KR20220006995A - Non-face-to-face personal authentication customer verification device and method - Google Patents

Abstract

Disclosed are an apparatus and method for non-face-to-face identity authentication customer verification based on artificial intelligence facial recognition using real-time ID photos and selfie photos. Non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention includes: an ID card photographing control unit that provides an ID card photographing interface for photographing an identification card to a terminal of a customer who needs self-authentication customer verification; a selfie-taking control unit that provides a selfie-taking interface for photographing a face to a customer's terminal requiring self-authentication; and when a selfie photo is generated by the customer taking a face using the terminal through the selfie shooting interface, the self-image is compared with the face image of the ID copy by artificial intelligence to calculate the degree of matching, and based on the calculated degree of matching It includes an authentication unit that determines forgery or falsification of the ID copy taken through the ID card photographing interface, and performs identity authentication according to the match calculated by artificial intelligence and the ID copy copy forgery or falsification determination result.

Description

Non-face-to-face personal authentication customer verification device and method

The present invention relates to a non-face-to-face identity authentication customer confirmation device and method, and more particularly, to a non-face-to-face identity authentication customer confirmation service based on artificial intelligence facial recognition using real-time photographed ID photos and real-time selfie photos It relates to a non-face-to-face identity authentication customer verification device and method for providing

In general, financial-related companies such as banks, securities companies, insurance companies, and fintech-related companies perform face-to-face personal authentication to verify the identity of customers who have requested financial services. However, this face-to-face authentication method is inconvenient for customers to visit a financial-related company, and there is a problem in that it is not possible to use the financial service procedure outside the business hours of the financial-related company.

In addition, the face-to-face identity authentication method has a problem in that the burden of customer confirmation tasks for financial companies is increased. In addition, the face-to-face authentication method becomes a factor in spreading infectious diseases when an infectious disease such as a virus is prevalent, and this has a limit in which customers are reluctant to visit.

For this reason, recently, a non-face-to-face authentication method has been in the spotlight. 1 and 2 are conceptual views illustrating a conventional non-face-to-face user authentication method. Conventional non-face-to-face authentication methods include: 1) taking a copy of the real name verification card or ID card, 2) comparing the ID card with the photo through a video call with the customer, 3) checking when delivering the access medium (delivery of cash card, security card, OTP) The identity of the customer is verified through two or more authentication requirements among various authentication requirements, including , 4) using an existing account (one-way authentication), 5) certificates from other organizations and other similar methods.

Such a conventional non-face-to-face authentication method requires a video call with a customer, a cash card, security card, or OTP delivery, checking the deposit details in an existing account and entering a password to perform one-way authentication, or a certificate from another institution The procedure for opening a customer's account is complicated, such as having to prepare

In addition, the conventional non-face-to-face personal authentication method has a problem in that the verification accuracy of identification is lower than that of the face-to-face method, and customers who are reluctant to expose unnecessary personal information beyond the information required for identification have to cover the back digit of their resident number with a memo pad, etc. there is rom In addition, in the conventional non-face-to-face authentication method, it is difficult to secure the real-time of the photo submitted by the customer, and when the customer tries to use financial services unfairly by forgery or falsification of the ID, it is difficult to detect it compared to the face-to-face method.

The present invention is based on optical character recognition technology (OCR), motion detection (Motion Detection), face recognition using artificial intelligence, and face matching (Face Matching) technology. An object of the present invention is to provide a non-face-to-face identity authentication customer confirmation device and method that can perform identity authentication simply and accurately based on a selfie photo taken with a face.

In addition, the present invention can prevent false self-authentication using another person's photo or video, simplify the customer's non-face-to-face account opening step, and replace the video call authentication means to enable 24-hour service use To provide a non-face-to-face personal authentication customer verification device and method that can increase customer convenience, reduce service costs used for one-way authentication, and enable simple identity authentication for foreigners and youth without an account it is for

In addition, the present invention provides a method in which a malicious user obtains another person's ID card and modifies the photo of the ID card into his/her own photo and performs authentication, or a malicious user modifies his/her ID information into someone else's information to perform authentication This is to provide a non-face-to-face identity authentication customer verification device and method that can prevent fraudulent authentication by judging various types of identification forgery and forgery.

Non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention includes: an ID card photographing control unit that provides an ID card photographing interface for photographing an identification card to a terminal of a customer who needs self-authentication customer verification; a selfie-taking control unit that provides a selfie-taking interface for photographing a face to a customer's terminal requiring self-authentication; and when a selfie photo is generated by the customer taking a face using the terminal through the selfie shooting interface, the self-image is compared with the face image of the ID copy by artificial intelligence to calculate the degree of matching, and based on the calculated degree of matching It includes an authentication unit that determines forgery or falsification of the ID copy taken through the ID card photographing interface, and performs identity authentication according to the match calculated by artificial intelligence and the ID copy copy forgery or falsification determination result.

The ID photographing control unit: displays an identification guide object in a rectangular shape corresponding to the identification selected by the customer on the image on the screen of the customer terminal in the identification photographing mode, and when the identification is matched with the identification guide object, the customer clicks the photographing button can be manipulated to determine whether an ID is being photographed, and a copy image of the ID can be created.

The non-face-to-face identity authentication customer confirmation device according to an embodiment of the present invention: performs super resolution processing to adjust the resolution of the ID copy image, and optically recognizes the super-resolution processed ID copy to process personal information It may further include an identification forgery determination unit that checks, creates a copy of the personal information-protected identification card by masking one or more personal information items set for each identification card, and stores it in the customer server.

The selfie taking control unit may provide a face guide object corresponding to the customer's face, determine whether a photographing button is operated in a state where the customer's face is located in the face guide object, and obtain a selfie photo of the customer.

The authenticator extracts feature points from the face images of the selfie photo and the copy of the ID card by an artificial intelligence model, respectively, and compares the corresponding feature points to calculate the face matching between the photo of the ID and the selfie photo of the customer.

