KR20120002110A - Computer security system using hand shape image, computer security method using hand shape image and recording medium thereof - Google Patents

Abstract

PURPOSE: A computer security device using a hand action image, a computer security method using a hand action image, and a recording medium thereof are provided to determine whether to unlock by recognizing a user image photographed by a camera module, thereby enhancing security. CONSTITUTION: A camera module(10) is connected to a computer to photograph a user image. An image recognizing unit(20) applies a skin color detecting algorithm based on a user image signal corresponding to the user image to recognize the user image. An image analyzing unit(30) calculates an image matching rate by comparing the user image with a target image stored in a memory. An image control unit(40) controls locking or unlocking of the computer based on the image matching rate. The user image is an image based on hand actions of a user.

Description

COMPUTER SECURITY SYSTEM USING HAND SHAPE IMAGE, COMPUTER SECURITY METHOD USING HAND SHAPE IMAGE AND RECORDING MEDIUM THEREOF}

The present invention relates to a computer security device and a security method. More particularly, the present invention relates to a computer security apparatus using a hand gesture image, a computer security method using a hand gesture image, and a recording medium thereof.

1 is an exemplary screen showing a password input window for conventional computer security. As shown in Figure 1, the existing personal computer and laptop security is to open a password input window on the screen and enter the password using a keyboard. Therefore, there is a problem that can be easily exposed to the people around it vulnerable to security.

In addition, in the case of inputting a password for unlocking a personal computer, a computer user may have to perform a computer unlock by directly inputting a password using a keyboard every time in a computer lock situation that may occur frequently.

On the other hand, in recent years, it has become common to mount a digital camera on a personal computer or a laptop and the like, and image recognition and processing techniques for images captured using the digital camera have been diversified.

Therefore, there is a need for a computer security device or a computer security method that can easily perform security using a digital camera mounted on the computer and replace the existing password or password keyboard input method.

The present invention has been made in view of the above necessity, and an object of the present invention is a computer security device using a hand gesture image that can perform computer unlocking by recognizing a user image captured by a camera module when using a personal computer or a notebook. And computer security methods.

An object of the present invention as described above, the camera module is connected to a computer for capturing a user image in a certain image area; Image recognition means for receiving a user image signal corresponding to the captured user image and recognizing the user image by applying a skin color detection algorithm based on the received user image signal; Image analysis means for comparing the recognized user image with the target image stored in the memory means to calculate an image matching rate; And image control means for controlling the locking or unlocking of the computer for security based on the calculated image matching rate.

 The user image may be a hand gesture image based on a hand gesture of a computer user, and the target image may be achieved by providing a computer security device using a hand gesture image, characterized in that a hand gesture image corresponding to unlocking of a computer.

The camera module is preferably activated via a keyboard or mouse.

The camera module preferably includes a charge coupled device or a CMOS image sensor.

The predetermined image area preferably includes a hand gesture image and a background image.

The skin color detection algorithm is preferably an algorithm for separating the hand gesture image from the background image based on the color value information of the skin color preset in the YCbCr space.

Preferably, the background image is a constant image area in which the image recognition means recognizes the hand gesture image.

The calculated image matching rate is preferably the shape matching rate of the hand gesture image and the target image.

On the other hand, an object of the present invention is another category, the camera module is connected to the computer to capture a user image in a certain image area (S110); Receiving, by the image recognition means, a user image signal corresponding to the captured user image (S120); Recognizing, by the image recognition means, a user image by applying a skin color detection algorithm based on the received user image signal (S130); Calculating image matching rates by comparing the recognized user image with the image of the target image stored in the memory means (S140); And controlling, by the image control means, locking or unlocking the computer for security based on the calculated image matching rate (S150).

 The user image may be a hand gesture image based on a hand gesture of a computer user, and the target image may be achieved by providing a computer security method using a hand gesture image, characterized in that a hand gesture image corresponding to unlocking of a computer.

Before the imaging step S110 of the camera module, the camera module is activated through a keyboard or a mouse (S105).

In the control step S150 of the image control means, when the calculated image matching rate is less than a predetermined value, the computer keeps a locked state and the camera module imaging step S110 to the image matching rate calculation step S140 of the image analyzing means are performed. Is performed repeatedly, and

In the control step S150 of the image control means, when the calculated image matching rate is equal to or greater than a predetermined value, the computer is preferably unlocked.

In the user image recognition step (S130) of the image recognition means, the skin color detection algorithm is preferably an algorithm for separating the hand gesture image from the background image based on the color value information of the skin color set in the YCbCr space.

On the other hand, the object of the present invention can be achieved in another category by providing a recording medium on which a computer readable program capable of executing a computer security method using hand gestures is recorded.

According to an embodiment of the present invention as described above, it is possible to determine whether to unlock the computer by recognizing the user image captured by the camera module when using a personal computer or a notebook, thereby improving user convenience and enhancing security. have.

