-dimensional face recognition technology relies on two-dimensional face recognition for previously registered people, thereby causing the following problems.

First, the conventional two-dimensional face recognition technology has a disadvantage in that the recognition rate significantly decreases according to the illumination state at the time of shooting the image and the direction in which the face faces.

That is, the conventional face recognition technology has a disadvantage in that authentication is not accurately performed to identify the user because the recognition rate is lowered because the false face information is extracted due to the influence of the brightness and darkness information of the image due to the change of the illumination.

Secondly, in the conventional two-dimensional face recognition technology, a large amount of photographs considering variations in various angles and subject sizes are required for forming a three-dimensional object, and there is a problem in that the calculation amount to be processed in the determination of the face similarity is increased .

In recognition of the above-described problems of the prior art, "Face Recognition Apparatus and Method Using 3-Dimensional Information" has been proposed in Registration No. 10-1053253 (Published on Aug. 23, 2011).

However, the conventional art has a drawback that it is difficult to generate a 3D object model in real time due to a large amount of computation to be processed by using a wire frame model as a three-dimensional generation method.

It is an object of the present invention to provide a real-time 3D object model capable of generating a real-time 3D object model with a minimum amount of calculation, And to provide a three-dimensional identification security system capable of improving the recognition rate.

According to an aspect of the present invention, there is provided a 3D identity security system comprising: a 3D stereo camera for capturing a subject and obtaining a pair of stereo images having a visual difference at the same time; A database in which image information about a specific person is stored; An operation unit for analyzing a stereo image photographed by the 3D stereo camera and for comparing the image information of the analyzed subject with the image information stored in the database to confirm the identity of the subject; Wherein the database stores image information in which depth information of each feature point is matched to a plurality of feature points based on a 2D image of a specific person, A plurality of feature points are selected from the stereo image so as to acquire image information of the feature points, and the depth information of the selected feature points is calculated using the pair of stereo images having a difference.

In the three-dimensional identification security system according to the present invention, the database stores image information of a specific person's face, and the operation unit extracts a face region of the subject from the stereo image.

delete

According to another aspect of the present invention, there is provided a three-dimensional identity security system, comprising: a statistical face model (AAM) based on a plurality of feature points selected from the stereo image and position information and depth information of the feature points; Dimensional face image of the subject by using the three-dimensional face image.

In the 3D identity security system according to the present invention, the database may store a 2D image of a front face of a specific person, and the operation unit may generate the three-dimensional ID information by using the statistical face model (AAM; Active Appearance Model) Dimensional face image of the subject is projected on a two-dimensional image from the front to acquire a 2D image of the front face of the subject, and compared with the 2D image of the front face of the specific person stored in the database to identify the subject .

In the three-dimensional identification security system according to the present invention, the feature points in the image information stored in the database or in the image information on the subject include eyes, nose, mouth, and ear.

In addition, the three-dimensional identification security system according to the present invention includes: a glass to be worn on the user's eyes; Wherein the 3D stereo camera is mounted on the glass.

In addition, the 3D identity security system according to the present invention is characterized in that the glass has a display means for displaying information received from the operation unit so that the user can directly see the information.

The three-dimensional identification security system according to the present invention, by virtue of the organic combination of the 3D stereo camera, the database and the operation unit, selects a plurality of feature points from a stereo image and calculates depth information for each feature point, By adding the depth information of each feature point to the image information, it is possible to generate a real-time 3D object model with a minimum amount of computation, thereby improving the recognition rate of the object irrespective of whether wearing glasses or changing illumination.

delete

In addition, the three-dimensional identification security system according to the present invention has an advantage that a three-dimensional facial image can be acquired quickly by using a statistical face model (AAM), and in addition to the comparison of 3D feature points, There is an advantage in that the 2D image obtained by projection can be compared with the 2D image of the specific person stored in the database, thereby enabling identification with higher accuracy.

In addition, the 3D identity security system according to the present invention is capable of patrolling a 3D stereoscopic camera in a state that a police officer and a security officer wear the 3D stereoscopic camera on a glass worn by a user, There is an advantage of being effective.

1 is a conceptual diagram of a three-dimensional identification security system according to an embodiment of the present invention.
2 is a block diagram of a 3D identity security system according to an embodiment of the present invention.
FIG. 3 is a diagram showing an arithmetic state diagram of an arithmetic unit according to an embodiment of the present invention.
FIG. 4 is a flowchart showing the operation of the operation unit according to the embodiment of the present invention.

Hereinafter, a three-dimensional identification security system according to the present invention will be described in detail with reference to the embodiments shown in the drawings.

FIG. 1 is a conceptual diagram of a 3D identity verification security system according to an embodiment of the present invention. FIG. 2 is a configuration diagram of a 3D identity security system according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating the operation of the operation unit according to the embodiment of the present invention.