The authentication unit: extracts first feature points from the face image of the copy of the ID photographed through the ID photographing interface, receives second feature points extracted from the face image of the copy of the ID of the customer stored in the financial database, from the financial database, a first matching degree calculator for calculating a first degree of matching based on a matching rate between the first feature points extracted from the face image of the copy of the ID card photographed in real time and the second feature points received from the financial database; The third feature points are extracted from the face image of the selfie photo taken by the customer in real time through the selfie shooting interface, the first feature points extracted from the face image of the ID copy taken by the customer in real time, and the selfie photo taken by the customer in real time a second degree of agreement calculator that calculates a second degree of agreement based on the matching rate of the third feature points extracted from the face image of ; a degree of agreement comparison unit comparing the first degree of agreement with the second degree of agreement; and a forgery determination unit for determining forgery or falsification of an identification card based on a comparison result of the first degree of agreement with the second degree of agreement.

The forgery determination unit: if the first degree of matching is equal to or greater than the second degree of matching, it is determined that the copy of the ID photographed through the ID photographing interface is a copy of a normal ID that has not been forged or falsified; In addition, if the first degree of matching is less than the second degree of matching, it may be determined that the copy of the ID photographed through the ID photographing interface is a forged or forged copy of the abnormal ID.

The non-face-to-face identity authentication customer confirmation device according to an embodiment of the present invention includes: a first time point when a selfie picture is taken for the front of the customer's face by a customer, and a second time point when a selfie picture is taken for the customer's face side Detects the customer's facial movement, and when the customer's facial movement is detected, may further include a motion detector for determining that the selfie photo was taken by the actual customer, not a pre-prepared photo or video.

The motion detection unit may include: a light output control unit that executes a light output control process for changing the light output from the customer terminal from the first light output state to the second light output state while the customer moves the face; a first brightness distribution calculator configured to calculate a first brightness distribution by calculating a first brightness for each face region of a first selfie photo taken in the first light output state; a second brightness distribution calculator configured to calculate a second brightness distribution by calculating a second brightness for each face region of a second selfie picture taken in the second light output state; a brightness change analyzer for analyzing a brightness change for each face region of a customer based on the first brightness distribution and the second brightness distribution; and a fraudulent action determination unit configured to determine a fraudulent act in which the user attempts to pass motion detection authentication by executing a video through another terminal based on the brightness change analyzed for each face region of the customer.

The identification forgery determination unit may include: a first sharpness pattern detection unit configured to detect a first sharpness pattern in a first area corresponding to a face image area of a copy of the ID card photographed in real time; a second sharpness pattern detection unit configured to detect a second sharpness pattern in a second region that does not correspond to the face image region of the real-time photographed ID copy; and a counterfeit photo determining unit that compares the first sharpness pattern with the second sharpness pattern to determine whether a photo of a copy of the ID card photographed in real time is forged.

The identification forgery determination unit includes: a hologram area detection unit that detects a hologram area corresponding to a hologram from a face image of a copy of an ID photographed in real time; a light reflection area detection unit that detects a light reflection area generated by light reflection in the face image of a copy of the ID card photographed in real time; a first image processing unit for performing first image processing for reducing the holographic information corresponding to the hologram and the light reflection information corresponding to the light reflection with respect to the hologram area and the light reflection area; and a second image processing unit that performs second image processing corresponding to super resolution processing on the face image of the copy of the ID card on which the first image processing has been performed.

The non-face-to-face identity authentication customer confirmation method according to an embodiment of the present invention comprises: providing, by an identity card photographing control unit, an identity card photographing interface for photographing an identity card to a terminal of a customer requiring identity authentication customer confirmation; providing, by the selfie-taking controller, a selfie-taking interface for photographing a face to a terminal of a customer who needs self-authentication customer confirmation; Comparing, by the authenticator, the face image of the selfie photo and the ID copy by artificial intelligence, calculating a degree of agreement; determining, by the authenticator, forgery or falsification of a copy of an ID photographed through an ID photographing interface based on the degree of matching; and performing, by the authenticator, the identity authentication according to the match calculated by the artificial intelligence and the forgery/falsification determination result of the ID copy.

The step of determining forgery or falsification of the ID copy may include: extracting first feature points from the face image of the ID copy photographed through the ID photographing interface by a first coincidence calculation unit, and a copy of the ID card of the customer stored in the financial database The second feature points extracted from the face image of 1 calculating a degree of agreement; By the second coincidence calculator, third feature points are extracted from the face image of the selfie photo taken by the customer in real time through the selfie shooting interface, and the first feature points extracted from the face image of the ID copy taken by the customer in real time and , calculating a second degree of matching based on a matching rate of third feature points extracted from a face image of a selfie taken by a customer in real time; comparing the first degree of agreement with the second degree of agreement by a degree of agreement comparison unit; and determining, by the forgery determination unit, forgery or falsification of the identification card based on a comparison result of the first degree of agreement and the second degree of agreement.

The non-face-to-face identity authentication customer confirmation method according to an embodiment of the present invention includes: by the motion detection unit, a first point in time when a selfie photo is taken for the front of the customer's face, and a selfie photo for the customer's face side The method may further include detecting the customer's facial movement between the second time points in which the customer's facial movement is detected, and determining that the selfie photo was taken by the actual customer rather than a pre-prepared photo or video.

The step of determining forgery or falsification of the ID copy may include: detecting, by a first sharpness pattern detection unit, a first sharpness pattern in a first area corresponding to a face image area of the ID copy photographed in real time; detecting, by the second sharpness pattern detection unit, a second sharpness pattern for a second area that does not correspond to the face image area of the real-time photographed ID copy; and comparing the first sharpness pattern with the second sharpness pattern, by the forged photo determining unit, to determine whether or not a photo of a copy of the ID card photographed in real time is forged.

The step of determining forgery or falsification of the ID copy may include: detecting, by a hologram zone detection unit, a hologram zone corresponding to a hologram in a face image of the ID copy photographed in real time; detecting, by a light reflection area detection unit, a light reflection area generated by light reflection in a face image of a copy of an ID photographed in real time; performing, by a first image processing unit, first image processing for reducing holographic information corresponding to the hologram and light reflection information corresponding to the light reflection with respect to the hologram area and the light reflection area; and performing, by a second image processing unit, a second image processing corresponding to super resolution processing on the face image of the copy of the ID card on which the first image processing has been performed.

According to an embodiment of the present invention, there is provided a computer-readable recording medium in which a program for executing the non-face-to-face user authentication method is recorded.

