KR102301785B1 - Method and appauatus for face continuous authentication - Google Patents

Abstract

A method and apparatus for continuous face authentication are disclosed. The face authentication method includes the steps of performing continuous shooting through a camera; detecting a face region in the image frame through the photographing; tracking a change in the position of the face region; and performing continuous user authentication through tracking of the face region.

Description

METHOD AND APPAUATUS FOR FACE CONTINUOUS AUTHENTICATION

The description below relates to an authentication technique for verifying a user's identity.

Biometric authentication (fast identity online) is a technology that uses an individual's unique biometric information, such as a fingerprint, Hongjae, face, and voice, to verify a user's identity.

Face recognition is one of the commonly used biometric authentication technologies, and it is being used in various security systems, such as smart doors, smartphones, and laptop computers, replacing the existing number key-based authentication systems. .

For example, Korean Patent Publication No. 10-0809044 (registration date: February 25, 2008) discloses a non-contact face authentication door lock system that authenticates a registrant by photographing a visitor's face.

Current face authentication technology is a method of receiving authentication by bringing a face closer to the device's camera when a device requests authentication from a user.

However, the existing face authentication technology has a disadvantage in that it requires an effort for close-up photography from the user, and in particular, there is a problem in that authentication is processed with a different type of input such as a non-real picture.

A face authentication method and apparatus capable of minimizing user effort for face authentication are provided.

A face authentication method and apparatus capable of solving a fake authentication problem using other types of input such as a photo are provided.

A face authentication method executed in a computer device, the computer device comprising at least one processor configured to execute computer readable instructions contained in a memory, the face authentication method comprising: in the at least one processor, a camera; performing continuous shooting through; detecting, by the at least one processor, a face region in the image frame through the photographing; tracking, in the at least one processor, a change in the position of the face region; and performing, in the at least one processor, continuous user authentication through tracking of the face region.

According to one aspect, the at least one processor, collecting the image captured through the camera, the detected face region, and a user authentication result; and learning, in the at least one processor, a deep learning model for user authentication using the collected image, face region, and user authentication result, wherein performing the continuous user authentication comprises: User authentication can be performed using a deep learning model.

According to another aspect, performing the continuous user authentication may include identifying a fake input using a photo using the deep learning model.

According to another aspect, the learning may include learning the image and the face region that have succeeded in user authentication as correct answer data together with user ID information.

According to another aspect, the detecting may include detecting the face region by cropping a region of interest (ROI) corresponding to a human candidate region in the image frame.

A computer device comprising: at least one processor implemented to execute computer readable instructions contained in a memory, wherein the at least one processor performs continuous shooting through a camera to display a face in an image frame through the shooting There is provided a computer device, characterized in that it detects a region, tracks a change in the position of the facial region, and performs continuous user authentication through tracking of the facial region.

According to embodiments of the present invention, face authentication can be processed without user effort for close-up photography, thereby improving user convenience.

According to embodiments of the present invention, it is possible to effectively solve the problem of fake authentication using other types of input such as a photo.

1 is a block diagram for explaining an example of an internal configuration of a computer device according to an embodiment of the present invention.
2 is a diagram illustrating an example of components that a processor of a computer device according to an embodiment of the present invention may include.
3 is a flowchart illustrating an example of a face authentication method that can be performed by a computer device according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Embodiments of the present invention relate to authentication technology for verifying the identity of a user.

Embodiments including those specifically disclosed herein can solve the problem of fake authentication using other types of input, such as photos, while processing face authentication without requiring user effort for close-up photography, and through this, the user It achieves significant advantages in terms of convenience, enhanced security, etc.

1 is a block diagram for explaining an example of an internal configuration of a computer device according to an embodiment of the present invention. For example, the face authentication system according to embodiments of the present invention may be implemented through the computer device 100 of FIG. 1 . As shown in FIG. 1 , the computer device 100 is a component for executing the face authentication method, and includes a processor 110 , a memory 120 , a persistent storage device 130 , a bus 140 , and an input/output interface 150 . ) and a network interface 160 .