1 to 4, a 3D identity security system according to an exemplary embodiment of the present invention includes a glass 10, a 3D stereo camera 20, a database 30, and an operation unit 40 .

The first camera 21 and the second camera 22 of the 3D stereo camera 20 are mounted on the glass 10 at regular intervals so that the glass 10 is worn on the user's eyes. The display unit 11 displays the information received from the operation unit 40 so that the user can see the information. The photographing and identification of the subject can be performed in a wearable manner. It is possible to patrol in the state, and it is said that it has an excellent effect especially on the search of the slave.

The display means 11 may be constituted by a projector type which transmits information to a user's eye using a projector and a prism, or may be manufactured by an LCD type or the like.

The 3D stereo camera 20 is configured such that a first camera 21 and a second camera 22 are mounted on the glass 10 at regular intervals to photograph a subject and generate a pair of stereo images .

Although the stereo image itself is a 2D image, the depth information of feature points selected by the operation unit 40 can be obtained using a pair of visual differences.

delete

The 3D stereo camera 20 is preferably composed of a high-definition camera of HD class so that the activation distance can be at least about 3 m.

delete

On the other hand, the stereo image acquired by the 3D stereo camera 20 is not a 2D image of the front face of the subject as an image photographed during movement of the subject, but can be compared with the 2D image of the front face stored in the database 30 A face image is converted into a 2D image by the operation unit 40, which will be described later in detail.

In an embodiment of the present invention, the database 30 stores image information of a specific person on the basis of a 2D image of a front face of a specific person, Information is stored.

The operation unit 40 analyzes the stereo image photographed by the 3D stereo camera 20 and compares the image information of the analyzed subject with the image information stored in the database 30 to confirm the identity of the subject to be.

3, the operation unit 40 extracts a face region of a subject from the stereo image, and acquires image information of the subject corresponding to the image information stored in the database 30, Selects a plurality of feature points from the image, and calculates each depth information of the selected feature points using the pair of stereo images having a difference in visual acuity.

In addition, the operation unit 40 may use a statistical face model (AAM) based on a plurality of feature points selected from the stereo image and position information and depth information of the feature points instead of all the pixels of the face image Dimensional face image of the subject.

As described above, by generating the three-dimensional face image of the subject using the statistical face model (AAM) based on the feature point selection and the depth information, a real-time 3D object model can be generated with a minimum amount of calculation.

Feature points in image information stored in the database or in image information about the subject include eyes, nose, mouth, and ear.

The operation unit 40 may be configured to acquire recognition results including various pose, facial expressions, and illumination changes on the three-dimensional face image generated as described above.

In addition, in the operation unit 40 of the present invention, in addition to the 3D feature point comparison, a 3D face image of a subject generated using the statistical face model (AAM; Active Appearance Model) A 2D image of the front face of the subject is projected on the front face to obtain a 2D image of the front face of the subject and compared with the 2D image of the front face of the specific person stored in the database to confirm the identity of the subject, It becomes possible.

The database 30 and the arithmetic unit 40 can be manufactured as portable type as shown in FIG. 1, and the database 30 and the arithmetic unit 40 are constructed in a remote server (not shown) , And a communication unit (not shown) to remotely connect to the remote server (not shown).

As a result, the three-dimensional identification security system according to the present invention adds depth image information through two-dimensional image analysis to generate a large amount of additional variables (individual's face shape) and internal values Head movement, emotional expression, light, age) will overcome many of the disadvantages of the two-dimensional face and get more accurate recognition results.

The three-dimensional identification security system described above and shown in the drawings is only one embodiment for carrying out the present invention, and should not be construed as limiting the technical idea of the present invention. The scope of protection of the present invention is defined only by the matters set forth in the following claims, and the embodiments improved and changed without departing from the gist of the present invention are obvious to those having ordinary skill in the art to which the present invention belongs It will be understood that the invention is not limited thereto.

10 Glass
11 display means
20 3D Stereo Camera
21 First camera
22 Second camera
30 databases
40 Operation unit

Claims (8)