According to an embodiment of the present invention, based on optical character recognition technology (OCR), motion detection (Motion Detection), face recognition using artificial intelligence, and face matching (Face Matching) technology, a customer can obtain an identification card in real time A non-face-to-face identity authentication customer verification device and method are provided that can perform simple and accurate self-authentication based on a photo taken of a person and a selfie photo of a face.

In addition, according to an embodiment of the present invention, it is possible to prevent false identity authentication using another person's photo or video, simplify the customer's non-face-to-face account opening step, and replace the video call authentication means. Non-face-to-face personal authentication customer verification device that can be used 24 hours a day to increase customer convenience, reduce the service cost used for one-won authentication, and provide easy identification for foreigners and teenagers who do not have an account The method is provided.

In addition, according to an embodiment of the present invention, a malicious user obtains another person's ID card and modifies the photo of the ID card into his/her own photo and performs authentication, or a malicious user modifies his/her ID information into another person's information A non-face-to-face identity authentication customer verification device and method are provided that can prevent fraudulent authentication by judging various types of identification forgery and falsification, such as performing authentication.

1 and 2 are conceptual views illustrating a conventional non-face-to-face user authentication method.
3 and 4 are block diagrams of a non-face-to-face personal authentication customer confirmation system according to various application examples of the present invention.
5 is a flowchart illustrating a process of performing non-face-to-face personal authentication according to the non-face-to-face identity authentication customer confirmation method according to an embodiment of the present invention.
6 is a block diagram of a non-face-to-face personal authentication customer confirmation device according to an embodiment of the present invention.
7 is a flowchart of a non-face-to-face personal authentication customer confirmation method according to an embodiment of the present invention.
8 to 11 are exemplary screen views of a customer terminal for explaining a method of providing an identification card photographing interface for photographing an identification card to the customer's terminal according to step S110 of FIG. 7 .
12 is an exemplary diagram for explaining step S140 of FIG. 7 .
13 is an exemplary diagram for explaining step S180 of FIG. 7 .
14 and 15 are exemplary views for explaining step S150 of FIG. 7 .
16 is an exemplary view of a manager screen of a manager terminal that manages non-face-to-face personal authentication customer identification information according to an embodiment of the present invention.
17 is a configuration diagram of an authentication unit constituting a non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention.
18 is an exemplary flowchart of steps S160 and S170 of FIG. 7 .
19 is a block diagram of an identification card forgery determination unit constituting a non-face-to-face personal authentication customer confirmation device according to an embodiment of the present invention.
20 is a flowchart according to an example of step S120 of FIG. 7 .
21 is an exemplary diagram for explaining the embodiment of FIG. 20 .
22 is an exemplary diagram illustrating a change in pixel values of a photo boundary portion of a normal ID.
23 is an exemplary diagram illustrating a change in pixel values of a photo boundary portion of an identification card to which a forged photo is attached.
24 is a block diagram of an identification card forgery determination unit constituting a non-face-to-face personal authentication customer confirmation device according to another embodiment of the present invention.
25 is a flowchart according to another example of step S120 of FIG. 7 .
26 and 27 are exemplary views for explaining the embodiment of FIG. 25 .
28 is a block diagram of a motion detection unit constituting a non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention.
29 is an exemplary flowchart of step S150 of FIG. 7 .
30 is an exemplary diagram for explaining the embodiment according to FIG. 29 .

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

In the present specification, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. As used herein, '~ unit, ~ module' is a unit that processes at least one function or operation, and may refer to, for example, software, FPGA, or hardware component. The functions provided by '~ unit, ~ module' may be performed separately by a plurality of components, or may be integrated with other additional components. 'Part, ~ module' in this specification is not necessarily limited to software or hardware, and may be configured to be in an addressable storage medium, or may be configured to reproduce one or more processors. Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

The non-face-to-face identity authentication customer confirmation apparatus and method according to an embodiment of the present invention may be utilized, for example, in a non-face-to-face identity authentication customer confirmation (KYC; Know Your Customer) solution for financial services. Non-face-to-face identity authentication customer confirmation device and method according to an embodiment of the present invention is optical character recognition technology (OCR), motion detection (Motion Detection), face recognition using artificial intelligence (Face Recognition) and face matching (Face Matching) Based on technology, a customer verification solution for non-face-to-face identity authentication based on real-time ID photos and selfie photos by simply and accurately performing identity authentication based on a photo of a customer taking an ID photo and a selfie photo of their face in real time can provide

Non-face-to-face identity authentication customer verification device and method according to an embodiment of the present invention, for example, use of an app service of a fintech company, opening an electronic wallet of a block chain exchange, opening an online banking account of a bank, and a securities trading app account of a securities company It can be used for non-face-to-face customer verification for financial services such as opening and online insurance application for insurance companies.

3 and 4 are block diagrams of a non-face-to-face personal authentication customer confirmation system according to various application examples of the present invention. 3 and 4, the non-face-to-face identity authentication customer confirmation device and method according to an embodiment of the present invention is, for example, an API (Application Program Interface) server 10 that provides a non-face-to-face identity authentication customer confirmation service can be performed by

Non-face-to-face identity authentication customer confirmation device and method according to an embodiment of the present invention is provided as an API type service through the authentication app 20, as shown in FIG. 3, or as shown in FIG. 4, the customer app ( Based on the authentication module 20' integrated in 40), it may be provided as a service in the form of an internal solution to the customer.

After confirming the non-face-to-face self-authentication customer, the ID and customer face photo (selfie photo) taken by the customer for self-authentication are stored in the customer DB 50 through the customer server 30, and the API server 10 is ID photo materials and face photos (selfie photos) taken may be discarded. Therefore, since the customer's personal information is not stored in the API server 10 other than the customer DB 50, leakage of the customer's personal information can be prevented.

5 is a flowchart illustrating a process of performing non-face-to-face personal authentication according to the non-face-to-face identity authentication customer confirmation method according to an embodiment of the present invention. 6 is a block diagram of a non-face-to-face personal authentication customer confirmation device according to an embodiment of the present invention. 7 is a flowchart of a non-face-to-face personal authentication customer confirmation method according to an embodiment of the present invention.

5 to 7 , the non-face-to-face identity authentication customer verification method according to an embodiment of the present invention includes the steps of: the customer taking a copy of the ID card in real time (S10), the customer taking a real-time face to create a selfie picture (S20), a step (S30) of providing financial services such as account opening through simple non-face-to-face personal authentication customer confirmation using a copy of an ID and a selfie taken in real time (S30).

