KR102059686B1 - Method, terminal and system for face authentication using multiple camera - Google Patents

Abstract

The present invention relates to a face authentication method, a terminal and a system using multiple cameras. The face authentication method using multiple cameras comprises: a step that the face authentication terminal photographs a depth image of at least one user entering a predetermined distance by using a 3D depth camera to obtain distance information of the at least one user; a step that the face authentication terminal detects an area of a user at a specific position from a gate according to the distance information; and a step that the face authentication terminal photographs a 2D image of the at least one user by using a 2D camera and overlays the depth image and the 2D image to detect a face area of a user at a position overlapping the area of the user at the specific position. Therefore, an immigration process can be efficiently processed for the user only by the face authentication.

Description

Face recognition method, terminal and system using multiple cameras {METHOD, TERMINAL AND SYSTEM FOR FACE AUTHENTICATION USING MULTIPLE CAMERA}

The disclosed technology relates to a method, a terminal and a system for authenticating a face of a user using a plurality of different cameras.

Techniques for verifying a person's identity using a face image or performing authentication for a specific procedure have been used. Representatively, a technology of confirming identity is used by photographing a user's face with a camera at an airport and comparing feature information of a face image with feature information extracted from a registered passport.

As the number of users going out and coming in through the airport increases each year, airport immigration is gradually changing to shorten the time required by the unmanned system to automatically process immigration. According to this trend, immigration procedures are expected to be performed in the direction of opening and closing the immigration gate based on minimal information recognition.

On the other hand, according to the automatic immigration screening system of Incheon International Airport, the user scans his passport, passes through the gate, performs fingerprint scan and face image, and performs immigration procedures. However, these immigration systems are operated under the premise that users enter one by one, so it is difficult to accurately process immigration only by face authentication. Therefore, there is a problem that the immigration process is cumbersome because there is a lot of information recognition actions that one user must perform to pass through the gate, and the user has to perform authentication by contacting a part of his / her body. I had. In addition, when a plurality of users are photographed at a time, there is a problem that an error occurs in the immigration process because it is not possible to check which user enters the gate first.

Meanwhile, referring to Korean Patent Laid-Open Publication No. 10-2016-0017000 (name of the invention: a face detection apparatus and method), a technique of detecting a position of a face based on a distance difference image obtained using a stereo camera is disclosed. However, this technique has a problem that it is possible to determine the location of the target, but not determine who the target is specifically.

The disclosed technology provides a method, a terminal, and a system for performing authentication by detecting a face region of a user at a specific location based on a depth image and a 2D image obtained using a plurality of different cameras.

In order to achieve the above technical problem, a first aspect of the disclosed technology captures a depth image of at least one user entered by a face authentication terminal within a predetermined distance using a 3D depth camera and displays distance information of the at least one user. Acquiring; detecting, by the face authentication terminal, an area of a user at a specific position from the gate according to the distance information; and capturing a 2D image of the at least one user by using the 2D camera by the face authentication terminal; And overlaying the depth image and the 2D image and detecting a face region for the user at a position overlapping with the region of the user at the specific position, to provide a face authentication method using a plurality of cameras. have.

In order to achieve the above technical problem, a second side of the disclosed technology is provided on a front side or side of a gate, and includes a plurality of cameras for photographing depth images and face images of a plurality of users who enter the gate within a predetermined distance, the depth A processor for detecting a region of a user at a specific position among the plurality of users using an image and a face region at a position overlapping with the user region using the face image and the detection according to a control signal of the processor The present invention provides a face authentication terminal using a plurality of cameras including a communication module for transmitting an image of a face region to an immigration server according to a predetermined period.

In order to achieve the above technical problem, a third aspect of the disclosed technology captures a depth image and a 2D image of a plurality of users who enter a gate within a predetermined distance by using a plurality of different cameras, and the depth image and the 2D image. Overlay to detect distance information and face area for the plurality of users and receive a face authentication terminal for detecting a face area of the user at a specific location from the gate and an image of the face area of the user at the specific location The present invention provides a face authentication system using a plurality of cameras including an immigration server that searches for specific user information matching an image of the face area among a plurality of stored user information.

