KR101963200B1 - Real time video contents converting system and method using ACR(Automatic Contents Recognition) - Google Patents

Abstract

The present invention relates to a real-time image conversion system and method using automatic image content recognition technology.
A method for real-time image conversion using an image content automatic recognition technology according to the present invention comprises the steps of: capturing a viewer watching a digital content displayed through a digital image imple- mentation device by a camera device to recognize an object; Determining whether a new object has been added among the objects recognized by the camera apparatus by the digital image implementing apparatus; Estimating a sex and an age according to a face of each object using a facial recognition algorithm by a digital image implementing device if a new object is added; Acquiring video fingerprint-based content meta information provided from a content providing server by a digital image implementing apparatus; Determining whether a new object added based on the video fingerprint-based content meta information acquired by the digital image implementing apparatus corresponds to a viewing age limit; And converting the image being broadcast by performing viewing control according to the parental control information preset by the user by the digital image implementing apparatus when the parental control is in the viewing age limit.

Description

Technical Field [0001] The present invention relates to a real-time image conversion system and a real-time image conversion system using automatic image recognition technology,

The present invention relates to a real-time image conversion system and method, and more particularly, to a system and method for real-time image conversion using an automatic content recognition (ACR) The present invention relates to a system and method for real-time image conversion using automatic image content recognition technology capable of automatically recognizing whether or not an image is displayed,

Today, due to technological advances in the field of TV and broadcasting media, existing analog TV is being transformed into various forms such as digital TV, IPTV, and DMB. Basically, the TV contents providing service is one-sided, that is, when the broadcasting provider unilaterally transmits the broadcasting contents, the user receives the broadcasting contents and outputs them to the TV display.

The most problematic situation in this situation is that general viewers who watch TV are forced to accept contents transmitted from a broadcasting provider. Among the contents provided by the broadcasting provider, there are a large amount of harmful contents such as the contents classified according to the degree of harm and the advertisement contents semi-compulsively broadcast to the unspecified majority. Adults can block this by stopping watching TV themselves (turning them to another channel or turning off the TV) while the harmful content is being broadcast, but it is also difficult for children who are not yet judged to judge whether the content is harmful, Even if it is determined that the content is harmful, it is difficult to stop the TV watching on its own because the self-control ability deteriorates. If such children (or young people) are repeatedly exposed to harmful contents (such as sexually explicit, violent images or various advertisements), such harmful contents may adversely affect the judgment ability, mindset, and values of the child The general view is that the risks are quite high. Therefore, special attention must be paid to watching TV for children or adolescents. In addition, it is necessary to filter (for example, mosaic process the scene or replace it with a natural scenic screen) so that a child or a teenager can not view the scenes as they are, such as sexual or violent scenes displayed on a TV screen .

On the other hand, in response to the above-mentioned demand, Japanese Patent Application Laid-Open No. 10-2010-0016720 (Patent Document 1) discloses "Method and system for blocking parental content and substitute contents in TV broadcast using network" A method for blocking and replacing harmful contents in a TV broadcast using a network includes receiving a channel selection command by a user input by a processor; Performing channel setting according to a channel selection command by a processor; Analyzing broadcast data by an external server; If it is determined by the external server that the broadcast data is not a harmful content, the processor receives the control signal transmitted by the external server in accordance with the determination, and transmits the broadcast data to the switch. When the broadcast data is determined to be the harmful content, Receiving a control signal transmitted by the processor and delivering replacement content to the switch; And outputting broadcast data or substitute contents delivered by the switch to the display.

In the above-described Patent Document 1, since harmful contents are automatically blocked and alternative contents are broadcasted during the broadcast time, it is possible to prevent a child or a teenager from being exposed to watching unwanted contents indiscriminately without a parent However, it is a mechanism of judging the broadcast data in the time domain corresponding to the broadcast classified as the harmful content in advance by the user's choice or the broadcast data preselected by the user's selection as the harmful content, There is a problem in that it is impossible to judge the harmful content with respect to the content or broadcast data that is insufficient.

