KR102688435B1 - Visitor access security system based on user terminal information and facial recognition detection - Google Patents

Abstract

The present invention relates to a visitor access security system based on user terminal information and facial recognition detection, comprising: a facial recognition means for obtaining facial image information by scanning the face of a user wishing to enter; The face image information of the user who wishes to enter is received from the facial recognition means, and if the user is identified as an entry target, the decision is made to allow access. The user's social service login information entered in advance is received from the user, and the user's social service login information is received and uploaded to the social service. an image extraction unit that collects user image information; and a face reading unit that reads a plurality of user image information extracted from the image extraction unit and facial image information obtained from the face recognition means to determine whether the user is present; and A central control server configured to include; an authentication processing unit that transmits an authentication signal through authentication processing to allow access when the result read by the reading unit corresponds to the user subject to authentication; A user terminal that receives approval for membership registration through a membership registration process at the central control server and inputs login information so that user image information uploaded to the user's social service can be extracted from the image extractor; A social service server that provides user image information uploaded to a social service by the user to the central control server when connected through the user's login authentication from the central control server; And it is configured in a local where the door device is installed to receive the access permission authentication process from the central control server and control the operation of the door.

Description

Visitor access security system based on user terminal information and facial recognition detection}

The present invention relates to a visitor access security system based on user terminal information and facial recognition detection, and more specifically, to perform access authentication and security operation by matching facial recognition information with SNS image information of users entering various doors. This relates to a visitor access security system based on user terminal information and facial recognition detection.

Face recognition technology mainly uses appearance-based matching method and feature-based face recognition. Face recognition is recognized differently depending on the camera's shooting angle, direction of lighting, posture, changes in expression, and changes in the face over time.

Feature-based face recognition uses a detection method using Haar-like features and a detection method using MCT (Modified Census Transform) images from image data captured with a digital camera, IoT device camera, or smartphone camera. . Using a face and eye detector learned with Haar-like features from the input image of the smartphone camera, the outline of the face and forehead/eyes/nose/mouth are detected, and the region of interest (ROI) is used to detect circular pupils. The eye area set to Interest) is converted to grayscale, and the histogram of the eye image [pixel value of each pixel on the x-axis, After calculating the number of corresponding pixel values on the y-axis and binarizing the eye image, preprocessing of the photo of the eye area is performed through histogram equalization, and in the face area, eyebrows, eyes, nose, mouth, The face is recognized by detecting the face data of the facial features of the outline, extracting the texture features and shape features, and comparing the similarity with the feature points of the face photo stored in the face recognition DB.

The feature values of the eyebrows, eyes, nose, mouth, and chin in the face area are expressed as the difference between the sum of pixels included in the white area of the Haar-like feature and the sum of the pixels included in the black area.

However, despite the advancement of existing facial recognition technology, errors in facial recognition due to environmental changes such as the user's makeup technique, style connections, hair styling, and wearing of accessories still remain a challenge in the industry.

There is an emerging need to apply facial information that varies depending on changes in the user's environment or conditions to various industries through accurate facial recognition without error.

KR Registered Patent No. 10-1783713 KR Registered Patent No. 10-1668958 KR Registered Patent No. 10-2060247 KR Registered Patent No. 10-2312152 KR Registered Patent No. 10-2189405 KR Registered Patent No. 10-2261880 KR Registered Patent No. 10-2473697 KR Registered Patent No. 10-2207071 KR Public Patent No. 10-2020-0116138

In order to solve the above problems, the present invention provides an access security system that determines whether or not to grant access through facial recognition. The present invention collects and compares and analyzes the user's image information (face information) in real time to determine the image change value in real time. The purpose is to provide a visitor access security system based on facial recognition detection with excellent security that prevents errors in access control by improving the accuracy of reading and determining correct access approval.

The present invention for achieving the above object includes: facial recognition means for obtaining facial image information by scanning the face of a user wishing to enter; The face image information of the user who wishes to enter is received from the facial recognition means, and if the user is identified as an entry target, the decision is made to allow access. The user's social service login information entered in advance is received from the user, and the user's social service login information is received and uploaded to the social service. an image extraction unit that collects user image information; and a face reading unit that reads a plurality of user image information extracted from the image extraction unit and facial image information obtained from the face recognition means to determine whether the user is present; and A central control server configured to include; an authentication processing unit that transmits an authentication signal through authentication processing to allow access when the result read by the reading unit corresponds to the user subject to authentication; A user terminal that receives approval for membership registration through a membership registration process at the central control server and inputs login information so that user image information uploaded to the user's social service can be extracted from the image extractor; A social service server that provides user image information uploaded to a social service by the user to the central control server when connected through the user's login authentication from the central control server; And it is configured in a local where the door device is installed to receive the access permission authentication process from the central control server and control the operation of the door.

