KR20170117786A - Celebrity Face Cut-out and Alternative Method that Appear in the Visual Media - Google Patents

Abstract

The present invention relates to a system for blocking and replacing a face of a person appearing on a video medium such as a TV or a monitor. In this embodiment, when a famous person who dislikes a viewer appears on the same video medium, Image, or to substitute a positive image when a celebrity that a viewer likes comes up.
According to an embodiment of the present invention, there is provided a method of broadcasting a program, the method comprising: (a) receiving image information of a broadcast program; (b) recognizing a face image and identification information of a person in the image information; (c) masking the face image of the recognized person; And (d) outputting a masked image to the image medium, wherein the masking is an operation of intercepting the face image of the person or replacing the face image with the selected image. And an alternative method.

Description

[0001] The present invention relates to a celebrity face cut-out and alternate system for a face image,

The present invention relates to a method for blocking and replacing a face of a person appearing on a video medium such as a TV or a monitor. In this embodiment, when a famous person who dislikes a viewer appears on the same video medium, Image, or to substitute a positive image when a celebrity that a viewer likes comes up.

In recent years, TVs have evolved into smart TVs, Internet TVs, etc., providing various functions and contents to users, and are used by many users.

Programs that are broadcasted on TV are offered in various fields such as drama, entertainment, sports, documentary, and news.

When a viewer dislikes a TV program, a viewer may switch to another channel or turn off the TV power source itself.

This is because it is not a content production structure in which a program cast can be determined according to a viewer's preference in the production of a TV program, and a method of blocking video information of a cast in a TV program is not provided.

If the viewer switches from one channel to another or turns off the TV, the viewer will not be able to receive the video information and other broadcast information of the program that he or she originally wanted to receive. And the like are frequently acquired.

The information about the cast in the TV program may be acquired in advance through a preview image of the program or related articles for posting information about the program, but this is merely an indirect measure.

DISCLOSURE OF THE INVENTION In order to solve the above problems, in order to solve the above-mentioned problem, when a famous person hated by a viewer appears on the basis of the preference of a viewer while watching a TV program, the face is blocked or replaced with a negative image, It is an object of the present invention to provide a method of replacing the image with a positive image.

According to an embodiment of the present invention, there is provided a method of broadcasting a program, the method comprising: (a) receiving image information of a broadcast program; (b) recognizing a face image and identification information of a person in the image information; (c) masking the face image of the recognized person; And (d) outputting a masked image to the image medium, wherein the masking is an operation of intercepting the face image of the person or replacing the face image with the selected image. And an alternative method.

According to an embodiment of the present invention, the method further includes a step of pre-designating a masking target person according to a user's selection before the step (c), so that when a face of a person designated in advance by the user appears on the image, And a masking unit.

The method may further include the step of designating an emoticon for the person to be masked according to the user's selection.

According to an embodiment, the step (c) may be performed in real time according to a user's selection.

In addition, by transmitting the masked image image and the related data to the statistics server, the user's preference using the image medium can be collected in real time.

According to an embodiment of the present invention, the face image and the identification information of the person are stored in the microcomputer in the image medium.

In addition, the face image and the identification information of the person stored in the microcomputer may be periodically updated.

On the other hand, when the name of the person is inputted by pressing the keyboard of the controller, the face image of the person is outputted to one side of the image medium, and when the user selects the outputted face image, the face is replaced with the blocked or preset emoticon .

According to an embodiment of the present invention, the step (b) may include calculating a face recognition rate by comparing a face image recognized in the image information with a face image stored in the microcomputer, And recognizes the facial image and identification information of the person by calculating the voice recognition rate by comparing the facial image and the facial image.

Here, the face recognition rate and the voice recognition rate may be weighted according to the illuminance and the sound environment inside the image screen.

According to the present invention, when a person who is not preferred by a viewer is present on a video medium, it is possible to provide a method of blocking video information of the person without turning the channel.

It is possible to provide a real-time evaluation method of the viewer for the character by investigating the viewer's preference with respect to the character appearing in the program in real time.

The facial recognition rate and the voice recognition rate are weighted by using the facial image and the voice information of the person appearing in the program, thereby effectively implementing the method of blocking the celebrity face and replacing the emoticon.

FIG. 1 is a diagram showing a face image and identification information of a person outputted on a video medium according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a face image replaced with an emoticon according to an exemplary embodiment of the present invention when a person outputting the image is an appeal.
FIG. 3 is a diagram illustrating a face image replaced with an emoticon according to an embodiment of the present invention when a character output from the image medium is inapplicable.
4 is a block diagram illustrating a flow of a celebrity face blocking and replacement method in accordance with an embodiment of the present invention.
5 is a block diagram illustrating a flow of a celebrity face interception and replacement method in accordance with another embodiment of the present invention.
6 is a block diagram illustrating a celebrity face interception and replacement system in accordance with one embodiment of the present invention.
7 is a block diagram illustrating a celebrity face interception and replacement system in accordance with another embodiment of the present invention.

Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference symbols as possible even if they are shown in different drawings. In the following description of the embodiments of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the difference that the embodiments of the present invention are not conclusive.

A celebrity face interception and substitution system according to an exemplary embodiment of the present invention includes: (a) receiving image information of a broadcast program; (b) Recognizing a face image and identification information of a person in the image information; (c) Masking a face image of a recognized person; And (d) And outputting the masked image to the image medium, wherein the masking is an operation of intercepting the face image of the person or replacing the face image with the selected image.

Here, a broadcast program refers to a broadcast unit having a certain theme transmitted to a TV set, a monitor, or other video medium in a home or a public place through radio waves, and all the programs such as a news report, an entertainment program, an entertainment program, . The broadcasting station transmits the video information and receives the video information transmitted from the video medium provided by the user (viewer).

The image information may be, for example, all data to be transmitted to the image, voice and other broadcast programs output to the display unit 100. The face recognition unit 200 may acquire the face image of the person in the image information and the identification information It can play a role of recognizing.

The face image of the person included in the image information may be masked according to the user's preference. Masking may mean masking the face image or replacing it with another image. Specifically, the face image may be mosaicked or replaced with various emoticons.

For example, as shown in FIGS. 1 to 3, the image transmitted to the original image medium may be mosaiced or replaced with an emoticon or an emoticon depending on the user's preference.

The facial image blocking and substitution here may include blocking and substitution of dynamic images as well as blocking and substitution of static images. For example, in order to block and replace a moving face image with respect to a person, the face recognition unit 200 recognizes the video information in real time, sets the blocking and replacement area in real time, and provides the blocking image and the substitute image to the area An operation can be performed. The masked area on the screen can be realized by enlarging or reducing the size of the face included in the image information, if the image information is a moving image (or moving image).

According to an embodiment of the present invention, the method further includes the step of pre-designating the masking target person according to the user's selection before the step (c), and when the face of the person designated in advance by the user appears on the image, The facial image of the person may be masked, and the emoticon for the person to be masked may be designated according to the user's selection, thereby replacing the facial image of the person with the designated emoticons.

The display of the likes or dislikes of a person depends on the user's choice.

For example, the user can pre-designate the masking target person before the masking process of the face image, which is the step (c), and determine whether the person is good or bad. Accordingly, it can be pre-selected whether to mosaic or replace it with an emoticon. In this case, since the face image of the person is automatically masked, the user (viewer) does not have to evaluate the person during the viewing of the image medium.

According to another embodiment, the face image of the person can be masked in real time according to the user's selection. As a post-designation method for the person, it can mean that the face image of the person is masked in real time according to the user's selection while viewing the image information outputted from the display unit. According to another embodiment, it is needless to say that the post designation method may be used in combination with the pre-designation method for the person.

4 and 5 are block diagrams illustrating a flow of a celebrity face blocking and replacement method according to an embodiment of the present invention.

If a database of celebrity face images is constructed, the viewer's real-time evaluation method for celebrities is provided by recognizing the faces of celebrities on the video medium and blocking or replacing the face images of the celebrities.

The facial image and the identification information of the person can be stored in the microcomputer corresponding to the database in the image medium. The facial image and the identification information of the person stored in the microcomputer are updated periodically to reliably block and replace the celebrity face . Here, the microcomputer refers to a medium for storing data for a short time such as a register, a cache, and a memory, and a recording medium capable of storing semi-permanently data such as a CD, a DVD, a hard disk, a Blu-ray disk, a USB memory card, .

In the present invention, by transmitting the masked image image and the related data to the pre-prepared statistical server, it is possible to collect the users' preferences using the image medium in real time. The real-time evaluation method is not necessarily applied to the post-designation method, but may be applied to the case of the pre-designation method of the viewer. It is possible to include not only the selection of whether or not the person is liked or not, but also the case of the pre-designation method for the emoticon as shown in FIG.

Next, with reference to FIG. 6 to FIG. 7, a method and system for blocking and replacing a face image of a person according to an embodiment of the present invention will be described in detail.

6 is a block diagram illustrating a celebrity face interception and replacement system in accordance with one embodiment of the present invention. 7 is a block diagram illustrating a celebrity face interception and replacement system in accordance with another embodiment of the present invention.

Referring to FIG. 6, the system of the present invention for celebrity face interception and replacement method may include a display unit 100, a face recognition unit 200, a user input unit 300, and an image processing unit 400.

Referring to FIG. 1 again, a method of recognizing a face image and identification information of a person will be described in detail. The face recognition unit 200 determines whether or not the face of the person, , Nose, mouth, facial contour, umbrella, and the like. At this time, in order to lower the error rate of the face recognition, the face image may be set to be blocked or replaced only when the size of the face of the selected person is outputted at a predetermined size or more on the screen of the image medium.

The identification information of the person may include various kinds of information such as voice data, a hairstyle, and a body shape. Using the identification information, a matching rate between a person included in the currently output image information and a person designated by the user can be increased .