The non-face-to-face identity authentication customer confirmation device 100 according to an embodiment of the present invention includes an identification card photographing control unit 110, an identification card forgery determination unit 120, a selfie photographing control unit 130, a motion detection unit 140, an authentication unit ( 150 ) and an authentication result providing unit 160 .

The identification card photographing control unit 110 provides an identification photographing interface for photographing an identification card to the terminal of the customer who needs to verify the identity of the customer (S110). The identification card photographing control unit 110 may display the identification guide object in the form of a rectangle corresponding to the identification selected by the customer on the image of the screen of the customer terminal in the identification photographing mode. The identification card photographing control unit 110 may generate an identification copy image by determining whether the customer operates the photographing button to photograph the identification card in a state in which the identification card matches the identification guide object.

8 to 11 are exemplary screen views of a customer terminal for explaining a method of providing an identification card photographing interface for photographing an identification card to the customer's terminal according to step S110 of FIG. 7 . The identification card photographing control unit 110 may include a cropping function for automatically photographing only a portion of the identification card, an optical character recognition technology (OCR), a function to automatically cover sensitive personal information, and a function to check the authenticity of the identification card. .

The user can automatically enter ID information by simply taking an ID card such as a resident registration card, driver's license, or passport (foreigner) with a mobile phone through the simple ID copy submission app service using the function of the ID card shooting control unit. When the customer runs the app on the customer's terminal to use the financial service, as shown in FIG. 8, a guidance screen will be generated on the screen of the customer's terminal so that the customer prepares an identification card such as a resident registration card or driver's license for non-face-to-face authentication. can

The ID card capture interface provides a selection screen for the customer to select an identification card (eg, resident registration card, driver's license, passport, etc.) along with a guide screen, and allows the customer to take a picture of the identification card in real time by the camera of the customer terminal after the ID card selected by the customer is prepared. It may include a shooting start item. For example, when a customer selects (for example, a touch input) "taking ID card" on the terminal screen shown in FIG. 8, the camera of the customer terminal is activated, and as shown in FIG. It automatically switches to ID photo shooting mode.

In the ID card photographing mode, the ID guide object G01 is displayed in the form of a rectangle corresponding to the ID selected by the customer on the image on the screen of the customer terminal. When the customer operates the shooting button to photograph the ID while the ID is aligned with the ID guide object (G01) by adjusting the distance and camera direction between the camera and the ID card of the customer terminal so that the customer matches the ID guide object (G01) , a copy image of the ID is created.

When a customer takes a photo of an ID card using a terminal through the ID card shooting interface, the resolution of the ID copy image is increased through super resolution processing A step (S120) of confirming the information may be performed.

The ID card forgery determination unit 120 performs super resolution processing to adjust the resolution of the ID copy image, and optical character recognition processing for the super-resolution ID card copy to confirm personal information. The ID card forgery determination unit 120 hides one or more personal information items (eg, the last 6 digits of the resident number) set for each identification card (eg, resident registration card, driver's license) among the photographed copies of the identification card to protect personal information A copy may be created and stored in the customer DB through the customer server (S130).

10 is an exemplary view illustrating extraction of personal information of a customer by OCR processing of an ID copy image according to an embodiment of the present invention. If the text information extracted from the copy of the ID does not match the actual ID information, the customer may operate the retake button to retake the ID. If the text information extracted from the copy of the ID matches the actual ID information and the customer operates the confirmation button, identity authentication is performed based on the extracted text information and the ID copy image.

11 is an exemplary view of a customer terminal screen for explaining the step of generating a personal information-protected copy of the ID card by masking the set personal information items among the photographed copies of the ID card and storing the ID copy in the customer server. As shown in FIG. 11 , when an identification card is photographed in a state in which the identification card matches the identification guide object GO1, the personal information item is displayed for one or more personal information items (eg, the last digit of the resident number) set for each identification card. You can create a masked, privacy-protected copy of your ID. Therefore, since the customer does not have to use a memo pad to cover the back digit of the resident registration number, it is possible to prevent the leakage of unnecessary personal information that is not necessary for identity authentication without inconvenience to the customer.

12 is an exemplary diagram for explaining step S140 of FIG. 7 . 6, 7, and 12 , the selfie taking control unit 130 provides a selfie taking interface for taking a face to the customer's terminal that requires self-authentication customer confirmation ( S140 ). The selfie taking interface may provide an interface that enables the customer to take a picture of their own face in real time by running the camera of the customer terminal.

The selfie capturing controller 130 may provide a face guide object GO2 corresponding to the customer's face. The face guide object GO2 may be provided in a shape such as a square, a circle, or an ellipse having a size corresponding to the customer's face. The selfie taking control unit 130 may acquire the customer's selfie photo by determining whether the photographing button is operated while the customer's face is located in the face guide object GO2. That is, if the customer manipulates the photographing button while adjusting the camera position and direction of the customer terminal so that his or her face is located within the face guide object GO2, a real-time selfie photo of the customer for self authentication can be obtained.

The motion detector 140 may determine whether the selfie photo generated through the selfie taking interface is a photo taken by a real customer or a fake photo (S150). The motion detection unit 140 detects the movement of the customer's face between the first time point when the selfie picture is taken for the front of the customer's face by the customer, and the second time point when the selfie picture is taken for the side of the customer's face, When a customer's facial movement is detected, it can be determined that the selfie photo was taken by the actual customer, not a pre-prepared photo or video.

When a selfie photo is generated by the customer taking a face using the terminal through the selfie shooting interface, the authentication unit 150 performs the authentication service between the ID photo and the selfie photo by artificial intelligence that provides an authentication service between the photo and the ID copy. A degree of agreement is calculated by comparing the face images (S160).

The authenticator 150 extracts feature points from the face images of the selfie photo and the ID copy by the artificial intelligence model, respectively, and compares the corresponding feature points to calculate the face matching between the ID photo and the customer's selfie photo. That is, the authenticator 150 may perform customer verification by comparing the ID submitted by the customer with the face of the actual holder through AI face recognition.