In addition, the central control server receives and stores the user's social service login information from the user terminal, and connects to the social service server through the login information when the user's facial recognition is scanned from the facial recognition means and requests approval. and a login information collection unit for collecting the user's image information, wherein the login information collection unit includes all of a plurality of social service login information input through the user terminal.

In addition, the user terminal further includes an information input unit for inputting the user's login information corresponding to social service login information, and an image upload unit for directly uploading the user's recent face photo to the central control server.

The present invention, constructed and operated as described above, collects and compares and analyzes in real time the user's image information (face information) that is frequently uploaded to a social network service (SNS) in an access security system that determines whether or not to grant access through facial recognition. This has the effect of reading the image change value in real time and determining whether or not to accurately grant access.

Accordingly, by improving the accuracy of facial recognition, errors do not occur in access control, and as a result, it is possible to provide a visitor access security system based on facial recognition detection with excellent security.

In particular, the present invention is very effective because it reads the user's facial recognition information based on image information from a social service where image information that changes in real time due to various environments or the user's face, style, makeup techniques, wearing accessories, etc. is uploaded from time to time. There is an advantage in providing facial recognition functions through accurate recognition information.

1 is an overall configuration diagram of a visitor access security system based on user terminal information and facial recognition detection according to the present invention;
Figure 2 is a detailed configuration diagram of the central control server in the visitor access security system based on user terminal information and facial recognition detection according to the present invention;
Figure 3 is an example diagram showing the configuration of a plurality of social service servers in the visitor access security system based on user terminal information and facial recognition detection according to the present invention;
Figure 4 is an example diagram showing the configuration of collecting user images from a plurality of social service servers in a visitor access security system based on user terminal information and facial recognition detection according to the present invention.

Hereinafter, a visitor access security system based on user terminal information and facial recognition detection according to the present invention will be described in detail with reference to the attached drawings.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, properties, procedures, Includes subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. In addition, the components and 'parts' may be implemented to regenerate one or more CPUs within the device or secure multimedia card.

The “terminal” mentioned below may be implemented as a computer or portable terminal that can connect to a server or other terminal through a network. Here, the computer is, for example, a laptop equipped with a web browser, a desktop, a laptop, a VR HMD (e.g., HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.), etc. may include.

Here, the VR HMD is for PC (e.g. HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), mobile (e.g. GearVR, DayDream, Storm Magic, Google Cardboard, etc.), and console (PSVR). Includes independently implemented Stand Alone models (e.g. Deepon, PICO, etc.). Portable terminals are, for example, wireless communication devices that ensure portability and mobility, and include not only smartphones, tablet PCs, and wearable devices, but also Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, ultrasonic, It may include various devices equipped with communication modules such as infrared, WiFi, and LiFi.

In addition, "network" refers to a connection structure that allows information exchange between nodes such as terminals and servers, including a local area network (LAN), a wide area network (WAN), and the Internet. (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, and ultrasound. This includes, but is not limited to, communication, Visible Light Communication (VLC), LiFi, etc.

A visitor access security system based on user terminal information and facial recognition detection according to the present invention includes: facial recognition means for obtaining facial image information by scanning the face of a user wishing to enter; The face image information of the user who wishes to enter is received from the facial recognition means, and if the user is identified as an entry target, the decision is made to allow access. The user's social service login information entered in advance is received from the user, and the user's social service login information is received and uploaded to the social service. an image extraction unit that collects user image information; and a face reading unit that reads a plurality of user image information extracted from the image extraction unit and facial image information obtained from the face recognition means to determine whether the user is present; and A central control server configured to include; an authentication processing unit that transmits an authentication signal through authentication processing to allow access when the result read by the reading unit corresponds to the user subject to authentication; A user terminal that receives approval for membership registration through a membership registration process at the central control server and inputs login information so that user image information uploaded to the user's social service can be extracted from the image extractor; A social service server that provides user image information uploaded to a social service by the user to the central control server when connected through the user's login authentication from the central control server; And it is configured in a local where the door device is installed to receive the access permission authentication process from the central control server and control the operation of the door.

The visitor access security system based on user terminal information and facial recognition detection according to the present invention improves the accuracy of user's facial recognition in configuring an access system that approves entry or exit of a visitor (user) through facial recognition information. To achieve this, we extract image information from the user's social network service (hereinafter referred to as 'novel service') that can most accurately obtain the user's real-time or recent facial information (image information) and perform facial recognition of the user based on this. It has main technical features.

Figure 1 is an overall configuration diagram of a visitor access security system based on user terminal information and facial recognition detection according to the present invention.