In order to achieve the above technical problem, a fourth aspect of the disclosed technology is provided at a specific height in front of a gate, and captures a first depth image and a first 2D image of a plurality of users using a plurality of different cameras. A first terminal for detecting a face region of a user at a specific position of the gate by using a first depth image and the first 2D image, and a camera provided on one side of the gate and of the same type as the plurality of different cameras A second terminal for capturing a second depth image and a second 2D image of the plurality of users using the second depth image and the second 2D image, and detecting a face region of the user at the specific location; And a registered company based on an image of the face area received from at least one of the first terminal and the second terminal. To provide a plurality of face authentication system using the camera, including the immigration server to retrieve specific user information that matches one of the party information.

Embodiments of the disclosed technology may have effects including the following advantages. However, since the embodiments of the disclosed technology are not meant to include all of them, the scope of the disclosed technology should not be understood as being limited thereto.

According to an embodiment of the disclosed technology, a face authentication method, a terminal, and a system using a plurality of cameras have an effect of efficiently handling a user's immigration process by opening and closing an entry / exit gate only by face authentication.

In addition, there is an effect of preventing the authentication error by identifying the entry order of a specific user using a plurality of different cameras.

In addition, even if a plurality of users are photographed in one image, it is effective to grasp the authentication order for each user.

1 is a flowchart illustrating a face authentication method using a plurality of cameras according to an embodiment of the disclosed technology.
2 is a block diagram of a face authentication terminal using a plurality of cameras according to an embodiment of the disclosed technology.
3 is a block diagram of a face authentication system using a plurality of cameras according to an embodiment of the disclosed technology.
4 is a view showing an access authentication terminal provided in a gate.
5 is a diagram illustrating a depth image photographed using a 3D depth camera.
6 is a diagram illustrating a 2D image photographed using a 2D camera.
7 is a diagram illustrating overlaying a depth image and a 2D image.

As the invention allows for various changes and numerous embodiments, particular embodiments will be illustrated in the drawings and described in detail in the written description. However, this is not intended to limit the present invention to specific embodiments, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

The terms first, second, A, B, etc. may be used to describe various components, but the components are not limited by the terms, but merely for distinguishing one component from other components. Only used as For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. The term and / or includes a combination of a plurality of related items or any item of a plurality of related items.

As used herein, the singular forms "a", "an" and "the" are to be understood as including plural forms unless the context clearly dictates otherwise. And the term " comprises, " and the like, means that there is a feature, number, step, action, component, part, or combination thereof described, and one or more other features or numbers, step action component, part, etc. Or it does not exclude the presence or the possibility of adding them.

Prior to the detailed description of the drawings, it is to be clear that the division of the components in the present specification is only divided by the main function of each component. That is, two or more components to be described below may be combined into one component, or one component may be provided divided into two or more for each function.

Each of the components to be described below may additionally perform some or all of the functions of other components in addition to the main functions of the components, and some of the main functions of each of the components are different. Of course, it may be carried out exclusively by. Therefore, the presence or absence of each component described through this specification should be functionally interpreted.

1 is a flowchart illustrating a face authentication method using a plurality of cameras according to an embodiment of the disclosed technology. Referring to FIG. 1, a face authentication method using a plurality of cameras includes the following steps.

In step 110, the face authentication terminal captures a depth image of at least one user who enters within a predetermined distance by using a 3D depth camera. Here, within a certain distance means within a distance from which the user can be photographed from the location where the face authentication terminal is installed. For example, if the face authentication terminal is provided in the immigration gate, the distance up to several meters in front of the immigration gate may be determined within a predetermined distance. Alternatively, if the face authentication terminal is provided in the attendance attendance table, the distance to several meters around the table may be determined to be within a certain distance.

The face authentication terminal is provided at a predetermined height of the front or side of the gate. The depth image may be captured using a 3D depth camera capable of determining a depth value according to a delay in which light provided on one surface of the terminal returns. In addition, it is possible to obtain distance information of at least one user captured in the depth image.

As an example, when the face authentication terminal is located at the front of the gate as an example, a depth image of a user who is within a range of 20 meters in front of the 3D depth camera that can recognize an object may be photographed using the front of the gate as a reference point. have. In this case, the 3D depth camera may capture depth images of at least one user and many users.

Meanwhile, the face authentication terminal obtains distance information of at least one user by using the depth image photographed as described above. That is, by using the distance information acquired using the depth image, it is possible to determine how close each user is photographed from the gate or how close to a predetermined specific point.

In step 120, the face authentication terminal detects an area of the user located at a specific location from the gate according to the distance information. Herein, the specific position means a specific position in front of the gate that is previously determined to recognize the face of the user as described above. For example, it may be the position of the guideline displayed in front of the gate. The facial authentication terminal detects an area of a specific user which is determined to be the closest to the guideline among the various users. Alternatively, when a plurality of users are photographed in the image, the area of the user closest to each other may be detected using distance information.