Japanese Patent Application Laid-Open No. 10-2010-0016720 (Feb. 16, 2010)

The present invention has been made in consideration of the above circumstances in a comprehensive manner, and it is an object of the present invention to provide a method and apparatus for detecting the hazardousness of image contents broadcasted when viewing a video using the Automatic Contents Recognition (ACR) And automatically transforms the visual sensibility of the video according to the age of the viewer and the level of expression of the violence in real time so as to minimize the adverse effects of the sexuality or violence of the harmful contents or video on the adolescents, And to provide a real-time image conversion system and method using the same.

To achieve the above object, according to the present invention, there is provided a system for real-

A digital image implementation in which an ACR (Automatic Contents Recognition) algorithm is applied and a digital content is received from an external device and displayed on a screen and a video fingerprint based query is requested to an external device Device;

And a display unit that is located near the digital image implementing apparatus and is electrically connected to the digital image implementing apparatus, captures an image of a viewer who views the image displayed through the digital image implementing apparatus, recognizes the object, A camera device for transmitting; And

And a content providing server for providing digital content to the digital image implementing apparatus and providing content meta information in response to a video fingerprint query request from the digital image implementing apparatus,

The present invention relates to a method and apparatus for automatically recognizing whether a video content to be broadcast is harmful when viewing a video by a user by using an ACR algorithm applied to the digital video realization device and an object recognition technique using the camera device, Or the level of expression of violence is converted in real time and displayed on the screen.

Here, the digital image implementing apparatus may include:

The image recognition unit compares an image recognized by the camera device with an image stored in a memory to check whether a new object is added. If a new object is added, an image that estimates the sex and age of the new object using a face recognition algorithm A processor;

A signal transmitting and receiving unit for requesting a video fingerprint based query to the content providing server and receiving content meta information as a response to the query request from the content providing server;

A streaming service unit for receiving digital contents from the contents providing server in a streaming manner;

A display unit for displaying the streaming digital contents received through the streaming service unit;

A parental control information input and storage unit for receiving and storing parental control information set by a user;

Acquires the parental control information set by the user, obtains the content meta information based on the video fingerprint information from the content providing server, A parental control module for performing parental control based on the parental control information set by the user if the parental control is based on the parental control; And

And a central control unit for controlling operations of the image processing unit, the signal transmission / reception unit, the streaming service unit, the display unit, the viewing restriction information input and storage unit, the viewing restriction module unit and the camera unit, Lt; / RTI >

At this time, the parental control information input to the parental control information inputting and storing unit may be set by a method such as play stop, mosaic processing, sound removal, etc. of the digital contents according to the age.

In addition, the digital image implementing device may include a smart TV, an IPTV, a cable TV, a satellite TV, a set top box (STB), and the like.

The content providing server may further include:

A content streaming server for providing the digital content to the digital image implementing apparatus in a streaming manner;

A fingerprint server that extracts content fingerprint information from the video and audio content and generates content meta information based on the extracted content fingerprint information; And

Receiving content fingerprint information in cooperation with the fingerprint server, generating parental control information based on the content meta information generated by the fingerprint server, and transmitting a video fingerprint query request And a viewing restriction information generation server for providing content meta information as a response to the viewing restriction information.

At this time, the content fingerprint information may include a fingerprint, a content ID, a channel ID, a time stamp, and the like.

Also, the content meta information may include a content ID, a channel ID, a time stamp, and viewing restriction information.

In addition, the viewing restriction information generating server and the contents streaming server may be packaged as one device and installed near the user's TV or set-top box (STB).

According to another aspect of the present invention, there is provided a method for real-

A real-time image conversion method using an image content automatic recognition technology based on a real-time image conversion system using an image content automatic recognition technology including a digital image implementation device, a camera device, and a content provision server,

a) capturing a viewer who views digital content displayed through the digital image implementing device by the camera device and recognizing the object;

b) determining whether a new object has been added among the objects recognized by the camera device by the digital image implementing device;

c) if the new object is added, estimating the sex and age according to faces of each object using the facial recognition algorithm by the digital image implementing device;

d) acquiring video fingerprint-based content meta information provided from the content providing server by the digital image implementing apparatus;

e) determining whether a new object added based on the video fingerprint-based content meta information acquired by the digital image implementing apparatus corresponds to a viewing age limit; And

and f) performing viewing control according to the parental control information preset by a user by the digital image implementing device, when the parental control is restricted, thereby converting the broadcasting image.