Processor 110 may include or be part of any device capable of processing a sequence of instructions as a component for face authentication. Processor 110 may include, for example, a computer processor, a processor in a mobile device, or other electronic device and/or a digital processor. The processor 110 may be included in, for example, a server computing device, a server computer, a set of server computers, a server farm, a cloud computer, a content platform, and the like. The processor 110 may be connected to the memory 120 through the bus 140 .

Memory 120 may include volatile memory, persistent, virtual, or other memory for storing information used by or output by computer device 100 . The memory 120 may include, for example, random access memory (RAM) and/or dynamic RAM (DRAM). Memory 120 may be used to store any information, such as state information of computer device 100 . The memory 120 may also be used to store instructions of the computer device 100 including, for example, instructions for face authentication. Computer device 100 may include one or more processors 110 as needed or appropriate.

Bus 140 may include a communications infrastructure that enables interaction between various components of computer device 100 . Bus 140 may carry data between, for example, components of computer device 100 , such as between processor 110 and memory 120 . Bus 140 may include wireless and/or wired communication media between components of computer device 100 , and may include parallel, serial, or other topological arrangements.

Persistent storage 130 is a component, such as a memory or other persistent storage device, as used by computer device 100 to store data for an extended period of time (eg, compared to memory 120 ). may include Persistent storage 130 may include non-volatile main memory as used by processor 110 in computer device 100 . Persistent storage 130 may include, for example, flash memory, a hard disk, an optical disk, or other computer readable medium.

The input/output interface 150 may include interfaces to a keyboard, mouse, voice command input, display, or other input or output device. Configuration commands and/or input for facial authentication may be received via input/output interface 150 .

Network interface 160 may include one or more interfaces to networks such as a local area network or the Internet. Network interface 160 may include interfaces for wired or wireless connections. Configuration commands and/or input for facial authentication may be received via network interface 160 .

Also, in other embodiments, the computer device 100 may include more components than those of FIG. 1 . However, there is no need to clearly show most of the prior art components. For example, the computer device 100 is implemented to include at least some of the input/output devices connected to the input/output interface 150 described above, or a transceiver, a global positioning system (GPS) module, a camera, various sensors, It may further include other components such as a database and the like.

The present embodiments relate to authentication technology for user identification, and more particularly, to face authentication technology.

2 is a diagram illustrating an example of components that a processor of a computer device according to an embodiment of the present invention may include.

As shown in FIG. 2 , the processor 110 may include a learning performing unit 210 and a user authenticating unit 220 . The learning performing unit 210 may include at least one of a data collecting unit 211 and a deep learning learning unit 212 according to an embodiment.

These components of the processor 110 may be representations of different functions performed by the processor 110 according to a control instruction provided by at least one program code. For example, the learning execution unit 210 may be used as a functional expression that operates to control the computer device 100 so that the processor 110 learns a deep learning model by using data related to face authentication. The processor 110 and components of the processor 110 may perform steps included in the following face authentication method. For example, the processor 110 and components of the processor 110 may be implemented to execute an operating system code included in the memory 120 and an instruction according to at least one program code described above. Here, at least one program code may correspond to a code of a program implemented to process the face authentication method.

3 is a flowchart illustrating an example of a face authentication method that can be performed by a computer device according to an embodiment of the present invention.

The face authentication method of FIG. 3 may not occur in the order shown, and some of the steps may be omitted or additional processes may be further included.