The artificial intelligence model extracts feature points from the face images of the real-time selfie photo and the real-time ID copy, respectively, and compares the corresponding feature points to calculate the face matching between the ID photo and the customer's selfie photo. The authentication unit 150 determines forgery or falsification of the ID copy photographed through the ID card photographing interface based on the calculated matching degree, and authenticates the person according to the matching degree calculated by artificial intelligence and the forgery/falsification determination result of the ID copy copy can be performed (S170, S180).

The authentication unit 150, for example, sets the degree of matching calculated by artificial intelligence or sets the calculated standard of agreement (eg, 90%, etc., or between the ID picture taken in real time and the ID picture on the financial DB) The user authentication can be performed by comparing it with the standard matching rate calculated according to the matching rate).

13 is an exemplary diagram for explaining step S180 of FIG. 7 . The authentication result providing unit 160 may provide the identification result 106 performed by the authenticator 150 by comparing the face image of the copy of the ID card 102 with the face image of the selfie photo 104 . According to an embodiment of the present invention, authentication is possible with a photo taken on an app rather than a photo file or video, and photo forgery or falsification can be prevented by securing real-time photo quality. Since the ID copy image is in a state of being restored through super-resolution processing, it is possible to accurately determine the degree of facial matching through comparison with the selfie photo obtained by the high-resolution photographing device of the customer terminal.

Prior to the step of calculating the face match by the artificial intelligence, a step ( S150 ) of determining whether the selfie photo generated through the selfie shooting interface is a photo taken by a real customer or a fake photo may be performed. 14 and 15 are exemplary views for explaining step S150 of FIG. 7 .

The motion detection unit 140 detects the movement of the customer's face between the first time point when the selfie picture is taken for the front of the customer's face by the customer, and the second time point when the selfie picture is taken for the side of the customer's face, When the customer's face movement is detected, it may be determined that the selfie photo was taken by the actual customer, not a pre-prepared photo or video. Therefore, it is possible to prevent the customer from performing false authentication by using the frontal face and side face photos of others by determining whether the actual customer has moved his or her face and performing authentication.

The motion detection unit 140 displays a guide phrase for the customer to take a picture of the front of the face or outputs a voice, etc., and then, after the customer takes a picture of the front of the face, makes the customer move the face in a predetermined direction (eg, left or right direction) ) can be displayed or output by voice or the like. After that, if the customer moves their face according to the guide, the side of the customer's face can be photographed.

The motion detection unit 140 generates a guide phrase instructing the face movement direction at random in a random direction, and then when a motion of the customer moving the face according to the face movement direction is detected at random, the customer actually moves the face It can be judged as a human act. Accordingly, it is possible to more effectively prevent self-authentication by preparing a video of another person performing an action of moving the face in advance and displaying it on the terminal by deceiving the person as the movement of the other person.

16 is an exemplary view of a manager screen of a manager terminal that manages non-face-to-face personal authentication customer identification information according to an embodiment of the present invention. When the customer's face movement is detected, the corresponding selfie photo may be determined to be taken by the actual customer, not a photo or a video of another terminal, and is then shown in FIG. 16 by artificial intelligence by comparing the selfie photo with the ID photo. As illustrated, the degree of face matching may be calculated based on a matching rate between the feature points FP1 of the copy of the ID card and the feature points FP2 of the selfie photo.

When the face matching degree is calculated by artificial intelligence, manual verification may be selectively performed by an administrator according to the face matching degree. For example, if the face match between the selfie photo and the ID image is calculated to be 90% or less, you can request manual verification from the administrator. Contrary to this, if the face match between the selfie photo and the ID image is calculated to be 90% or higher, manual verification by the administrator may be omitted.

17 is a configuration diagram of an authentication unit constituting a non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention. 18 is an exemplary flowchart of steps S160 and S170 of FIG. 7 . 17 and 18 , the authenticator 150 may include a first matching unit 152 , a second agreement calculating unit 154 , a matching comparison unit 156 , and a forgery determination unit 158 . have.

The first coincidence calculator 152 may extract first feature points from the face image of the copy of the ID photographed through the ID photographing interface (S162). The first coincidence calculator 152 may receive the second feature points extracted from the face image of the copy of the customer's ID stored in the financial database 60 from the financial database 60 (S164).

The financial database 60 may be, for example, a database operated by an authorized financial institution or personal information management institution. Since the authentication unit 150 receives the second feature points extracted from the ID photo without directly receiving the ID photo from the financial database 60, it is possible to prevent the ID photo from being transmitted to the outside of the financial database 60 and utilized. .

The first degree of matching calculator 152 calculates the first degree of matching based on the matching rate of the first feature points extracted from the face image of the ID copy photographed by the customer in real time and the second feature points transmitted from the financial database 60 . It can be done (S166).

The second coincidence calculator 154 may extract the third feature points from the face image of the selfie picture taken by the customer in real time through the selfie shooting interface. The second match calculation unit 154 is based on the matching rate of the first feature points extracted from the face image of the ID copy taken by the customer in real time and the third feature points extracted from the face image of the selfie photo taken by the customer in real time. A second degree of agreement may be calculated (S168).

The degree of agreement comparison unit 156 may compare the first degree of agreement calculated by the first degree of agreement calculator 152 with the second degree of agreement calculated by the second degree of agreement calculator 154 ( S172 ). The forgery and falsification determination unit 158 determines the first degree of matching (the degree of similarity between the facial image of the ID photographed in real time by the customer and the facial image of the ID stored in the financial database) and the second degree of matching (the facial image of the ID photographed in real time by the customer and the customer) Based on the comparison result of the feature similarity between selfie photos taken in real time), it is possible to determine forgery or falsification of the ID card (S174, S176).

The forgery determination unit 158 may determine that the copy of the ID photographed through the ID photographing interface is a copy of the normal ID that has not been forged or altered if the first degree of matching is equal to or greater than the second degree of matching (S174). The forgery determination unit 158 may determine that, if the first degree of matching is less than the second degree of matching, the copy of the ID photographed through the ID photographing interface is a copy of the forged or forged abnormal ID (S176).

When the first degree of agreement and/or the second degree of agreement are compared with each set reference value, the accuracy of determining forgery or falsification of the identification card may depend on the setting of the reference value, but the result of comparison between the first degree of agreement and the second degree of agreement By judging forgery or falsification of ID cards, the accuracy of identification can be improved.