The method may further include receiving digital content provided from the content providing server by the digital image implementing apparatus before step a) and displaying the received digital content on a screen.

If the new object is not added in the determination of step b), the step of returning to step a) may be further included.

The step of estimating the sex and age according to faces of each object using the facial recognition algorithm of step c)

c-1) detecting a face of each object;

c-2) evaluating the image validity of the detected face;

c-3) extracting features of the face on which the image validity is evaluated; And

c-4) estimating the sex and age of the object based on the feature information of the extracted face.

The method may further include requesting a video fingerprint based query by the digital image implementing device to the content providing server based on the estimated sex and age before the step c) and after the step d) ;

And providing video fingerprint-based content meta information as a response to the video fingerprint-based query request by the content providing server.

At this time, the content meta information may include a content ID, a channel ID, a time stamp, and viewing restriction information.

The method may further include returning to the step a) if the viewing age limit is not satisfied in the determination of the step e).

In addition, in the step f), the viewing control may include at least one of stopping digital content play, digital content mosaic processing, and digital content sound removal.

According to the present invention, it is possible to automatically recognize whether a video content to be broadcast when viewing a video object is harmful or not by using an automatic content recognition (ACR) and an object recognition technology by a camera device, It is possible to minimize the adverse effects of the sexuality and violence of the harmful contents and the video on the adolescents by converting the expressiveness of the video material and the expression level of the violence in real time.

1 is a diagram schematically showing a general configuration of a real-time image conversion system using an image content automatic recognition technology according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an internal system configuration of a digital image implementing apparatus of a real-time image conversion system using the image content automatic recognition technology shown in FIG.
3 is a flowchart illustrating an execution process of a real-time image conversion method using an image content automatic recognition technology according to an embodiment of the present invention.
4 is a flowchart specifically showing the contents of steps S301 to S303 of the flowchart of FIG.

The terms and words used in the present specification and claims should not be construed as limited to ordinary or dictionary terms and the inventor can properly define the concept of the term to describe its invention in the best way Should be construed in accordance with the principles and meanings and concepts consistent with the technical idea of the present invention.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. Also, the terms " part, "" module, "and" device " Lt; / RTI >

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

1 is a diagram schematically showing a general configuration of a real-time image conversion system using an image content automatic recognition technology according to an embodiment of the present invention.

Referring to FIG. 1, a real-time image conversion system 100 using an image content automatic recognition technology according to the present invention includes a digital image implementation device 110, a camera device 120, and a content provision server 130 .

The digital image implementing apparatus 110 is a system in which an ACR (Automatic Contents Recognition) algorithm (a kind of software program) is applied to an internal central control unit 110g (to be described later) (E.g., providing server 130), displays it on the screen, and requests a video fingerprint based query to the external device. The digital image implementing apparatus 110 may include a smart TV 111, an IPTV, a cable TV, a satellite TV, a set top box (STB) 112, and the like.

2, the digital image implementing apparatus 110 includes an image processing unit 110a, a signal transmission / reception unit 110b, a streaming service unit 110c, a display unit 110d, a viewing restriction An information input and storage unit 110e, a viewing restriction module unit 110f, and a central control unit 110g.

The image processing unit 110a compares an image recognized through the camera device 120 with an image stored in a memory (not shown) to check whether a new object has been added. If a new object is added, Which is installed in advance by a system developer or an operator of the present invention as a software program of the present invention) to estimate the gender and age of the new object.

The signal transmitting and receiving unit 110b requests a video fingerprint based query to the content providing server 130 and receives the content meta information as a response to the query request from the content providing server 130 . Such content meta information will be described later.

The streaming service unit 110c receives the digital content from the content providing server 130 in a streaming manner.

The display unit 110d displays the streaming digital contents received through the streaming service unit 110c.

The viewing restriction information input and storage unit 110e receives and stores the viewing restriction information set by the user. At this time, the parental control information input to the parental control information inputting and storing unit 110e may be set in a manner such as play stop, mosaic process, and sound cancellation of the corresponding digital content by age.