The present invention broadly provides a facial recognition means (100) for scanning the user's face in a form that is installed at a specific location or portable by a security manager and receives the user's face information scanned from the facial recognition means to allow access to the subject. A central control server 200 that determines access approval after reading the access information, and a user terminal 300 and the user, which is a terminal carried by the user, providing login information for a social service or uploading his/her image information. The social service server 400 uploads the image information uploaded from the terminal on a social network and provides the user's image information upon request from the central control server 200, and receives an access approval signal from the central control server 200 to provide on-site access. It is configured to include a local control device 500 that controls the opening and closing of the door 600 installed in.

The face recognition means 100 may be configured in various structures such as a fixed type, a stand type, or a portable type. Basically, the face recognition means 100 uses a camera unit and an image with a specific resolution value to scan the face of the person entering the room. It can be configured to include a memory unit that can store data, a communication module that can communicate with an external system, and a power unit depending on the power supply.

The example in FIG. 1 shows a portable type facial recognition device 100. In the case of the portable type, an access security officer can carry the device and scan the face of the user requesting access to confirm whether the device is subject to access. At this time, of course, it can have a sound output function so that security personnel can easily recognize it by outputting a confirmation sound or a warning sound depending on whether access is approved after scanning through facial recognition means.

Accordingly, the facial recognition means 100 acquires facial image information by scanning the face of the user seeking entry, and provides the obtained image information to the central control server 200 to determine whether or not to approve entry.

The central control server 200 determines whether or not access is permitted based on the image information received from the facial recognition means 100 and provides the information. At this time, the central control server 200 stores image information of the first user, extracts and reads image information from social services in real time in addition to the stored images, and determines whether to allow access based on the facial recognition results. Accordingly, when facial image information of a user seeking entry is received from the facial recognition means 100 and the user is identified as an entry target, it is decided to allow entry.

Accordingly, the central control server is configured to collect user image information from social services and includes a login information collection unit, an image extraction unit, an image reading unit, and an authentication processing unit, which will be explained in detail in FIG. 2 below. do.

The user terminal 300 registers as a member through an initial membership registration process at the central control server 200 and initially uploads its own image information.

In addition, according to the main technical feature of the present invention, the user terminal 300 inputs and provides social service login information so that user image information uploaded to the user's social service can be collected in real time from the central control server.

Therefore, by providing login information, the central control server 200 can collect the user's image information uploaded to the social service in real time.

The social service server 400 provides a social network service used by users. In order to use the social network service, the user accesses the service in the form of a web or app and uploads daily photo or video information. The uploaded photo or video information may be an image corresponding to the user's face or another image, and the central control server 200 extracts the user's face information only from the image or video information corresponding to the user's face.

The local control device 500 is composed of a piece of hardware that controls the opening and closing of the door 500 when the visitor is approved for entry. It receives approval information through a communication module and controls the opening and closing of the door 500.

Figure 2 is a detailed configuration diagram of the central control server in the visitor access security system based on user terminal information and facial recognition detection according to the present invention.

The central control server 200 according to the present invention largely includes a login information collection unit 210, an image extraction unit 220 for extracting the user's image information from a social service, a face reading unit 230 for determining whether the user is present, It is configured to include an authentication processing unit 240 that determines access approval according to the reading result.

The login information collection unit 210 receives and stores the user's social service login information from the user terminal 100, and logs in to the social service server when the user's facial recognition is scanned from the facial recognition means and requests approval. The user's image information is collected by accessing the information.

At this time, the user's image information uploaded in various ways on the social service is extracted by the image extraction unit 220, and even if the uploaded content is in the form of an image or video, only the user's face image is extracted to extract user information. .

Accordingly, the user's pre-entered social service login information is received from the user, and the image extractor 220 extracts a plurality of user image information uploaded to the social service.

Next, the plurality of user image information extracted from the image extraction unit 220 and the facial image information obtained from the facial recognition means are read and extracted by the face reading unit 230, which determines whether the user is a user. The face reading unit 230 extracts the user's image information through deep learning or artificial intelligence model, and compares and determines the image information input to the facial recognition means 100 and a plurality of images extracted from the image extraction unit. By doing so, it is possible to accurately read in response to the constantly changing values of the user's face.

Finally, if the result read by the face reading unit 230 corresponds to the user subject to authentication, it is processed through the authentication processing unit 240, which transmits an authentication signal through authentication processing to allow access.

Meanwhile, the user terminal 300 includes an information input unit 310 to provide social service login information to the central control server 200, and social service login information is input and provided through the information input unit.

In addition, the user terminal 300 includes an image upload unit 320, which directly uploads photos of the user's recent changes to the central control server 200. At this time, when the user directly uploads a recent photo to improve the accuracy of facial recognition, the central control server 200 may provide points in the form of a cache according to the image upload, and points to encourage active participation of the user. may be paid or separate compensation may be provided, and a portion of the advertising proceeds generated through advertisements provided by the central control server may be paid as points.