For example, if the photo of the ID card is forged or forged, the first degree of matching (eg, 0-40% matching rate) may be lowered, so that it may be determined that the ID card has been forged or forged. In addition, in case of forgery or falsification of the ID, the second degree of matching is higher than the first degree of matching between the ID card photographed in real time and the ID stored in the financial DB, so it can be determined that the ID is forged or forged.

According to the embodiment of FIGS. 17 and 18 , a malicious user obtains another person's ID card, modifies the picture of the ID card into his or her own picture, and performs authentication, or a malicious user converts his or her ID information into another person's information It is possible to prevent fraudulent authentication by judging various types of identification forgery and falsification, such as performing authentication by falsification.

19 is a block diagram of an identification card forgery determination unit constituting a non-face-to-face personal authentication customer confirmation device according to an embodiment of the present invention. 20 is a flowchart according to an example of step S120 of FIG. 7 . 21 is an exemplary diagram for explaining the embodiment of FIG. 20 . 19 to 21 , the identification forgery determination unit 120 may include a first sharpness pattern detection unit 111 , a second sharpness pattern detection unit 112 , and a forgery photo determination unit 113 .

The first sharpness pattern detection unit 111 may detect the first sharpness pattern with respect to the first area AR1 corresponding to the face image area AR0 of the copy of the ID photographed in real time (S121). The first sharpness pattern may include information on damage and aging patterns appearing in the first area AR1 corresponding to the face image area AR0 of the ID card due to the customer's ID card usage habit or possession habit.

The second sharpness pattern detection unit 112 may detect the second sharpness pattern for the second region AR2 that does not correspond to the face image region AR0 of the real-time photographed ID copy (S122). The second sharpness pattern may include information on damage and aging patterns appearing in the second area AR2 that does not correspond to the face image area AR0 of the ID card due to the customer's ID card usage habit or possession habit.

The forged photo determining unit 113 may determine whether a photo forgery of a copy of the ID card photographed in real time by comparing the first sharpness pattern and the second sharpness pattern (S123). The forged photo determination unit 113 may include a sharpness pattern comparison unit 1132 and a photo forgery probability calculation unit 1134 . The sharpness pattern comparison unit 1132 may compare the first sharpness pattern with the second sharpness pattern. The photo forgery probability calculator 1134 may determine whether the photo forgery of the copy of the ID card photographed in real time according to the comparison result of the first sharpness pattern and the second sharpness pattern. In an embodiment, an artificial intelligence model may be generated by learning the sharpness pattern change by artificial intelligence based on the pattern of pixel values in the area around the border of the photo of the forged photo ID, and using the learned artificial intelligence model, the first and whether the photo is forged based on the second sharpness pattern may be determined.

22 is an exemplary diagram illustrating a change in pixel values of a photo boundary portion of a normal ID. 23 is an exemplary diagram illustrating a change in pixel values of a photo boundary portion of an identification card to which a forged photo is attached. In the case of a normal ID, as shown in FIG. 22 , the change in the sharpness pattern at the boundary of the ID photo does not appear to be large, but in the case of an ID with a forged photo, the change in the sharpness pattern at the boundary of the ID photo may appear significantly.

That is, when the user replaces another person's ID photo with the user's own photo to forge or falsify the ID, the first sharpness pattern of the photo area of the ID is different from the second sharpness pattern of the area other than the photo area of the ID. will have Therefore, when the first sharpness pattern and the second sharpness pattern are different, it can be determined that the user has forged or forged the ID photo.

As the first region from which the first sharpness pattern is extracted and the second region from which the second sharpness pattern is extracted are closer, the accuracy of forgery/falsification determination of the ID photo according to the comparison result between the first sharpness pattern and the second sharpness pattern can be increased. have. Accordingly, the first area may be set as a corner area of the ID photo, and the second area may be set as an area surrounding the corner area of the ID photo.

24 is a block diagram of an identification card forgery determination unit constituting a non-face-to-face personal authentication customer confirmation device according to another embodiment of the present invention. 25 is a flowchart according to another example of step S120 of FIG. 7 . 26 and 27 are exemplary views for explaining the embodiment of FIG. 25 . 24 to 27 , the identification forgery determination unit 120 includes a hologram area detection unit 124 , a light reflection area detection unit 124 ′, a first image processing unit 125 and a second image processing unit 126 . can do.

The hologram area detection unit 124 may detect a hologram area corresponding to the hologram among the face images of the copy of the ID photographed in real time (S124). The light reflection area detection unit 124' may detect a light reflection area generated by light reflection among the face images of the copy of the ID card photographed in real time (S124).

The light reflection region may be generated as, for example, artificial light such as indoor/outdoor illumination light or sunlight is reflected on the ID card and is incident on the camera. In an embodiment, the hologram area and the light reflection area of the ID copy image may be detected based on an artificial intelligence model generated by learning patterns of pixel values respectively appearing in the hologram area and the light reflection area by artificial intelligence.

The first image processing unit 125 may perform a first image processing on the hologram area (S125). The first image processing may be image processing for removing or reducing hologram information included in the hologram region and/or light reflection information included in the light reflection region. The first image processing unit 125 smoothes the areas HG1 and HG2 in which the pixel value increase exceeds the reference value among pixels in the hologram area and/or light reflection area corresponding to the hologram in the face image of the copy of the ID card. The first image data D1 converted into the pixel information HG3 and HG4 from which the hologram information has been removed or reduced may be generated.

The second image processing unit 126 performs second image processing on the face image of the copy of the ID card from the first image data D1 in which the hologram information and/or light reflection information are removed or reduced to obtain the first image data D1 The second image data D2 having a higher resolution may be generated ( S126 ). The second image processing may be image processing for improving the resolution of the face image of the ID copy by a Super Resolution algorithm.

28 is a block diagram of a motion detection unit constituting a non-face-to-face self-authentication customer confirmation device according to an embodiment of the present invention. 29 is an exemplary flowchart of step S150 of FIG. 7 . 30 is an exemplary diagram for explaining the embodiment according to FIG. 29 . 28 to 30 , the motion detection unit 140 may include a light output control unit 142 , a brightness distribution calculation unit 144 , a brightness change analysis unit 146 , and a fraudulent activity determination unit 148 . can

The light output control unit 142 may execute a light output control process of changing the light output generated from the customer terminal from the first light output state to the second light output state while the customer moves the face (S151) . The light output adjusting unit 142 may execute light output adjusting processing such as changing the lighting generated by the customer terminal or generating a flash while the customer makes a motion of moving his or her face.