The viewing restriction module 110f obtains the viewing restriction information set by the user, acquires the content meta information based on the video fingerprint information from the content providing server 130, Based on the information, it is determined whether the parental age restriction is applied to the child and the teenager who need to restrict the parental control. If the parental parental age restriction is satisfied, the parental control is performed according to the parental control information set by the user.

The central control unit 110g includes the image processing unit 110a, the signal transmission / reception unit 110b, the streaming service unit 110c, the display unit 110d, the viewing restriction information input and storage unit 110e, (110f) and the camera device (120), and diagnoses and adjusts the overall state of the system.

1, the camera device 120 is located close to the digital image implementing apparatus 110 and is electrically connected to the digital image implementing apparatus 110, and displays a video image displayed through the digital image implementing apparatus 110 Captures a viewer who views the image, recognizes the object, and transmits the captured image information to the digital image implementing apparatus 110.

The content providing server 130 provides digital content to the digital image implementing apparatus 110 and provides content meta information as a response to a video fingerprint query request from the digital image implementing apparatus 110 do. 1, reference numeral 132a denotes a database of the fingerprint server 132, and reference numeral 133a denotes a database of the parental control information generation server 133. [

The content providing server 130 may include a content streaming server 131 for providing the digital content to the digital image implementing apparatus 110 in a streaming manner; A fingerprint server 132 for extracting content fingerprint information from video and audio content (Reference Content) and generating content meta information based on the extracted content fingerprint information; And the fingerprint server 132, generates the parental control information based on the content meta information generated by the fingerprint server 132, and generates the parental control information from the digital image implementing apparatus 110 And a parental control information generation server 133 for providing content meta information in response to a video fingerprint query request.

At this time, the content fingerprint information may include a fingerprint, a content ID, a channel ID, a time stamp, and the like. Here, such content fingerprint information means feature data indicating the feature of the content, and is also referred to as fingerprint data, DNA data, or gene data. The use of such fingerprint information makes it possible to easily determine whether the data is the same or not, and is widely used in the field of copyright management and the like. For example, in the case of audio data, fingerprint information is generated using various feature data (e.g., frequency, amplitude, etc.) indicating the characteristics of audio data, and in the case of video data, various feature data , Motion vector information of a frame, color information, and the like) can be used to generate fingerprint information.

Also, the content meta information may include a content ID, a channel ID, a time stamp, and viewing restriction information.

The viewing restriction information generating server 133 and the contents streaming server 131 may be constituted by a packaged device and installed near the user's TV (smart TV, IPTV, etc.) or the set-top box (STB).

The real-time image conversion system 100 using the image content automatic recognition technology according to the present invention having the above-described configuration can determine whether the image content to be broadcasted when the user views the video image is harmful to the digital image implementation apparatus 110 The ACR algorithm and the object recognition technology by the camera device 120, and displays the sensibility of the video object or the expression level of the violence in real time according to the age of the viewer and displays it on the screen.

Hereinafter, a real-time image conversion method based on the real-time image conversion system 100 using the image content automatic recognition technology according to the present invention having the above-described configuration will be described.

3 is a flowchart illustrating an execution process of a real-time image conversion method using an image content automatic recognition technology according to an embodiment of the present invention.

Referring to FIG. 3, the real-time image conversion method using the image content automatic recognition technology according to the present invention includes the digital image implementation apparatus 110, the camera apparatus 120, and the content providing server 130 A real-time image conversion method using an image content automatic recognition technology based on a real-time image conversion system (100) using an image content automatic recognition technology, wherein the camera device (120) And recognizes the object by capturing a viewer who watches the digital content (step S301). Here, the method may further include receiving digital content provided from the content providing server 130 by the digital image implementing apparatus 110 and displaying the received digital content on the screen before step S301.

When the camera device 120 captures a viewer and recognizes the object, the digital image implementing device 110 determines whether a new object has been added to the object recognized by the camera device 120 (step S302). If no new object is added in this determination, the process returns to step S301. If a new object is added in the determination, the digital image implementing apparatus 110 estimates the sex and age according to the face of each object using the face recognition algorithm (step S303). Here, the facial recognition algorithm will be described in more detail with respect to estimating the sex and age according to faces of each object.

4 is a flowchart specifically showing the contents of steps S301 to S303 of the flowchart of FIG.