A 3D stereoscopic camera for photographing a subject placed at regular intervals and acquiring a pair of stereo images having a visual difference at the same time; A database in which image information about a specific person is stored; An operation unit for analyzing a stereo image photographed by the 3D stereo camera and for comparing the image information of the analyzed subject with the image information stored in the database to confirm the identity of the subject; Including,
The database stores image information in which depth information of each feature point is matched to a plurality of feature points based on a 2D image of a specific person,
Wherein the operation unit is configured to select a plurality of feature points from the stereo image so as to obtain image information on the subject corresponding to the image information stored in the database and to display the selected feature points using the pair of stereo images having a visual difference Dimensional face of the subject using a statistical face model (AAM; Active Appearance Model) based on a plurality of feature points selected from the stereo image and position information and depth information of the feature points, Generating an image,
The database stores a 2D image of a front face of a specific person,
The operation unit may obtain a 2D image of a front face of a subject by projecting the 3D face image of the subject generated using the statistical face model (AAM; Active Appearance Model) on the 2D image on the front face, And comparing the face image with a 2D image of a front face of a specific person stored in the database to confirm the identity of the subject.
delete delete delete delete The method according to claim 1,
Wherein the feature points in the image information stored in the database or in the image information on the subject include eyes, nose, mouth, and ear.
7. The method according to claim 1 or 6,
A glass worn by the user's eyes; Further included,
Wherein the 3D stereo camera is mounted to the glass.
8. The method of claim 7,
Wherein the glass is provided with a display means for displaying information received from the operation unit so that the user can directly see the information.
KR1020140178509A 2014-12-11 2014-12-11 3d identification and security system KR101529673B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020140178509A KR101529673B1 (en) 2014-12-11 2014-12-11 3d identification and security system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020140178509A KR101529673B1 (en) 2014-12-11 2014-12-11 3d identification and security system

Publications (1)

Publication Number Publication Date
KR101529673B1 true KR101529673B1 (en) 2015-06-17

Family

ID=53519259

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020140178509A KR101529673B1 (en) 2014-12-11 2014-12-11 3d identification and security system

Country Status (1)

Country Link
KR (1) KR101529673B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101799335B1 (en) * 2016-07-26 2017-11-20 주식회사 에스원 Fake Face Distinction System by Using Monocular Camera and Method thereof

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009157767A (en) * 2007-12-27 2009-07-16 Nippon Telegr & Teleph Corp <Ntt> Face image recognition apparatus, face image recognition method, face image recognition program, and recording medium recording this program
KR101053253B1 (en) * 2009-09-01 2011-08-02 (주)실리콘화일 Apparatus and method for face recognition using 3D information
KR101316805B1 (en) * 2013-05-22 2013-10-11 주식회사 파이브지티 Automatic face tracing and recognition method and system
KR20140139730A (en) * 2013-05-28 2014-12-08 주식회사 포디컬쳐 Method for classifying elements of face using depth difference

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009157767A (en) * 2007-12-27 2009-07-16 Nippon Telegr & Teleph Corp <Ntt> Face image recognition apparatus, face image recognition method, face image recognition program, and recording medium recording this program
KR101053253B1 (en) * 2009-09-01 2011-08-02 (주)실리콘화일 Apparatus and method for face recognition using 3D information
KR101316805B1 (en) * 2013-05-22 2013-10-11 주식회사 파이브지티 Automatic face tracing and recognition method and system
KR20140139730A (en) * 2013-05-28 2014-12-08 주식회사 포디컬쳐 Method for classifying elements of face using depth difference

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101799335B1 (en) * 2016-07-26 2017-11-20 주식회사 에스원 Fake Face Distinction System by Using Monocular Camera and Method thereof

Similar Documents

Publication Publication Date Title
CN106407914B (en) Method and device for detecting human face and remote teller machine system
US20170337441A1 (en) Systems And Methods Of Biometric Analysis With A Spectral Discriminator
US11682231B2 (en) Living body detection method and device
CN108875485A (en) A kind of base map input method, apparatus and system
JP5127531B2 (en) Image monitoring device
Jana et al. Age estimation from face image using wrinkle features
KR101640014B1 (en) Iris recognition apparatus for detecting false face image
WO2020020022A1 (en) Method for visual recognition and system thereof
KR101444538B1 (en) 3d face recognition system and method for face recognition of thterof
CN104537292A (en) Method and system for spoof detection for biometric authentication
JP5592040B1 (en) Fraud detection in biometric type access control systems
CN110309782A (en) It is a kind of based on infrared with visible light biocular systems living body faces detection methods
CN108304828B (en) Three-dimensional living body face recognition device and method
KR20120135469A (en) Facial image search system and facial image search method
CN108875468B (en) Living body detection method, living body detection system, and storage medium
CN106937532B (en) System and method for detecting actual user
US20210256244A1 (en) Method for authentication or identification of an individual
JP6855872B2 (en) Face recognition device
CN114894337B (en) Temperature measurement method and device for outdoor face recognition
RU2315352C2 (en) Method and system for automatically finding three-dimensional images
CN106991376B (en) Depth information-combined side face verification method and device and electronic device
KR101053253B1 (en) Apparatus and method for face recognition using 3D information
KR101529673B1 (en) 3d identification and security system
KR20070077264A (en) A method of face recognizing
KR100862526B1 (en) Method and system constructing moving image database and face recognition method and system using the same

Legal Events

Date Code Title Description
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
LAPS Lapse due to unpaid annual fee