The brightness distribution calculator 144 may include a first brightness distribution calculator 1442 and a second brightness distribution calculator 1444 . The first brightness distribution calculator 1442 calculates the first brightness for each face region P1 to P5 of the first selfie picture taken in the first light output state (eg, in the low light output mode) to calculate the first brightness A distribution can be calculated (S152). The second brightness distribution calculator 1444 calculates a second brightness for each face region P1 to P5 of the second selfie picture taken in the second light output state (eg, high light output mode) to calculate the second brightness A distribution can be calculated (S153).

The brightness change analyzer 146 may analyze the brightness change for each face region P1 to P5 of the customer based on the first brightness distribution and the second brightness distribution ( S154 ). The fraudulent action determination unit 148 may determine the fraudulent action in which the user attempts to pass the motion detection authentication by executing a video through another terminal based on the brightness change analyzed for each face region of the customer (S155).

That is, based on the result of comparing the first brightness distribution with the second brightness distribution for each face region P1 to P5, the authenticator 150 determines whether the actual user is moving the face, or whether the user is using another terminal. You can distinguish whether you are trying to pass motion detection authentication by running a video through .

When an actual user moves his or her face, the brightness change appears differently depending on the curvature (inclination) of each face area according to the light output brightness. The change acts uniformly on the entire face, so that the brightness change for each face area is relatively constant.

Therefore, if it is determined that the rate of change of light between the first selfie picture and the second selfie picture is different depending on the user's face part (for example, the tip of the nose, the forehead, the lips, the cheekbones, etc.), it is assumed that the actual motion of the user is normal. If it is determined that the rate of change of light between the first selfie photo and the second selfie photo is relatively constant for each face part, it can be determined that the motion detection authentication is passed in an illegal way by executing a video on the terminal. . Therefore, according to the embodiment of FIGS. 28 and 29 , it is possible to prevent an act of passing the motion detection authentication by a third party using an illegal method of executing a video of another person's facial movement through another terminal.

As described above, according to the non-face-to-face identity authentication customer confirmation device and method according to an embodiment of the present invention, optical character recognition technology (OCR), motion detection (Motion Detection), face recognition using artificial intelligence (Face Recognition) And artificial intelligence using real-time ID photos and selfie photos that perform simple and accurate self-authentication based on customer’s real-time ID photos and face selfie photos based on Face Matching technology A face recognition-based non-face-to-face identity authentication customer verification device and method are provided.

In addition, according to an embodiment of the present invention, it is possible to prevent false identity authentication using another person's photo or video. In addition, it is possible to simplify the customer's non-face-to-face account opening step, to replace the video call authentication method and to use the service 24 hours a day, so customer convenience can be increased, and the cost of the service company used for one-way authentication can be reduced. . In addition, simple identity verification for foreigners and teenagers who do not have an account is also possible.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, method, and component described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). Array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers.

The processing device may run an operating system and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, a processing device is sometimes described as being used, but a person of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It will be understood that this may include

For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a Parallel Processor. The software may include a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device.

The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software.

Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CDROMs and DVDs, and ROM, RAM, and flash memory. Hardware devices specially configured to store and execute program instructions, such as, etc. are included. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible from the above description by those skilled in the art. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result. Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (17)