The processor 110 may load a program code stored in a program file for the face authentication method into the memory 120 . For example, a program file for the face authentication method may be stored in the persistent storage device 130 described with reference to FIG. 1 , and the processor 110 may program the program from the program file stored in the persistent storage device 130 via a bus. The computer device 100 may be controlled so that the code is loaded into the memory 120 . At this time, each of the processor 110 and the data collection unit 211 , the deep learning learning unit 212 , and the user authentication unit 220 included in the processor 110 corresponds to the program code loaded in the memory 120 . They may be different functional representations of the processor 110 for executing the instructions of the part to execute subsequent steps S301 to S308. For execution of steps S301 to S308 , the processor 110 and components of the processor 110 may directly process an operation according to a control command or control the computer device 100 .

In step S301 , the user authentication unit 220 may perform continuous or periodic photographing through a camera connected to the input/output interface 150 . The user authenticator 220 does not require a separate user effort for face authentication, but may continuously photograph the user's face while the camera is on, or may photograph the user's face through the camera at regular intervals. A service can be assumed in which there are many moments in which the user's face is captured by the camera, for example, continuously shooting the user in a situation where the camera is always on, such as CCTV, or whenever the camera is turned on or periodically while using a smartphone. You can turn on the camera to take a picture of the user. In addition to continuous shooting or periodic shooting, when a predefined environment is detected through a sensor (eg, a motion sensor, an infrared sensor, a touch sensor, etc.) included in the computer device 100, it is also possible to turn on the camera to take a picture of the user. do.

In step S302 , the user authenticator 220 may detect a face region from the image captured in step S301 . The user authenticator 220 may detect a position where a face is present in the image frame through a face detection algorithm. For example, the user authenticator 220 generates a pyramid image to detect faces of various sizes in the image frame and then moves one pixel at a time to determine whether the corresponding area of a specific size (eg, 20×20 pixels) is a face. a can be determined as a classifier such as a neural network (neural Network), Ada-boost (Adaboost), support vector machine (Support Vector machine).

In step S303 , the user authenticator 220 may track a change in the position of the face region detected in step S302 . The user authenticator 220 may track a change in a face region using a similarity between specific information such as a size, color, shape, and outline of a face region in a series of image frames through a face tracking algorithm.

In step S304, the user authentication unit 220 may perform user authentication using the face region tracked in step S303. The user authentication unit 220 may continuously or periodically authenticate the user while tracking the user's face through continuous or periodic photographing. The user authenticator 220 may authenticate the user by comparing the tracked face region with a face DB (database) pre-registered in the memory 120 . Accordingly, the user authentication unit 220 may perform user authentication without additional user effort at a time when user authentication is required. A user can be authenticated whenever a face is captured by the camera, even in a situation where the user does not make an effort for authentication without requiring a separate user effort for face authentication.

The learning performer 210 may improve the system by collecting authentication-related data whenever a user's face is captured by the camera and learning a deep learning model based on the collected data.

In step S305 , the data collection unit 211 may collect the captured data, that is, the image captured by the camera in step S301 as learning data for model learning.

In step S306 , the data collection unit 211 may collect face region data, that is, the face region detected in step S302 , as training data for model learning.

In step S307, the data collection unit 211 may collect user authentication result data, that is, user ID information that has succeeded in user authentication in step S304 as training data for model learning.

In step S308 , the deep learning learning unit 212 may learn a deep learning model for user authentication by using photographing data, face area data, and user authentication result data collected as training data for model learning. The deep learning learning unit 212 may classify the photographed data and face region data collected as model learning data into data in which user authentication is successful and data in which user authentication is unsuccessful. At this time, the deep learning learning unit 212 may classify data in which user ID information exists as data that has succeeded in user authentication as user authentication is successful, and divide the photographed data and face area data in which user authentication is successful to the corresponding user ID information. You can learn from the correct answer data with Meanwhile, as user authentication fails, data in which user ID information does not exist may be classified as data that has failed user authentication, and photographed data and face area data that have failed user authentication may be learned as incorrect answer data.

Thereafter, the user authentication unit 220 may perform user authentication based on the deep learning model learned in step S308 without requiring additional user effort when user authentication is required.