In step 130, the face authentication terminal captures a 2D image of at least one user by using a 2D camera. The 2D camera may generally be a widely used optical camera. The face authentication terminal may include two cameras in a similar position and control to shoot at the same time to reduce the occurrence of an error value when overlaying the images taken from the two cameras.

In operation 130, the face authentication terminal detects a face region of the user at a position overlapping the region of the user at a specific position by overlaying the depth image and the 2D image. In other words, by using the depth image, the range of which the user is primarily detected is reduced, and then the face area of the detection target is detected to prepare for face authentication.

In operation 130, the face authentication terminal extracts an image of the detected face region and transmits the image to the immigration server. That is, when the detection target is limited among the various users and the face region of the user is detected, the face authentication of the user may be performed by transmitting an image thereof to the immigration server.

The face authentication terminal is connected to the immigration server and can transmit an image to the immigration server using the connection path. The connection path between the terminal and the server can use a wired path through a dedicated line, and images can be transmitted wirelessly as needed. The face authentication terminal opens and closes the gate according to the face authentication result performed through the immigration server.

Meanwhile, the face authentication terminal may have a database synchronized with the database of the immigration server using a route connected to the immigration server. That is, the gate opening and closing may be performed using a database synchronized with the server without transmitting the image of the detected face region to the server. For example, the image of the detected face region may be matched to a plurality of face images stored in the database, and the gate may be opened when the matching face image exists in the database, and the gate may not be opened when the matching face image does not exist in the database. . The operation result is transmitted to the connected immigration server to update the immigration server's database so that the two databases can be synchronized.

Meanwhile, the facial authentication terminal includes an IR sensor. Like the conventional IR sensor, the IR sensor included in the terminal also detects the presence of a person within a certain distance. The face authentication terminal may wait for the 3D depth camera and the 2D camera in the sleep mode if the user is not detected within a certain distance using the IR sensor. If the IR sensor detects a user, the 3D depth camera and the 2D camera can be switched to the active mode.

On the other hand, two types of cameras provided in the face authentication terminal have a predetermined waiting time to continuously photograph the user entering the gate without error. For example, the 3D depth camera may capture a next depth image after a preset waiting time, and the 2D camera may also capture a 2D image including a face region of another user who enters a specific location after the same waiting time.

The reason why the two cameras have the same waiting time is to minimize the possibility of error when overlaying the images acquired from the two cameras as described above, and to accurately detect the user's face in the overlapping area.

Meanwhile, the gate mentioned herein may be a gate used to perform an immigration procedure, such as an airport. That is, the left and right gates may be gates that are opened and closed while rotating. The gate is opened and closed according to a control signal transmitted from the face authentication terminal or the immigration server, and the face authentication terminal provided in the gate may take an operation for photographing the next user according to the open / closed state of the gate. For example, when the two gates rotate, it may be determined that the face authentication of the current user is successful, and the two cameras may be initialized to photograph the next user.

Meanwhile, as described above, the face authentication terminal basically overlays the depth image and the 2D image to detect one user. However, it is also possible to perform the same image overlay but detect face regions for a plurality of users. For example, when a plurality of users are photographed in the depth image, an authentication sequence for each user may be given according to distance information. In addition, a face area may be detected for each user. Here, the authentication order means the order for passing the gate, and it is preferable that the authentication order is given in the order close to the gate.

Conventionally, a user's face is recognized by using one camera. In this case, a face area of a specific user may be larger than another user. In general, a person with a large face is recognized as being near, but in reality, a face of a far person is larger than a person in front of a person depending on race, sex, and body type. Therefore, in the disclosed technology, the distance information of each user is determined based on the depth image without determining the distance by simply the size of the face, and the distance information is reflected on the matching face to determine the order of performing the face authentication for the gate passing for each user. Can be.

Meanwhile, the face authentication terminal extracts an image of the face area detected for each user and sequentially transmits the image of the face area to the immigration server according to the authentication procedure. That is, face authentication may be performed faster by sequentially processing face authentication for a plurality of users through a single image overlay.

2 is a block diagram of a face authentication terminal using a plurality of cameras according to an embodiment of the disclosed technology. Referring to FIG. 2, the face authentication terminal 200 includes a plurality of cameras 210a and 210b, a processor 220, and a communication module 230.

