KR101457377B1 - User authetication method based on mission gesture recognition, and computer-readable recording medium with user authetication program based on mission gesture recognition - Google Patents

Abstract

The present invention relates to a technique for recognizing a mission execution gesture to authenticate a user. A user authentication method using the mission execution gesture recognition method of the present invention includes: outputting a password or a pass phrase indicating a gesture of at least one object set in advance to a UI screen of a display device; Receiving shooting data shot by an imaging device provided in a display device and extracting object data divided into respective objects from shooting data; Judging whether a copper wire extracted from each object data matches with a copper wire of a gesture according to an object on the pre-stored password or pass phrase, and performing authentication processing for the user when matching is performed on all objects.

Description

TECHNICAL FIELD [0001] The present invention relates to a user authentication method using a mission execution gesture recognition, and a user authentication program using a mission execution gesture recognition, mission gesture recognition}

The present invention relates to user authentication techniques using mission-aware gesture recognition. In particular, in order to solve the problem that a recognition method is exposed to another user by using a key input or a voice input to recognize a user, security is weakened by imitation and modulation, and a hardware device must be accompanied, And a technique for recognizing the execution gesture and authenticating the user.

Conventionally, in the Internet or personal terminal, the user authentication is individually performed by the setting of the Internet service provider or the personal terminal. In this case, generally, the user has used a password inputting method according to the account according to a combination of preset numbers and characters. In recent years, there are also many methods through user recognition through fingerprint input or fingerprint recognition.

However, in the case of an electronic password input method, there is a high risk of exposure to other users due to hacking or careless management, and once exposed, it is difficult to prevent leakage of personal information due to fraudulent use. In addition, the latter voice input method or fingerprint recognition method has a disadvantage in that a hardware structure such as a separate input device must be accompanied.

Accordingly, in the related art, illegal user authentication by an unauthorized user is prevented, and technology for designing a usage right for personal data according to user authentication and authentication by using a software configuration is developed Is desperately required.

[Related Technical Literature]

1. Global Authentication Continuity Features and Implementation Method (Patent Application No. 10-2004-0094524)

2. Voice Authentication Device, Voice Authentication System, and Voice Authentication Method (Patent Application No. 10-2006-7012391)

SUMMARY OF THE INVENTION It is an object of the present invention to provide a method and apparatus for recognizing a user by using a key input or a voice input in order to solve a problem that a recognition method is exposed to another user and security is weakened by imitation and modulation, And a technique for authenticating a user by recognizing a mission execution gesture of an object.

According to another aspect of the present invention, there is provided a method for authenticating a user using a mission-execution gesture recognition, the method comprising: a first step of outputting a mission including a gesture of at least one object set in advance to a user; A second step of acquiring image pickup data generated by the image pickup apparatus; A third step of extracting object data divided into respective objects from photographed data; A fourth step of extracting a copper wire of a gesture per object of photographed data from the object data; A fifth step of acquiring copper line information of a gesture per object stored in advance for the user with respect to the mission; A fifth step of comparing a copper wire of the gesture of the photographic data with the copper wire information of the gesture of each object previously stored; And a sixth step of determining whether the user is authenticated according to the comparison result. In this case, the method may further include requesting a mission for each user, acquiring shooting data corresponding to the mission, extracting the moving-line information of the object-specific gesture from the shooting data, and storing it in advance.

Meanwhile, in the user authentication method using the mission-execution gesture recognition of the present invention, the fourth step includes a step 4a of extracting a motion vector according to the flow of photographing time with respect to each of the object data, And acquiring a copper wire of the gesture per object based on the copper wire of the object. In addition, the object-by-object gesture in the third step includes at least one of face movement, eye flicker, head turning, mouth movement, finger movement in response to a preset time, And the like.