ID card photographing control unit that provides an identification card photographing interface for photographing identification to a customer's terminal requiring identification of the customer;
Self-verification control unit that provides a selfie-taking interface for photographing a face to a customer's terminal requiring customer confirmation; and
When a selfie photo is generated by a customer taking a face using a terminal through the selfie shooting interface, artificial intelligence compares the selfie photo with the face image of a copy of the ID card to calculate the degree of matching, and based on the calculated degree of matching, the ID card Non-face-to-face self-certification customer, including an authenticator that judges forgery or falsification of a copy of ID card photographed through a shooting interface, and performs self-certification according to the match calculated by the artificial intelligence and forgery/falsification determination result of ID copy verification device. According to claim 1,
The ID photographing control unit is:
In the ID card shooting mode, the ID guide object is displayed in the form of a rectangle corresponding to the ID selected by the customer on the image on the screen of the customer terminal, and the ID is captured by the customer by operating the shooting button while the ID matches the ID guide object A non-face-to-face personal authentication customer verification device that generates a copy image of an ID by judging whether it is. According to claim 1,
Super-resolution processing to adjust the resolution of the ID copy image, optical character recognition processing for the super-resolution ID copy to confirm personal information, and to protect personal information by hiding one or more personal information items set for each ID Non-face-to-face personal authentication customer verification device, further comprising an identification forgery determination unit that generates a copy of the ID card and stores it in the customer server. According to claim 1,
The selfie shooting control unit: provides a face guide object corresponding to the customer's face, and determines whether the shooting button is operated in a state where the customer's face is located in the face guide object to obtain a customer's selfie picture, non-face-to-face Identity verification customer verification device. According to claim 1,
The authenticator: extracting feature points from the face images of the selfie photo and the ID copy by an artificial intelligence model, and comparing the corresponding feature points to calculate the facial match between the ID photo and the customer's selfie photo, non-face-to-face person Authenticated Customer Identification Device. According to claim 1,
The authentication unit:
The first feature points are extracted from the face image of the copy of the ID photographed through the ID photographing interface, the second feature points extracted from the face image of the copy of the ID of the customer stored in the financial database are transmitted from the financial database, and the a first coincidence calculator that calculates a first degree of matching based on a matching rate between the first feature points extracted from the face image of the copy of the ID card and the second feature points transmitted from the financial database;
The third feature points are extracted from the face image of the selfie photo taken by the customer in real time through the selfie shooting interface, the first feature points extracted from the face image of the ID copy taken by the customer in real time, and the selfie photo taken by the customer in real time a second degree of agreement calculator for calculating a second degree of agreement based on the matching rate of the third feature points extracted from the face image of ;
a degree of agreement comparison unit comparing the first degree of agreement with the second degree of agreement; and
A non-face-to-face identity authentication customer confirmation device comprising a forgery determination unit for determining forgery or falsification of an identification card based on a comparison result of the first degree of agreement and the second degree of agreement. 7. The method of claim 6,
The forgery determination unit:
if the first degree of matching is equal to or greater than the second degree of matching, it is determined that the copy of the ID photographed through the ID photographing interface is a copy of a normal ID that has not been forged or altered; and
If the first degree of agreement is less than the second degree of agreement, it is determined that the copy of the ID photographed through the ID photographing interface is a forged or forged copy of the abnormal ID. According to claim 1,
Detects the customer's face movement between a first time point when a selfie picture is taken for the front of the customer's face by the customer and a second time point when a selfie picture is taken for the customer's face side, and when the customer's face movement is detected Non-face-to-face identity authentication customer verification device further comprising a motion detection unit for determining that the selfie photo was taken by a real customer rather than a pre-prepared photo or video. 9. The method of claim 8,
The motion detection unit:
a light output adjusting unit that executes a light output adjusting process for changing the output of light generated from the customer terminal from the first light output state to the second light output state while the customer moves the face;
a first brightness distribution calculator configured to calculate a first brightness distribution by calculating a first brightness for each face region of a first selfie photo taken in the first light output state;
a second brightness distribution calculator configured to calculate a second brightness distribution by calculating a second brightness for each face region of a second selfie picture taken in the second light output state;
a brightness change analyzer for analyzing a brightness change for each face region of a customer based on the first brightness distribution and the second brightness distribution; and
Non-face-to-face identity authentication customer verification device, comprising a fraudulent determination unit that determines a fraudulent act in which the user attempts to pass motion detection authentication by executing a video through another terminal based on the brightness change analyzed for each face region of the customer . According to claim 1,
The identification forgery determination unit:
a first sharpness pattern detector configured to detect a first sharpness pattern in a first region corresponding to a face image region of a copy of the ID card photographed in real time;
a second sharpness pattern detection unit configured to detect a second sharpness pattern in a second region that does not correspond to the face image region of the real-time photographed ID copy; and
and a counterfeit photo determining unit that compares the first sharpness pattern with the second sharpness pattern to determine whether a photo of a copy of the ID card photographed in real time is forged. According to claim 1,
The identification forgery determination unit:
a hologram area detection unit that detects a hologram area corresponding to a hologram among the face images of the copy of the ID card photographed in real time;
a light reflection area detection unit that detects a light reflection area generated by light reflection in the face image of a copy of the ID card photographed in real time;
a first image processing unit for performing first image processing for reducing the holographic information corresponding to the hologram and the light reflection information corresponding to the light reflection with respect to the hologram area and the light reflection area; and
Non-face-to-face personal authentication customer confirmation device comprising a second image processing unit for performing a second image processing corresponding to a super-resolution (Super Resolution) processing on the face image of the copy of the ID card on which the first image processing has been performed. providing, by the identification photographing control unit, an identification photographing interface for photographing identification to a terminal of a customer requiring identification of the customer;
providing, by the selfie-taking controller, a selfie-taking interface for photographing a face to a terminal of a customer who needs self-authentication customer confirmation;
Comparing, by the authenticator, the face image of the selfie photo and the ID copy by artificial intelligence, calculating a degree of agreement;
determining, by the authenticator, forgery or falsification of a copy of an ID photographed through an ID photographing interface based on the degree of matching; and
A non-face-to-face identity authentication customer confirmation method comprising, by the authentication unit, performing identity authentication according to the matching result calculated by the artificial intelligence and the forgery or falsification determination result of the ID copy. 13. The method of claim 12,
The step of determining forgery or falsification of the copy of the identification card is:
By the first coincidence calculation unit, first feature points are extracted from the face image of the ID copy photographed through the ID card photographing interface, and second feature points extracted from the face image of the ID copy copy of the customer stored in the financial database are extracted from the financial database. calculating a first degree of matching based on a matching rate between first feature points received and extracted from the face image of a copy of an ID photographed by the customer in real time and second feature points received from a financial database;
By the second coincidence calculator, third feature points are extracted from the face image of the selfie photo taken by the customer in real time through the selfie shooting interface, and the first feature points extracted from the face image of the ID copy taken by the customer in real time and , calculating a second degree of matching based on a matching rate of third feature points extracted from a face image of a selfie taken by a customer in real time;
comparing the first degree of agreement with the second degree of agreement by a degree of agreement comparison unit; and
Non-face-to-face self-authentication customer verification method comprising, by a forgery determination unit, determining forgery or falsification of an identification card based on a comparison result of the first degree of agreement and the second degree of agreement. 13. The method of claim 12,
Detect, by the motion detector, a movement of the customer's face between a first time point at which a selfie picture is taken for the front of the customer's face by the customer and a second time point at which a selfie picture is taken with respect to the side of the customer's face, Further comprising the step of determining that the selfie photo was taken by an actual customer rather than a pre-prepared photo or video when the facial movement of 13. The method of claim 12,
The step of determining forgery or falsification of the copy of the ID is:
detecting, by the first sharpness pattern detection unit, a first sharpness pattern for a first area corresponding to a face image area of a copy of the ID card photographed in real time;
detecting, by the second sharpness pattern detection unit, a second sharpness pattern for a second area that does not correspond to the face image area of the real-time photographed ID copy; and
Comprising the step of comparing, by a forged photo determining unit, the first sharpness pattern and the second sharpness pattern, to determine whether a photo of a copy of the ID card photographed in real time is forged or not, the non-face-to-face identity authentication customer confirmation method. 13. The method of claim 12,
The step of determining forgery or falsification of the copy of the identification card is:
detecting, by a hologram area detection unit, a hologram area corresponding to a hologram in a face image of a copy of an ID photographed in real time;
detecting, by a light reflection area detection unit, a light reflection area generated by light reflection in a face image of a copy of an ID photographed in real time;
performing, by a first image processing unit, first image processing for reducing holographic information corresponding to the hologram and light reflection information corresponding to the light reflection with respect to the hologram area and the light reflection area; and
Non-face-to-face identity authentication customer, comprising the step of performing, by a second image processing unit, a second image processing corresponding to Super Resolution processing on the face image of the copy of the ID card on which the first image processing has been performed checking way. A computer-readable recording medium in which a program for executing the non-face-to-face personal authentication customer verification method of claim 12 is recorded.

Images