The plurality of cameras 210a and 210b are provided at the front or side of the gate. For example, a main terminal for face authentication may be provided at the front of the gate, and a sub terminal may be provided at the side of the gate to assist the main terminal. The plurality of cameras 210a and 210b may include the same type of camera in each of the two terminals. For example, if 210a is a 3D depth camera and 210b is a 2D camera, the main terminal and the sub terminal may have a 3D depth camera and a 2D camera, respectively.

Meanwhile, as described above, the plurality of cameras 210a and 210b include a 3D depth camera and a 2D camera. The 3D depth camera captures depth images of a plurality of users, and the 2D camera captures face images of a plurality of users.

The processor 220 detects an area of a user located at a specific position among the plurality of users by using depth images captured by the plurality of cameras 210a and 210b, respectively. The face region is detected by using the face image at a position overlapping with the user region. The processor 220 may overlay the depth image and the face image photographed by the plurality of cameras 210a and 210b, respectively, and detect a face region at a position matching the user's region at a specific position detected through the depth image. .

Since the plurality of cameras 210a and 210b simultaneously photograph the user at almost the same position, it is possible to detect the user area through overlapping contours when the image is overlaid, and to detect the face area of the user at a specific location. Do.

The communication module 230 transmits an image of the face region detected according to a control signal of the processor 220 to the immigration server according to a preset period. When the processor 220 detects a face region of the user at a specific position, the processor 220 generates an image of the face region of the user. The control signal may be transmitted to the communication module 230 for image transmission. The communication module 230 may transmit the received image to the immigration server according to the control signal.

Meanwhile, as described with reference to FIG. 1, the facial authentication terminal 200 may include an IR sensor, and may drive the plurality of cameras 210a and 210b when a user is detected within a predetermined distance using the IR sensor. The plurality of cameras 210a and 210b may be different kinds of cameras, that is, one 3D depth camera and the other 2D camera. The face authentication terminal 200 may drive two kinds of cameras simultaneously to capture an image.

The processor 220 may assign a gate entry order to each user according to a plurality of user distance information. In one embodiment, the gate entry order may be given according to a position close to the gate. That is, the user at the nearest location can be assigned once, the next closest user twice, and the next closest user 3 times. The processor 220 may detect the face region for each user in the order given in this manner.

3 is a block diagram of a face authentication system using a plurality of cameras according to an embodiment of the disclosed technology. Referring to FIG. 3, the face authentication system 300 includes a face authentication terminal 200 and an immigration server 310.

The face authentication terminal 200 captures depth images and 2D images of a plurality of users who enter a gate within a predetermined distance using a plurality of different cameras 210a and 210b. In addition, the depth image and the 2D image are overlaid to detect distance information and face regions of the plurality of users and to detect a face region of the user at a specific position from the gate.

As described above with reference to FIG. 2, the face authentication terminal 200 captures depth images and 2D images of a plurality of users and overlays them to detect a face region of a user at a specific location. Since the face authentication terminal 200 has been described above with reference to FIGS. 1 and 2, it will be omitted.

Meanwhile, the immigration server 310 receives an image of a face region of a user at a specific location. The immigration server 310 may be associated with an airport immigration desk system and stores a plurality of user information.

Here, the user information means identification information for each user registered in advance by means such as a passport in order to automatically pass through the gate. For example, the image may include a face image extracted through a photograph of the passport, a name described in the passport, a social security number, and the like. The immigration server 310 includes a communication module 310a which communicates with the face authentication terminal to receive an image of the face area.

On the other hand, the immigration server 310 includes a database 310c for storing the plurality of user information. In addition, specific user information matching the image of the face region received from the terminal 200 may be searched using the database 310c. If specific user data matching the image of the face area is found, a control signal for opening / closing an entry / exit gate may be transmitted to the face authentication terminal 200. In order to perform such an operation, the immigration server 310 is provided with a processor 310b that can control the communication module 310a and the database 310c and perform a predetermined operation.

Meanwhile, referring back to FIG. 2, the face authentication terminal 200 may include a database 240 synchronized with the database 310c of the immigration server 310. In an embodiment, the facial authentication terminal 200 may search for specific user data matching the image of the face area in the database 240. That is, the image of the face area may be matched by itself without receiving the matching result through the server. Of course, if the terminal 200 performs its own image matching, the matching result may be transmitted so that the latest data may be stored in the database 310c of the immigration server 310. Therefore, the database 240 of the terminal 200 and the database 310c of the server 310 may be synchronized.