According to another aspect of the present invention, there is provided a user authentication program for use in recognition of a mission-execution gesture recorded on a computer-readable recording medium, the program comprising an authentication UI for controlling a user to output a mission including a gesture of one or more objects Implementation means 21a; Object recognizing means (21c) for extracting object data divided into respective objects from the photographic data generated by the image pickup apparatus; A storage unit (22) for storing movement information of a gesture per object for each user in advance for the mission; And authentication determination means (21e) for comparing the copper wire extracted from the object data with the copper wire information of the object-specific gesture stored in advance in the storage unit (22) and determining whether or not the user is authenticated based on the comparison result.

At this time, the user authentication program extracts a motion vector according to the flow of photographing time with respect to each of the object data, and then, using the motion vector of the motion vector extracted by the authentication determination means 21e, And motion vector analysis means (21d) for comparing and judging the motion vector information with the motion vector information. In addition, the user authentication program may further comprise split focus means (21b) for controlling the autofocus, which is divided for each object previously set for the image pickup apparatus, to be performed before the image pickup data is received.

According to the present invention, illegal use by other users can be prevented through inputting pass characters or pass phrases set for each user without visible input means such as key input or voice input.

That is, by visualizing (body) a part of a body such as a mouth, a face, a finger, etc. of a user, or attachments possessed by a user, and taking a gesture for each object or identifying a user by a combination of gestures, It is effective to enhance the security of the individual by allowing the user to be authenticated without voice input.

1 illustrates an overall system in which a user authentication method using mission-aware gesture recognition is implemented in accordance with the present invention.
2 is a diagram for explaining a display device and an imaging device in the entire system according to the present invention.
FIG. 3 is a flowchart illustrating an embodiment of a user authentication method using the mission-execution gesture recognition according to the present invention.
4 is a flowchart illustrating another embodiment of a user authentication method using the mission-execution gesture recognition according to the present invention.

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

1 is a diagram illustrating an entire system in which a user authentication method using a mission-execution gesture recognition according to the present invention is implemented.

1, the entire system in which the user authentication method using the mission execution gesture recognition of the present invention is implemented includes a display device 10 having an image capture device 11, a gesture authentication module 21, And an authentication unit (20) having a unit (22). Here, the authentication device 20 may be formed of a data bus in the local area with the display device 10, or an external server connected to the display device 10 through a data cable via a network.

The gesture authentication module 21 includes an authentication UI implementation unit 21a, a split focusing unit 21b, an object recognition unit 21c, a motion vector analysis unit 21d and an authentication determination unit 21e.

The authentication UI implementing means 21a designates a mission representing a predetermined object-based gesture stored in the storage unit 22 in correspondence with a user's authentication (login) request for each user's ID, ) To the UI screen. Here, the mission is a specific task that a user who wishes to authenticate can perform, such as reading a specific password or passphrase, following a specific body motion, or a combination thereof Do. For example, the following may be missions.

(1) Please read the following words.

(2) Please read the following sentence.

(3) Put your index finger on the right side of the face and read the words below.

(4) Turn your head to the left and right.

(5) Shake the car key up and down.

Also, in the present invention, objects can be designated as parts of the user's mouth, eyes, face, fingers and the like, attachments carried by the user, and the like. Here, the object gesture is basically aimed at recognizing the movement of the entire face acting in response to the mission. In addition, since face movements can be easily followed, it can be implemented by adding mouth-shaped movements that read a pass character or pass phrase formed by a single character or a continuous string in face movement in terms of enhancing security for user authentication have. In addition, the movement of external attachments (fingers / other objects) responding to the preset time presented in the description on the password or pass phrase, the blinking of the eyes reacting to the movement of the face at a specific time, Or the like.

The split focusing means 21b controls the image pickup device 11 of the display device 10 to transmit a control command so as to perform auto focusing for each object previously set for user authentication.

The object recognizing means 21c receives the photographic data photographed by the image pickup device 11 in a state in which the pre-set divided auto focusing for each object is performed by the split focusing means 21b, And extracts individual object data divided into focused objects.

The motion vector analyzing means 21d extracts a motion vector for each object data extracted by the object recognizing means 21c by using a change of pixels according to the shooting time.

The authentication judging means 21e judges whether or not each copper wire of the motion vector extracted from each object data is matched with the password stored in the storage unit 22 by the authentication UI implementing means 21a or the copper wire of the gesture per object on the pass phrase .