Referring to FIG. 4, in step S301 in FIG. 3, that is, in capturing a viewer who views digital contents by the camera device 120 and recognizing the object, the camera device 120 captures an image of a viewer to acquire an image (Step S301a), and recognizes the object based on the acquired image (step S301b). The image information (data) photographed by the camera device 120 is transmitted to the digital image implementing apparatus 110 and the image processing unit 110a of the digital image implementing apparatus 110 receives the image information The image information (data) is compared with the image information (data) stored in the memory to check whether a new object is added (step S302). If a new object is added, the gender of the new object Estimate your age. That is, the face of a new object is detected first (step S303a). Then, the image validity of the detected face is evaluated (step S303b). Then, the feature of the face on which the image validity is evaluated is extracted (step S303c), and the gender and age of the object are estimated based on the feature information of the extracted face (step S303d).

Referring to FIG. 3 again, after the gender and age are estimated according to the face of the new object by the digital image implementing apparatus 110 as described above, And acquires video fingerprint-based content meta information (step S304).

Here, in the image transformation method according to the present invention, before step S303 and step S304, a digital fingerprint-based query is generated by the digital image implementation device 110 on the basis of the estimated sex and age To the providing server 130; And providing video fingerprint based content meta information as a response to the video fingerprint based query request by the content providing server 130. [ At this time, the content meta information may include a content ID, a channel ID, a time stamp, and viewing restriction information.

As described above, when the digital fingerprint-based content meta information is acquired by the digital image implementation apparatus 110, the digital image implementation apparatus 110 generates a new fingerprint-based content meta information based on the acquired fingerprint- It is determined whether the object corresponds to the viewing age limit (step S305). If it does not correspond to the viewing age limit in this determination, the process returns to step S301. If it is determined that the viewing age limit is met, the digital image implementing apparatus 110 performs viewing control according to the viewing restriction information previously set by the user (step S306) to convert the broadcasting image (step S307). Here, the viewing control may include at least one of stopping digital content (e.g., VOD) play, digital content screen mosaicing, and digital content sound removal.

Hereinafter, the real-time image conversion method using the image content automatic recognition technology according to the present invention will be described in further detail.

1) Using the ACR technology, read the tag of the transmitted video to grasp the information related to the rating of the entire video.

- With the method of the present invention applied, a user (for example, a parent with a child and a teenager's child) first grasps the entire viewership, the audience over 12 years old, the audience over 15 years old, At this time, the tag of the video material is inserted into the video material creator by a specific symbol, code, character, or the like according to the grade according to the age at the time of producing the video material.

2) The age of the viewer (s) is determined by the TV system through the user age recognition camera technology.

- The camera device 120 installed on the TV 111 (see FIG. 1) recognizes the face of an individual or a plurality of viewers, and grasps the age of each viewer individually.

In the case of an individual viewer (for example, 10 years old), the digital image implementing apparatus 110 may not be able to view a viewing grade video image (e.g., 15 years old or older) according to the age of the individual viewer recognized in the camera device 120 (For example, mosaic processing of the screen) or replacing it with a screen of another image.

In the case of a plurality of viewers (for example, 10 and 40 years old), the digital image implementing device 110 may display a viewing grade video image (e.g., a viewer 15 years or older), depending on the age of the youngest viewer recognized in the camera device 120. [ (For example, mosaic processing of the screen) so as not to view the image, or to replace it with a screen of another image.

3) If the video is normally transmitted according to the age of the viewer and displayed on the TV screen, ACR technology recognizes the information about the violence and perceptibility of each scene.

 In other words, while the real-time image conversion TV system (smart TV receiver itself, IPTV, cable TV, satellite TV, set-top box, etc.) plays back video images, And recognizes the degree of violence and sensibility of each video scene in real time through a tag inserted in advance.

4) The TV system (Digital Image Implementation Device) estimates the age of the viewer based on the image information (data) captured by the camera device, and determines the level of violence and selectivity (eg, According to the present invention, the sensible and violent scenes of the video are transformed and transmitted in real time.

That is, the user previously displays a tag for information on the sensibility and the level of violence (upper, middle, and lower) for each of the video scenes, and the digital image implementing apparatus 110 recognizes the tag using the mounted ACR algorithm. At this time, the user can display a tag for the sensibility and the violence level (upper, middle, lower) information for each of the video scenes using a remote controller or the like in advance.