In addition, it is possible to utilize the pre-installed camera module and the application algorithm is simple, it is possible to perform computer security at low cost.

1 is an exemplary screen showing a password input window for conventional computer security;
2 is a block diagram showing a configuration according to an embodiment of a computer security device using the present invention gesture image,
3 is a view showing an example of a hand gesture according to an embodiment of the computer security device using the hand gesture image of the present invention,
4A is an exemplary screen shot of a hand gesture image according to an embodiment of a computer security apparatus using a hand gesture image of the present invention;
4B and 4C are exemplary screens showing a shape of a hand gesture image captured and a shape of a pre-stored target image according to an embodiment of the computer security apparatus using the hand gesture image of the present invention;
5 is a flowchart sequentially showing an embodiment of a computer security method using a hand gesture image of the present invention.

<Computer Security Device Configuration>

2 is a block diagram showing a configuration according to an embodiment of the computer security device using the present invention gesture image. As shown in FIG. 2, this embodiment includes a camera module 10, an image recognition means 20, an image analysis means 30, and an image control means 40.

According to the present embodiment, when the camera module 10 captures a user image of a predetermined user for use security of a computer such as a personal computer (PC) or a laptop computer, the image recognition means 20 receives a user image. Image recognition means 30 compares the image matching rate with the previously stored target image, and causes the image control means 40 to control the unlocking of the computer based on the image matching rate to perform computer security. Done.

In this case, the camera module 10 is connected to a computer to capture a user image in a certain image area, and a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) image sensor is used. Can be used. In this case, the predetermined image area is used to identify a location where the user image should be located so that image recognition and analysis can be easily performed, and to distinguish it from a user image that is not intended to unlock a computer. In addition, the user image should be an image in which diversity and stability are considered in order to faithfully achieve the purpose of security, and a hand gesture image based on the hand gesture of a computer user is suitable.

The image recognizing means 20 receives a user image signal corresponding to the captured user image, and serves to recognize the user image by applying a skin color detection algorithm based on the received user image signal. The image recognition means 20 may be performed by applying a computer programmed skin color detection algorithm to a central processing unit (CPU) and a memory. Such a central processing unit (not shown) and memory (not shown) are suitable as a direct method to use the central processing unit and the memory of the computer to be secured.

In addition, the skin color detection algorithm is an algorithm that separates the hand motion image from the background image based on the color value information of the skin color preset in the YCbCr space, and is applied by computer programming as described above. Here, YCbCr is a type of color space used in an imaging system, where Y is a luminance component and Cb and Cr are color difference components. RGB (red cyan) is difficult to apply to the algorithm due to the influence of contrast, and since the color difference components Cb and Cr of the camera's YCbCr signal are less sensitive to changes in illumination, it is preferable to use this to separate the hand motion image.

Therefore, even when using YCbCr, only the color difference component is used, and color values of skin color (for example, 77 <Cr <127, 133 ≤ Cb ≤ 173) may be used as a model.

The image analyzing means 30 calculates an image matching rate by comparing the recognized user image with the target image stored in the memory means (not shown). In this case, the calculated image matching ratio may use a shape matching ratio that contrasts the shape of the hand gesture image and the target image. That is, when the image recognizing means 20 recognizes the hand gesture image in a certain image area, shape information corresponding to pixel information where the hand gesture image is located in relation to the background image is generated, and compared with the shape information of the previously stored target image. Shape matching ratio can be calculated. Here, the target image is a hand gesture image corresponding to unlocking of the computer, and is an image set in advance for security.

In addition, since the background image is a range in which the image recognition means 20 recognizes the hand gesture image, the background image serves as a limited constant image region, and the hand gesture image and the background image are included in the predetermined image region preset by the computer user.

The image control means 40 serves to control the locking or unlocking of the computer for security based on the calculated image matching rate. Here, the image matching rate is an image matching rate between the user image and the target image, and the present embodiment has been described above as the shape matching rate based on the pixel information occupied by each image.

The image matching rate may have a variable value by setting. For example, when the threshold value is set to 95%, the computer is unlocked only at a higher level, and when it is lower than that, the image matching means and the image recognition means of the camera module 10 ( The user image recognition of 20) and the image matching rate calculation of the image analysis means 30 are repeatedly performed.

3 is a view showing an example of a hand gesture according to an embodiment of the computer security device using the hand gesture image of the present invention. As shown in Fig. 3, if any hand gesture is made on the front of the camera module 10 mounted for the use security of the computer 1, the use of the computer 1 is allowed or compared with the previously stored target image. Disallowed.

4A is an exemplary screen shot of a hand gesture image according to an embodiment of a computer security apparatus using a hand gesture image of the present invention, and FIGS. 4B and 4C are images captured according to an embodiment of the computer security apparatus using a hand gesture image of the present invention. It is an example screen showing the shape of a hand gesture image and the shape of a previously stored target image. As shown in FIG. 4A, a certain image area D1 is set as a hand gesture recognition area, and a user image captured in the hand gesture recognition area is used as a user image for unlocking a computer.