Accordingly, the authentication determination means 21e performs authentication processing for the user when the copper wire of the gesture per object on the password or pass phrase and the copper wire of the extracted movement vector are matched in all the objects.

Fig. 2 is a view for explaining the display device 10 and the image pickup device 11 of Fig. 1. Referring to FIGS. 1 and 2, an imaging device 11 is formed at the top of the front of the display device 10 in a fixed or detachable manner. Here, the imaging apparatus 11 sets an area for the user and performs shooting. That is, as shown in Fig. 2, the imaging apparatus 11 photographs a specific area A formed in a circular shape, a quadrangle shape, or other shape, and outputs the photographed data to the display device 10 in real time .

Here, the image output to the display device 10 may be as shown in FIG. 2C. In this case, the first focuses f1, The second focus f2, the third focus f3 to the n-th focus (fn, n is a natural number of 4 or more), or the like.

Here, the first focus f1 may be automatically designated by the split focus means 21b as the user's eye, the second focus f2 as the user's mouth, and the third focus f3 as the user's face. In addition, when an attachment such as a hand or an item carried by a user is placed on the area A, autofocusing can be performed by the split focusing means 21b.

3 is a flowchart illustrating a user authentication method using the mission-execution gesture recognition according to the present invention. Referring to FIG. 1 to FIG. 3, the authentication device 20 outputs a password or a pass phrase indicating a predetermined object-based gesture to the UI screen of the display device 10 (S1).

After the step S1, the authentication device 20 controls the image sensing device 11 of the display device 10 to perform auto focusing which is divided for each object previously set on the image sensing device 11, (Step S2). [0031] As shown in Fig.

After step S2, the authentication device 20 extracts individual object data segmented into individual autofocused objects from the photographic data (S3).

After step S3, the authentication device 20 extracts a motion vector for each object data using the change of the pixels according to the shooting time flow (S4).

After step S4, the authentication device 20 determines whether the motion vector extracted from each object data is matched with the motion vector of the gesture of each object on the pass phrase or pass phrase in step S1 (S5).

After step S5, the authentication device 20 performs an authentication process for the user (S6) if the motion of the object-based gesture on the password or pass phrase matches the motion vector of the extracted motion vector on all objects.

4 is a flowchart illustrating a method of authenticating a user using a mission-execution gesture recognition according to another embodiment of the present invention. Referring to FIGS. 1 to 4, the authentication device 20 controls the image capture device 11 of the display device 10 with respect to a predetermined area A for the user, (A), and receives the photographed image data and a storage request (S11). The photographed image data may be static photographic images.

After step S11, the authentication device 20 outputs a password or pass phrase including one or more gestures of the user's mouth motion, eye flicker, head turning, and finger motion to the UI screen of the display device 10 (S12). Here, the password or the pass phrase may be formed of data indicating the mouth-shaped motion gesture alone, and may be replaced with eye flicker, head turning, hand movements, or a mouth-shaped movement gesture and metadata according to the time of each gesture And can be provided as one type of data.

In a more specific embodiment, the password or pass phrase may be broadly defined for a method of recognizing a face (mission execution gesture), such as changing a mouth shape, a change in eye flicker on a user's face, The addition of a part outside the same face to a predetermined area A, and the like.

Meanwhile, the password or pass phrase may be variously implemented in addition to the word or sentence, and may include various expressive actions that can explain the user's gesture. For example, it can be presented as "read the given word with the index finger on the right side" and "follow the face (avatar) shown before".

After step S12, the authentication device 20 controls the imaging device 11 of the display device 10 so as to perform autofocusing on at least one of the mouth part, eye part, face part and finger part of the user After that, auto focusing is performed and photographed photographic data is received (S13).

After step S13, the authentication device 20 extracts a motion vector by analyzing motion of at least one of the mouth part, eye part, face part, and finger part of the user from the photographic data of step S13 (S14).