- The user preliminarily sets the violence of the specific age group and the video scene in the TV system, and the sending level of positivity, for example, upper, middle, and lower. For example, if a 16-year-old viewer views a TV alone or a 40-year-old viewer, then a 16-year-old viewer enters the viewing range, no matter how aged 15 or older, The user can pre-set the display level to be automatically converted to " low "

- The automatic conversion of violence and sensibility transmission level (upper, middle, and lower) of the above video scene is applied to all viewers, 12 year olds, 15 years olds,

Let's take a look at an example.

For example, suppose that a couple (husband: 47 years old, wife: 45 years old) and child (16 years old) are watching together video material (including violent scenes)

The TV system (digital image implementation device 110) to which the ACR algorithm is applied recognizes that the video content being transmitted is 15 years or older, and transmits it as it is.

At this time, the ACR algorithm of the TV system (digital image implementing apparatus 110) operates and is applied to the transmitted video in real time, and accordingly, the TV system detects whether the violent scene is included in the transmitted video scene do.

If the video footage being sent contains violent footage and the violent footage is higher than the violence level set by the user (in this case, the parent), even if the current footage is a viewable video content over 15 years of age, (Parent) does not match the level of selectivity and violence set in the TV system and treats the scene with a mosaic or other sound (eg, mosaic treatment of murder or bleeding, dealing with beep sound) , And then automatically moves to the next video scene.

In addition, when only the couple watches the video, the age of the couple is recognized based on the image (image) information photographed by the camera device 120 installed on the TV 111, , So that it is transmitted as it is at the expression level of the existing video without any sanctions.

As described above, the real-time image conversion system and method using the automatic image content recognition technology according to the present invention can be realized by using an automatic content recognition (ACR) It is possible to automatically recognize whether or not the video content to be broadcast is harmful and to minimize the adverse effect of the sexuality or violence of the harmful content or video on the adolescents by realizing the display quality of the video image or the violence level according to the viewer's age There is an advantage.

In addition, when the image conversion method of the present invention as described above is applied, it is possible to express freely according to the creator's intention without imposing a burden on viewing (rating) There are advantages.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but many variations and modifications may be made without departing from the spirit and scope of the invention. Be clear to the technician. Accordingly, the true scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of the same should be construed as being included in the scope of the present invention.

110: digital image implementing apparatus 110a: image processing unit
110b: signal transmission / reception section 110c: streaming service section
110d: Display unit 110e: Parental control information input and storage unit
110f: parental control module unit 110g: central control unit
111: TV 112: set-top box
120: camera device 130: content providing server
131: content streaming server 132: fingerprint server
133: Parental status information generation server 132a, 133a:

Claims (18)