4 is a view showing an access authentication terminal provided in a gate. Referring to FIG. 4, the system may perform authentication using two face authentication terminals 401 and 402 provided in the gate 400. In an embodiment, the system may include a first terminal 401, a second terminal 402, and a server, and perform face authentication using at least one terminal.

The first terminal 401 and the second terminal 402 include the same configuration as the face authentication terminal 200 described above. However, there is a slight difference in the position of the gate. For example, the first terminal 401 may be disposed in front of the rotating gate 400 as shown in FIG. 4. The second terminal 402 may be disposed on the side of the gate 400.

In order to effectively operate the face authentication system and improve the accuracy of face authentication, the two terminals 401 and 402 may be divided into a main terminal and a sub terminal, respectively, and the result of performing the process for face authentication through the sub terminal and through the main terminal It is possible to compare the results of performing the process by face authentication.

As an example, if the image photographed by the first terminal 401 is called a first depth image and a first 2D image, and the image photographed by the second terminal 402 is called a second depth image and a second 2D image, Each terminal may detect the face region of the user at a specific position by overlaying the captured image according to the above-described process.

Meanwhile, the immigration server 310 searches for matching specific user information among pre-registered user information based on the image of the face area received from at least one of the two terminals. That is, the server 310 may search for specific user information by receiving an image of the face area from the first terminal 401 or search for specific user information by receiving an image of the face area from the second terminal 402.

In addition, both terminals may receive an image of the face region and may aggregate the same to search for specific user information. For example, by detecting similarity between the images of the face regions received from the two terminals, one of the face region images that can easily recognize the face may be selected. Alternatively, specific user information may be searched for using the resultant image obtained by overlaying the two images once again and calculating the average value.

5 is a diagram illustrating a depth image photographed using a 3D depth camera. Referring to FIG. 5, a plurality of users captured in the depth image are displayed in different colors. Herein, the color difference means distance information of the user. For example, the brighter the color, the closer it can be determined. Or the darker the color, the closer it can be seen.

In general, it may be recognized that a user with a large face photographed is located close, but according to the disclosed technology, it is determined which user is closer to the gate based on distance information without considering the size of the user area. Alternatively, it is determined which user is the user closest to a specific location where the user should be located in order to perform face authentication.

6 is a diagram illustrating a 2D image photographed using a 2D camera. Referring to FIG. 6, an image captured by the 2D camera includes a face of a user. That is, the terminal may extract the face image of each user based on the image photographed from the front or the side. The administrator of the system can determine the optimal point for the face authentication in consideration of the angle of view of the 2D camera as a specific position and display a mark so that the user can stand exactly at that position.

On the other hand, it is possible to determine which user is ahead of other users by using the contour extraction technique. However, in this method, when noise occurs during contour extraction, the accuracy of the result of distance determination is significantly lowered. Therefore, a depth image including distance information and a 2D image of each user's face region are superimposed so that the distance information of a specific user is overlapped. It is desirable to judge.

7 is a diagram illustrating overlaying a depth image and a front image. Referring to FIG. 7, it is possible to determine the entry order for each user's face image by overlaying two images. For example, an overlay may be performed by using a depth image having distance information as a base, specifying a region corresponding to a face among the images of the user captured in the image, and merging the face image extracted from the front image.

On the other hand, using the overlaid image, it is possible to specify which face image of a specific user is located at the first position of entering the gate among the face images processed for each user. For example, after merging the face images as described above, it is possible to determine who is the user having the shortest distance information or who is closest to the specific location, and transmit the face image of the user to the server.

Face authentication method using a plurality of cameras, a terminal and a system according to an embodiment of the disclosed technology has been described with reference to the embodiment shown in the drawings for clarity, but this is merely illustrative, and common knowledge in the art Those skilled in the art will appreciate that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical protection scope of the disclosed technology should be defined by the appended claims.