For example, instead of authenticating the user with additional effort in the smart door attached to the door, the camera attached to the smart door may recognize the user walking in the hallway from a distance and continuously authenticate the user. When an actual user arrives at the door, the user can already be recognized to determine whether to enter or not.

In order to more accurately recognize a user's face from a distance, a region of interest (ROI) may be cropped from an image frame to a candidate region where a person is expected to be used as an input for face detection.

In particular, the user authentication unit 220 performs user authentication through a deep learning model learned from photographing data, face region data, and user authentication result data, so that other types of inputs such as photos can be selected as fakes, resulting in a stronger authentication environment can provide

As such, according to embodiments of the present invention, face authentication can be processed without user effort for close-up photography, thereby improving user convenience. And, according to embodiments of the present invention, it is possible to effectively solve the problem of fake authentication using other types of input such as a photo.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, the apparatus and components described in the embodiments may include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), and a programmable logic unit (PLU). It may be implemented using one or more general purpose or special purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one 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 can be seen that can 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 parallel processors.

The software may comprise 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 embodied in any type of machine, component, physical device, computer storage medium or device for interpretation by or providing instructions or data to the processing device. have. 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. In this case, the medium may be to continuously store a program executable by a computer, or to temporarily store it for execution or download. In addition, the medium may be a variety of recording means or storage means in the form of a single or several hardware combined, it is not limited to a medium directly connected to any computer system, and may exist distributed on a network. Examples of the medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and those configured to store program instructions, including ROM, RAM, flash memory, and the like. In addition, examples of other media may include recording media or storage media managed by an app store for distributing applications, sites for supplying or distributing other various software, and servers.

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 a different order than 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 (6)

A face authentication method executed on a computer device, the method comprising:
the computer device comprises at least one processor configured to execute computer readable instructions contained in a memory;
The face authentication method is
performing, in the at least one processor, continuous photographing through a camera;
detecting, by the at least one processor, a face region in the image frame through the photographing;
tracking, in the at least one processor, a change in the position of the face region;
performing, in the at least one processor, continuous user authentication through tracking of the face region;
collecting, in the at least one processor, the image captured by the camera, the detected face region, and a user authentication result; and
Learning, in the at least one processor, a deep learning model for user authentication using the collected image, face region, and user authentication result
including,
The detecting step is
generating a pyramid image from the image frame; and
detecting the face region from the pyramid image
including,
The step of performing the continuous user authentication,
Perform user authentication using the deep learning model,
The learning step is
classifying the collected images and face regions into data in which user authentication succeeds and data in which user authentication fails according to a user authentication result;
learning the image and face region that has succeeded in user authentication as correct answer data along with user ID information; and
Learning the image and face area that failed user authentication as incorrect answer data
A face authentication method comprising a. delete According to claim 1,
The step of performing the continuous user authentication,
Using the deep learning model to identify a fake input using a photo
A face authentication method comprising a. delete According to claim 1,
The detecting step is
detecting the face region by cropping a region of interest (ROI) corresponding to a human candidate region in the image frame;
A face authentication method comprising a. In a computer device,
at least one processor implemented to execute computer readable instructions contained in a memory
including,
the at least one processor,
detecting a face region in an image frame through the photographing by performing continuous photographing through a camera;
performing continuous user authentication through tracking of the face region while tracking a change in the position of the face region;
collecting an image captured by the camera, the detected face region, and a user authentication result; and
A process of learning, in the at least one processor, a deep learning model for user authentication using the collected image, face region, and user authentication result
process the
The detection process is
After generating a pyramid image from the image frame, detecting the face region from the pyramid image,
The process of performing the continuous user authentication is,
Perform user authentication using the deep learning model,
The learning process is
Classifying the collected image and face region into data that succeeds in user authentication and data that fails user authentication according to the user authentication result,
It learns images and face areas that have succeeded in user authentication as correct answer data along with user ID information,
Learning images and face areas that fail user authentication with incorrect answer data
A computer device characterized by a.

Images