For example, in the celebrity face interception and replacement method according to an embodiment of the present invention, in step (b), a face recognition rate is calculated by comparing a face image recognized in the image information with a face image stored in the microcomputer, And recognizes the face image and identification information of the person by comparing the voice recognized by the voice recognition unit and the voice stored in the micom to calculate the voice recognition rate.

The face recognition unit 200 may be divided into a face recognition rate calculation unit 210, a voice recognition rate calculation unit 220, and a weight adjustment unit 230 to perform the above operations.

The face recognition rate and the voice recognition rate can be adjusted by varying weights according to the illuminance and the sound environment inside the image screen.

In other words, the facial recognition rate and the voice recognition rate are computed together. In some cases, a higher weight is assigned to the more reliable data among the face recognition rate and the voice recognition rate, so that the matching rate between the person included in the currently output image information and the user specified by the user .

Specifically, when it is difficult to acquire a face contour due to low illuminance within the image plane, the weight of the face recognition rate may be set to 20%, the weight of the speech recognition rate may be set to 80%, and the noise included in the image information may be detected , The accuracy of the recognition rate can be improved by setting the weight of the face recognition rate to 90% and setting the voice recognition rate to about 10%. As described above, the face recognition rate can be freely selected in a range of more than 0% to less than 100%, and the voice recognition rate can be freely selected in a range of more than 0% to less than 100%.

However, the above-described embodiment is merely an example of the celebrity face blocking and replacement method of the present invention. The object of the present invention may be achieved by extracting identification information such as hair style, body shape and the like and adjusting the weight of the extracted identification information together with the face recognition rate.

According to another embodiment of the present invention, when a name of a person is inputted by pressing a key board of a controller, a face image of the person is output to one side of the image medium, and when the user selects a face image, It can be replaced by an emoticon. A thumbnail method can be adopted as an input method such as a user's liking or disliking of a person. Here, a user inputs a signal through a controller, which is an example of the user input unit 300, receives the input signal from an image medium, and can block or replace a face image through the image processing unit 400. [

It is possible to provide a real-time evaluation method of the viewer for the character by investigating the viewer's preference with respect to the character appearing in the program in real time.

According to various embodiments of the present invention as described above, when a person who is not preferred by a viewer is displayed on a video medium, a method of blocking image information of a corresponding person or replacing the image with an image that can display a non- . On the other hand, if the viewer is a favorite person, the image may be replaced with an image that can display the appeal.

In addition, it is possible to provide a real-time evaluation method of a viewer for a character by examining the viewer's preference with respect to a character appearing in the program in real time.

In addition, by weighting the face recognition rate and the voice recognition rate by using the face image and the voice information of the person appearing in the program, it is possible to effectively implement the blocking of the celebrity face and the method of replacing the emoticon.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. Furthermore, the terms "comprises", "comprising", or "having" described above mean that a component can be implanted unless otherwise specifically stated, But should be construed as including other elements. All terms, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used terms, such as predefined terms, should be interpreted to be consistent with the contextual meanings of the related art, and are not to be construed as ideal or overly formal, unless expressly defined to the contrary.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100:
200: Face Recognition Unit
300: User input
400:

Claims (10)

(a) receiving image information of a broadcast program;
(b) recognizing a face image and identification information of a person in the image information;
(c) masking the face image of the recognized person; And
(d) outputting a masked image to an image medium;
, ≪ / RTI &
Wherein the masking is an operation of intercepting or replacing a face image of a person with a selected image. The method according to claim 1,
Prior to step (c)
Further comprising the step of pre-designating the masking target person according to the user's selection,
And automatically masking the face image of the person when the face of the person designated in advance by the user appears on the image. 3. The method of claim 2,
Further comprising the step of designating an emoticon for the person to be masked according to the user's selection. The method according to claim 1,
The step (c)
Wherein the face masking is performed in real time according to a user's selection. 5. The method of claim 4,
And transmitting the masked image image and the related data to the statistic server, thereby collecting the users' preferences using the image medium in real time. The method according to claim 1,
Wherein the face image and the identification information of the person are stored in a microcomputer inside the image medium. The method according to claim 6,
Wherein the face image and the identification information of the person stored in the microcomputer are periodically updated. The method according to claim 1,
When a name of a person is inputted by pressing the keyboard of the controller, a face image of the person is outputted to one side of the image medium, and when the user selects the outputted face image, the face is replaced with a blocked or preset emoticon Face blocking and replacement methods. The method according to claim 1,
The step (b)
A face recognition unit for calculating a face recognition rate by comparing a face image recognized in the image information with a face image stored in the microcomputer,
The voice recognition rate is calculated by comparing the voice recognized in the image information with the voice stored in the microcomputer,
And recognizing the face image and the identification information of the person. 10. The method of claim 9,
Wherein the face recognition rate and the voice recognition rate are weighted according to an illuminance and an acoustic environment inside the image screen.

Images