After step S14, the authentication device 20 stores each of the motion vectors of the motion vector representing the motion of at least one of the mouth part, eye part, face part, and finger part of the user extracted in step S14 to the storage part 22 The comparison is made with the gesture copper line representing the stored password or the pass phrase to judge whether or not the matching is performed (S15).

After step S15, the authentication device 20 performs an authentication process for the user when both the copper wire of the extracted motion vector and the copper wire of the gesture indicating the stored password or the pass phrase are matched (S16).

Here, the authentication apparatus 20 grants the user's right to use the initial image data stored in the storage unit 22 in step S11, and stores the initial image data in step S11 in the storage unit 22 (S17).

The present invention mainly uses a dynamic mouth-shape tracking of a user when reading a specific word or sentence on a password or pass phrase as an authentication means for a user. In this case, it is possible to implement the password input function without sound, and the possibility of exposure to the surroundings can be reduced. When the authentication in step S16 is completed, the initial image data stored in step 11 is deleted, Such as copying, editing, transmission to the outside via a network, and the like, so that it is possible to perform a function of performing security enhancement on personal information.

The present invention can also be embodied as computer-readable codes on a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device and the like, and also implemented in the form of a carrier wave (for example, transmission over the Internet) .

The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner. And functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers skilled in the art to which the present invention pertains.

As described above, preferred embodiments of the present invention have been disclosed in the present specification and drawings, and although specific terms have been used, they have been used only in a general sense to easily describe the technical contents of the present invention and to facilitate understanding of the invention , And are not intended to limit the scope of the present invention. It is to be understood by those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

10: Display device
11: Imaging device
20: Authentication device
21: Gesture authentication module
21a: Authentication UI implementation means
21b: split focusing means
21c: Object recognition means
21d: Moving vector analysis means
21e: authentication determination means
22:

Claims (7)

A first step of outputting a mission including a gesture of one or more predetermined objects to a user;
A second step of acquiring image pickup data generated by the image pickup apparatus;
A third step of extracting a plurality of pieces of object data divided for each of a plurality of objects including a user's body component from the captured data;
A fourth step of acquiring a motion line of the object-based gesture on the basis of the motion vector of the extracted motion vector by extracting a motion vector according to a photographing time flow for each of the divided object data;
A fifth step of acquiring copper information of a gesture per object stored in advance for user authentication with respect to the mission;
A sixth step of comparing the copper wire of the gesture per object obtained from the photographic data with the copper wire information of the gesture pertaining to the pre-stored object;
Determining whether the user is authenticated according to the comparison result;
And a user authentication method using the mission execution gesture recognition.
The method according to claim 1,
A 0th step of requesting the mission for each user and acquiring photographic data corresponding to the mission, extracting copper line information of a gesture per object from the photographic data, and storing the copper line information in advance;
And a user authentication method using the mission execution gesture recognition.
delete The method according to claim 1,
Wherein the object-specific gesture in the third step includes a step of selecting one of the face movement, eye flicker, head turning, mouth movement, finger movement in response to a preset time, The method of claim 1, further comprising:
An authentication UI implementing means (21a) for outputting a mission including a gesture of at least one object set in advance to a user;
Object recognizing means (21c) for extracting a plurality of object data divided for each of a plurality of objects including a user's body component from the image pickup data generated by the image pickup apparatus;
Motion vector analysis means (21d) for obtaining a motion vector of the object-based gesture based on the motion vector of the extracted motion vector by extracting a motion vector according to the flow of shooting time with respect to each of the divided object data;
A storage unit (22) for storing movement information of a gesture per object for each user in advance for user authentication;
Compares the copper wire of the gesture per object obtained by the motion vector analysis means 21d with the copper wire information of the object gesture stored in advance in the storage unit 22 with respect to the user, An authentication judgment means 21e for judging;
And a user authentication program that uses the mission execution gesture recognition.
delete The method of claim 5,
The user authentication program includes:
A split focusing means (21b) for controlling to perform autofocusing, which is divided for each object previously set in the image pickup apparatus, before receiving the image pickup data;
And a user authentication program that uses the mission execution gesture recognition.

Images