A digital image implementation in which an ACR (Automatic Contents Recognition) algorithm is applied and a digital content is received from an external device and displayed on a screen and a video fingerprint based query is requested to an external device Device;
And a display unit that is located near the digital image implementing apparatus and is electrically connected to the digital image implementing apparatus, captures an image of a viewer who views the image displayed through the digital image implementing apparatus, recognizes the object, A camera device for transmitting; And
And a content providing server for providing digital content to the digital image implementing apparatus and providing content meta information in response to a video fingerprint query request from the digital image implementing apparatus,
The present invention relates to a method and apparatus for automatically recognizing whether a video content to be broadcast is harmful when viewing a video by a user by using an ACR algorithm applied to the digital video realization device and an object recognition technique using the camera device, Or the level of expression of violence is converted into real time and displayed on the screen,
The content providing server,
A content streaming server for providing the digital content to the digital image implementing apparatus in a streaming manner;
A fingerprint server that extracts content fingerprint information from the video and audio content and generates content meta information based on the extracted content fingerprint information; And
Receiving content fingerprint information in cooperation with the fingerprint server, generating parental control information based on the content meta information generated by the fingerprint server, and transmitting a video fingerprint query request And a viewing restriction information generation server for providing content meta information as a response to the viewing restriction information.
The method according to claim 1,
The digital image implementing apparatus includes:
The image recognition unit compares an image recognized by the camera device with an image stored in a memory to check whether a new object is added. If a new object is added, an image that estimates the sex and age of the new object using a face recognition algorithm A processor;
A signal transmitting and receiving unit for requesting a video fingerprint based query to the content providing server and receiving content meta information as a response to the query request from the content providing server;
A streaming service unit for receiving digital contents from the contents providing server in a streaming manner;
A display unit for displaying the streaming digital contents received through the streaming service unit;
A parental control information input and storage unit for receiving and storing parental control information set by a user;
Acquires the parental control information set by the user, obtains the content meta information based on the video fingerprint information from the content providing server, A parental control module for performing parental control based on the parental control information set by the user if the parental control is based on the parental control; And
And a central control unit for controlling operations of the image processing unit, the signal transmission / reception unit, the streaming service unit, the display unit, the viewing restriction information input and storage unit, the viewing restriction module unit and the camera unit, Real - Time Image Conversion System Using Automatic Image Content Recognition Technology.
3. The method of claim 2,
Wherein the viewing restriction information input to the viewing restriction information inputting and storing unit is set in at least one of a play stop, a mosaic process, and a sound cancellation of the corresponding digital content by age.
The method according to claim 1,
Wherein the digital image implementing apparatus includes at least one of a smart TV, an IPTV, a cable TV, a satellite TV, and a set top box (STB).
delete The method according to claim 1,
Wherein the content fingerprint information includes a fingerprint, a content ID, a channel ID, and a time stamp.
The method according to claim 1,
Wherein the content meta information includes a content ID, a channel ID, a time stamp, and viewing restriction information.
The method according to claim 1,
Wherein the viewing restriction information generating server and the contents streaming server are packaged as a single device and installed in the vicinity of a user's TV or set-top box.
A real-time image conversion method using an image content automatic recognition technology based on a real-time image conversion system using an image content automatic recognition technology including a digital image implementation device, a camera device, and a content provision server,
a) capturing a viewer who views digital content displayed through the digital image implementing device by the camera device and recognizing the object;
b) determining whether a new object has been added among the objects recognized by the camera device by the digital image implementing device;
c) if the new object is added, estimating the sex and age according to faces of each object using the facial recognition algorithm by the digital image implementing device;
d) acquiring video fingerprint-based content meta information provided from the content providing server by the digital image implementing apparatus;
e) determining whether a new object added based on the video fingerprint-based content meta information acquired by the digital image implementing apparatus corresponds to a viewing age limit; And
f) performing a viewing control according to parental control information preset by a user by the digital image implementing device to convert an image being broadcasted if the parental control is restricted,
In converting the broadcasting image in step f), the digital image implementing device estimates the age of the viewer based on the image information photographed by the camera device, and determines the level of violence and sensibility A real-time image conversion method using an automatic recognition method of image contents in which sensational and violent scenes of a video are transformed and transmitted in real time.
10. The method of claim 9,
Further comprising the step of: receiving the digital content provided from the content providing server by the digital image implementing apparatus before step a) and displaying the received digital content on a screen.
10. The method of claim 9,
And if the new object is not added in the determination of step b), returning to step a).
10. The method of claim 9,
The step of estimating sex and age according to faces of each object using the face recognition algorithm of step c)
c-1) detecting a face of each object;
c-2) evaluating the image validity of the detected face;
c-3) extracting features of the face on which the image validity is evaluated; And
and c-4) estimating the sex and age of the object based on the feature information of the extracted face.
10. The method of claim 9,
Requesting a video fingerprint-based query to the content providing server by the digital image implementing device based on the estimated sex and age before the step c) and after the step d);
And providing video fingerprint-based content meta information as a response to the video fingerprint-based query request by the content providing server.
14. The method of claim 13,
Wherein the content meta information includes a content ID, a channel ID, a time stamp, and viewing restriction information.
10. The method of claim 9,
The method of claim 1, further comprising the step of returning to step a) if the viewing age limit is not satisfied in the determination of step e).
10. The method of claim 9,
Wherein the viewing control in step (f) includes at least one of stopping digital content playback, digital content mosaicing, and digital content sound removal. delete 10. The method of claim 9,
The method of claim 1, wherein the video content is selected from the group consisting of:

Images