Meanwhile, the central control server 200 may also extract location information or text information posted on the social service during the process of extracting the image from the social service server 400. For example, if the recent location information indicates overseas, and the location information is different when requesting door approval based on this, it can be judged as suspicious information and a request for re-approval can be made. The user's location can also be requested through text-based extracted information values. It can be read by applying it to access approval through information or status information. It is possible to extract location information or user activity information from text information and read whether the user is subject to a request for approval at the location of the door where the facial recognition device is installed.

Figure 3 is an exemplary diagram showing the configuration of a plurality of social service servers in the visitor access security system based on user terminal information and facial recognition detection according to the present invention.

As shown, there are various known social services, and the user can provide all login information corresponding to each social service to the central control server 200 as needed.

At this time, the central control server 200 can collect user image information uploaded to multiple social service servers A to D in real time and use it for facial recognition, thereby significantly improving accuracy and minimizing the occurrence of errors. There is an advantage.

Figure 4 is an exemplary diagram showing the configuration of collecting user images from a plurality of social service servers in a visitor access security system based on user terminal information and facial recognition detection according to the present invention.

As shown, the image extraction unit 220 configured in the central control server 200 collects only the photos necessary for facial recognition from the images (photos) uploaded by the user to the social service, and through this, the user's image changes from time to time. The accuracy of facial recognition can be improved by extracting information.

The present invention, constructed in this way, collects and compares and analyzes in real time the user's image information (face information) that is frequently uploaded to a social network service (SNS) in an access security system that determines whether or not to grant access through facial recognition, and provides an image change value. It has the effect of being able to read in real time and accurately determine whether or not to grant access.

Accordingly, by improving the accuracy of facial recognition, errors do not occur in access control, and as a result, it is possible to provide a visitor access security system based on facial recognition detection with excellent security.

In particular, the present invention is very effective because it reads the user's facial recognition information based on image information from a social service where image information that changes in real time due to various environments or the user's face, style, makeup techniques, wearing accessories, etc. is uploaded from time to time. There is an advantage in providing facial recognition functions through accurate recognition information.

Although the present invention has been described and illustrated in connection with preferred embodiments for illustrating the principles of the present invention, the present invention is not limited to the construction and operation as so shown and described. Rather, those skilled in the art will appreciate that many changes and modifications can be made to the present invention without departing from the spirit and scope of the appended claims. Accordingly, all such appropriate changes, modifications and equivalents shall be considered to fall within the scope of the present invention.

100: facial recognition means
200: Central control server
210: Login information collection unit
220: image extraction unit
230: face reading unit
240: Authentication processing unit
300: user terminal
310: information input unit
320: Image upload unit
400: Social service (SNS) server
500: local control device
600: Entrance door

Claims (3)

Facial recognition means for obtaining facial image information by scanning the face of a user wishing to enter;
The face image information of the user who wishes to enter is received from the facial recognition means, and if the user is identified as an entry target, the decision is made to allow access. The user's social service login information entered in advance is received from the user, and the user's social service login information is received and uploaded to the social service. an image extraction unit that collects user image information; and a face reading unit that reads a plurality of user image information extracted from the image extraction unit and facial image information obtained from the face recognition means to determine whether the user is present; and A central control server comprising: an authentication processing unit that transmits an authentication signal through authentication processing to allow access when the result read by the reading unit corresponds to the user subject to authentication;
A user terminal that receives approval to join as a member through a member registration process at the central control server and inputs login information so that user image information uploaded to the user's social service can be extracted from the image extractor;
A social service server that provides user image information uploaded to a social service by the user to the central control server when connected through the user's login authentication from the central control server; and
It is configured to include; a local control device configured locally where the door device is installed to receive the access permission authentication process from the central control server and control the operation of the door,
The central control server,
Receiving and storing the user's social service login information from the user terminal, and collecting the user's image information by accessing the social service server through the login information when the user's facial recognition is scanned by the facial recognition means and requesting approval. Consisting of a login information collection unit for
The login information collection unit includes all of the plurality of social service login information input through the user terminal,
The user terminal is,
an information input unit for entering user login information corresponding to social service login information;
It further includes an image upload unit for uploading the user's recent face photo directly to the central control server,
In the process of extracting the user's image from the social service server, the central control server also extracts location information or text information posted on the social service, and when the latest location information indicates overseas, location information is provided when requesting door approval based on this. If the information is different, it can be judged as suspicious information and a re-approval request can be made. It can also be read by applying to access approval through the user's location information or status information through text-based extracted information values. A visitor access security system based on user terminal information and facial recognition detection that extracts location information or user activity information and reads whether the user is subject to an approval request at the door location where the facial recognition means is installed. delete delete