110: acquisition of distance information using depth image
120: specific location user area detection
130: user's face area detection
200: facial authentication terminal 210a, 210b: camera
220: processor 230: communication module
240: database 330: facial authentication system
310: immigration server 310a: communication module
310b: Processor 310c: Database

Claims (19)

Photographing, by a facial authentication terminal, a depth image of at least one user who has entered within a predetermined distance by using a 3D depth camera and obtaining distance information of the at least one user;
Detecting, by the face authentication terminal, an area of a user at a specific position from the face authentication terminal according to the distance information; And
The face authentication terminal captures a 2D image of the at least one user by using a 2D camera and overlays the depth image and the 2D image to a user at a position overlapping with an area of the user at the specific position. Detecting a face area for a face authentication method using a plurality of cameras comprising a. The method of claim 1,
The detecting of the face area may include extracting, by the face authentication terminal, an image of the detected face area and transmitting the extracted image to an immigration server. The method of claim 2,
The face authentication terminal includes a database for storing a plurality of face images synchronized with the immigration server and the face authentication method using a plurality of cameras to match the image of the detected face area with the plurality of face images. The method of claim 1,
The face authentication terminal includes an IR sensor, and if the user is not detected within the predetermined distance by using the IR sensor, the 3D depth camera and the 2D camera are placed in a sleep mode and when the user is detected, the 3D Face authentication method using a plurality of cameras to switch the depth camera and the 2D camera to the active mode (Active Mode). The method of claim 1,
The 3D depth camera captures a next depth image after a preset waiting time, and the 2D camera uses a plurality of cameras to capture a 2D image including a face area of another user who has entered the specific location after the waiting time. Facial authentication method. The method of claim 1,
When the plurality of users are photographed in the depth image, the face authentication terminal assigns an authentication order to each user according to the distance information, and detects a face area for each user. The method of claim 6,
The face authentication terminal extracts an image of a face area detected for each user and sequentially transfers the image of the face area to an immigration server according to the authentication sequence. A plurality of cameras for photographing depth images and face images of a plurality of users who have entered within a distance from which photographing is possible;
A processor for detecting a region of a user at a specific position among the plurality of users using the depth image and a face region at a position overlapping with the region of the user using the face image; And
And a communication module configured to transmit an image of the detected face region to an immigration server according to a control signal of the processor at a predetermined period. The method of claim 8,
The plurality of cameras face authentication terminal using a plurality of cameras including at least one 3D depth camera and a 2D camera. The method of claim 8,
The face authentication terminal includes an IR sensor, and the face authentication terminal using a plurality of cameras to drive the plurality of cameras when a user is detected within a predetermined distance by using the IR sensor. The method of claim 8,
The processor may provide a gate entry order for each user according to the plurality of user distance information, and detect a face region for each user. Using a plurality of different cameras to take a depth image and a 2D image of a plurality of users entering a gate within a certain distance, and overlay the depth image and the 2D image distance information and face for the plurality of users A face authentication terminal detecting a region and detecting a face region of a user at a specific position from the gate; And
An immigration server that receives an image of a face area of a user at the specific location and searches for specific user information that matches the image of the face area among a plurality of prestored user information; Authentication system. The method of claim 12,
The face authentication terminal is a face authentication system using a plurality of cameras to take the depth image using at least one 3D depth camera and to take the 2D image using at least one 2D camera. The method of claim 12,
The face authentication terminal includes an IR sensor, and the face authentication system using a plurality of cameras to drive the plurality of cameras when a user is detected within the predetermined distance using the IR sensor. The method of claim 12,
The immigration server includes a database storing the plurality of user data, and when a specific user data matching the image of the face area is found, the plurality of cameras transmits a control signal for opening and closing the gate to the face authentication terminal. Facial authentication system using. The method of claim 12,
The face authentication terminal includes a database synchronized with the immigration server, and uses the synchronized database to search for a specific user information matching the image for the face area using a plurality of cameras. The method of claim 12,
The face authentication terminal extracts an image of a face region detected for each of the plurality of users, assigns an authentication sequence to each face region image according to the distance information, and sequentially displays images of the face regions according to the authentication sequence. Face authentication system using a plurality of cameras to send to the server. A first depth image and a first 2D image of a plurality of users are photographed using a plurality of different cameras at a specific height in front of the gate, and the gate is formed using the first depth image and the first 2D image. A first terminal detecting a face area of a user at a specific position of the first terminal;
A second depth image and a second 2D image of the plurality of users are photographed using a camera provided on one side of the gate and the same type of camera as the plurality of different cameras, and the second depth image and the second depth image are captured. A second terminal detecting a face area of a user at the specific location by using a 2D image; And
Facial authentication using a plurality of cameras, including; an immigration server for searching for matching specific user information among the pre-registered user information based on the image of the face area received from at least one of the first terminal and the second terminal system. The method of claim 18,
The immigration server is a face authentication system using a plurality of cameras for detecting the similarity between the image of the face area received from the first terminal and the image of the face area received from the second terminal.

Images