4B and 4C, when the hand gesture image D2 detected by the skin color detection algorithm is the same as the shape of the target image D3 (eg, 95% or more of image matching rate), the lock of the computer is performed. Is released.

<How to secure your computer>

5 is a flowchart sequentially showing an embodiment of a computer security method using a hand gesture image of the present invention. Referring to FIG. 5, in the present embodiment, first, the camera module 10 is connected to a computer to capture a user image in a predetermined image area (S110). In this case, before the image capturing step S110, the camera module 10 may be in a standby state, and thus, activating the camera module 10 through a keyboard (not shown) or a mouse (not shown) (S105). ) May be preceded.

Next, the image recognition means 20 receives a user image signal corresponding to the picked-up user image (S120).

Next, the image recognition means 20 recognizes the user image by applying the skin color detection algorithm based on the received user image signal (S130). Here, the skin color detection algorithm is an algorithm for separating the hand gesture image from the background image based on the color value information of the skin color preset in the YCbCr space.

Next, the image analyzing means 30 compares the recognized user image with the target image stored in the memory means to calculate an image matching rate (S140).

Finally, the computer control method using the hand gesture image is performed by the image control means 40 controlling the locking or unlocking of the computer for security based on the calculated image matching rate (S150).

Here, in the control step (S150) of the image control means 40, if the calculated image matching rate is less than a predetermined value, the computer keeps the lock state and calculates the image matching rate of the camera module imaging step (S110) to image analysis means. Step S140 is repeatedly performed, and

In the control step S150 of the image control means, when the calculated image matching rate is equal to or greater than a predetermined value, the computer may be unlocked to terminate the computer security method.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be understood that the invention may be practiced. Therefore, the embodiments described above are to be understood as illustrative and not restrictive in all aspects. In addition, the scope of the present invention is indicated by the appended claims rather than the detailed description above. Also, it is to be construed that all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts are included in the scope of the present invention.

1: computer
10: camera module
20: image recognition means;
30: image analysis means
40: image control means

Claims (12)

A camera module connected to the computer to capture a user image in a certain image area;
Image recognition means for receiving a user image signal corresponding to the captured user image and recognizing the user image by applying a skin color detection algorithm based on the received user image signal;
Image analysis means for comparing the recognized user image with the target image stored in the memory means to calculate an image matching rate; And
And image control means for controlling the locking or unlocking of the computer for security based on the calculated image matching rate.
The user image is a hand gesture image based on a hand gesture of a computer user.
And the target image is the hand gesture image corresponding to the unlocking of the computer.
The method of claim 1,
And the camera module is activated through a keyboard or a mouse.
The method of claim 1,
And the camera module comprises a charge coupled device or a CMOS sensor.
The method of claim 1,
And the predetermined image area includes the hand gesture image and a background image.
The method of claim 4, wherein
The skin color detection algorithm is an algorithm for separating the hand gesture image from the background image based on color value information of skin color preset in a YCbCr space.
The method of claim 4, wherein
And the background image is a predetermined image area in which the image recognition means recognizes the hand gesture image.
The method of claim 1,
And the calculated image matching rate is a shape matching rate of the hand gesture image and the target image.
A camera module connected to a computer to capture a user image in a predetermined image area (S110);
An image recognition means receiving a user image signal corresponding to the picked up user image (S120);
Recognizing, by the image recognizing means, the user image by applying a skin color detection algorithm based on the received user image signal (S130);
Calculating image matching rates by comparing the recognized user image with the target image stored in the memory means (S140); And
And controlling, by the image control means, locking or unlocking the computer for security based on the calculated image matching rate (S150).
The user image is a hand gesture image based on a hand gesture of a computer user.
And the target image is the hand gesture image corresponding to the unlocking of the computer.
The method of claim 8,
Before the imaging step (S110) of the camera module,
The camera module is activated via a keyboard or a mouse (S105); Computer security method using a gesture image further comprising a.
The method of claim 8,
In the control step (S150) of the image control means, when the calculated image matching rate is less than a predetermined value, the computer maintains a locked state and calculates the image matching rate of the camera module imaging step (S110) to the image analysis means. Step S140 is repeatedly performed, and
And in the controlling step (S150) of the image control means, when the calculated image matching rate is equal to or greater than a predetermined value, the computer is unlocked.
The method of claim 8,
In the user image recognition step (S130) of the image recognition means,
The skin color detection algorithm is an algorithm for separating the hand gesture image from the background image based on color value information of a preset skin color in a YCbCr space.
12. A recording medium having recorded thereon a computer readable program for executing the computer security method of any one of claims 8-11.

Images