KR102021843B1 - Video provision system using contents for children, and method for providing contents of children based on the same - Google Patents

Abstract

The present invention relates to a video providing system using content for children, and a video providing method therefor. The present invention, the user terminal set (100g) consisting of a plurality of user terminal 100, the network 200, the child video content providing server 300, VR content providing server 400, and the big data collection server 500 In the video providing system 1 using the child-targeted content including the child video content providing server 300, one of the user terminal set (100g) consisting of a plurality of user terminals 100 through the network 200 In response to the request for providing the child content by the user terminal 100 of the control unit 310 to transmit the authentication request message to the user terminal 100, and receives a unique encryption authentication key from the user terminal 100 After storing the encryption authentication key together with the terminal number of the user terminal 100 in the database 330, performing authentication through an error checking method for the encryption authentication key and netting the authentication result. Child content greater identity module 321 for controlling the transceiver 310 through 200 to transmit to the user terminal (100); The children's content authentication module 321 performs decryption on the encryption authentication key, and performs an error checking method for analyzing whether the authentication key is an adult upload or a child upload. In the case of uploading, it is characterized by receiving video content for children.
As a result, it is possible to effectively manage uploading and downloading of children's video content on a website, planning additional business such as characters, and providing an effect of proceeding a copyright contract for providing VR-based children's content.
In addition, it blocks the video including sensational, violent, fearful, imitation, etc. to children at the source, and provides the effect that can be specified through machine learning and deep learning for filtering.

Description

Video provision system using content for children, and method for providing video {Video provision system using contents for children, and method for providing contents of children based on the same}

The present invention relates to a video providing system using a content for children, and a video providing method for the same, and more specifically, to effectively manage uploading and downloading of video content for children to a website, and additional business such as characters The present invention relates to a video providing system using content for children, and a video providing method therefor, to plan, proceed with a copyright agreement for providing VR-based children's content.

Recently, a video sharing site such as YouTube, which allows a user to freely upload a video and downloads the same or another unspecified user through a real time streaming method, has been activated.

However, such a video sharing site has recently been spread by smart phones, but children can easily watch it, but there is no restriction on this, and the technical field is required to block access to harmful contents.

Korean Patent Application No. 10-2008-0089948 "METHOD AND SYSTEM FOR PROVIDING CONTENTS USING A TABLE-TOP INTERFACE"

The present invention is to solve the above problems, to effectively manage the upload and download of video content for children on the website, and to plan additional business, such as characters, copyright agreement for providing VR-based children's content It is to provide a video providing system using the content for children to proceed, and a video providing method for this.

In addition, the present invention provides a video using the content for children to block the video containing the concepts of sensation, violence, fear, imitation, etc. to the child at the source, and to materialize through the machine learning and deep learning for filtering It is to provide a system and a video providing method therefor.

However, the objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, a video providing system using content for children according to an embodiment of the present invention includes a user terminal set 100g consisting of a plurality of user terminals 100, a network 200, and a video content providing server for children. In the video providing system 1 using child-targeted content including the 300, the VR content providing server 400, and the big data collection server 500, the child video content providing server 300 is a network 200. Transmitting and receiving unit to transmit the authentication request message to the user terminal 100 in response to the request for providing the child content by the user terminal 100 of the user terminal set (100g) consisting of a plurality of user terminals 100 through () 310 and receives a unique encryption authentication key from the user terminal 100, and transmits the encryption authentication key to the database number 330 and the terminal number of the user terminal 100; After storing together, the child content authentication module 321 for controlling the transceiver 310 to transmit the authentication result to the user terminal 100 through the network 200 by performing authentication through an error check method for the encryption authentication key. ); The children's content authentication module 321 performs decryption on the encryption authentication key, and performs an error checking method for analyzing whether the authentication key is an adult upload or a child upload. In the case of uploading, it is characterized by receiving video content for children.

At this time, the child video content providing server 300, the IP header and the child video content payload by the authenticated user terminal 100 receives the IP packetized packet data payload included in the IP header Extracting the length information, and analyzing whether it is less than or equal to the preset payload length information and, if it is less than or equal to the preset payload length information, completing the verification; It characterized in that it further comprises.

In addition, the children's content verification module 322 separates payload information from the received packet data to perform image analysis in real time, and extracts a frame image of one frame for a predetermined time during image analysis. Verification of at least one or more of keyword extraction based on sensibility, violence, fear, imitation, subtitles and speech recognition categories in the image is performed.

In addition, the children's content verification module 322, when performing verification on sensibility, violence, fear, imitation, big data based sensational image set DB, violent image set DB, fear image stored in the big data collection server 500 Characterized by determining the search for the set DB, mimic image set DB.

In addition, the children's content verification module 322 transmits an image search request and a frame image for at least one of sensibility, violence, fear, and imitation to the big data collection server 500 through the network 200. After controlling the transceiver 310, the verification result data may be received from the big data collection server 500 as return information.

A video providing system using children's content according to an embodiment of the present invention, and a video providing method therefor, can effectively manage uploading and downloading of video content for children to a website and plan additional projects such as characters. In addition, it provides an effect that can proceed with the copyright agreement for providing VR-based children's content.

In addition, the video providing system using a child-targeted content according to another embodiment of the present invention, and a video providing method therefor, blocks the video including the sensational, violent, fearful, imitation to the child, Machine learning and deep learning for filtering provide concrete effects.

1 is a diagram illustrating a video providing system 1 using content for children according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating components of a child video content providing server 300 in the video providing system 1 using the child-targeted content of FIG. 1.
3 is a diagram illustrating a video providing system 1 using content for children according to another embodiment of the present invention.
4 is a block diagram illustrating components of a child video content providing server 300 in the video providing system 1 using the child-targeted content of FIG. 1.
5 is a flowchart illustrating a video providing method based on a video providing system using content for children according to an embodiment of the present invention.

Hereinafter, the detailed description of the preferred embodiment of the present invention will be described with reference to the accompanying drawings. In the following description of the present invention, detailed descriptions of well-known functions or configurations will be omitted when it is deemed that they may unnecessarily obscure the subject matter of the present invention.

In the present specification, when one component 'transmits' data or a signal to another component, the component may directly transmit the data or signal to another component, and through at least one other component. This means that data or signals can be transmitted to other components.

1 is a diagram illustrating a video providing system 1 using content for children according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating components of a child video content providing server 300 in the video providing system 1 using the child-targeted content of FIG. 1.

First, referring to FIG. 1, a video providing system 1 using child-targeted content includes a user terminal set 100g consisting of a plurality of user terminals 100, a network 200, a child video content providing server 300, The VR content providing server 400 and the big data collection server 500 may be included.

Next, referring to FIG. 2, the child video content providing server 300 includes a transceiver 310, a controller 320, a database 330, and the controller 320 includes a child content authentication module 321, A child content verification module 322, a child content collection module 323, and a child content providing module 324 may be included.

The child content authentication module 321 is a user terminal 100 in response to a request for providing child content by one user terminal 100 from a set of user terminals 100g consisting of a plurality of user terminals 100 through a network 200. The transceiver 310 may be controlled to transmit an authentication request message for the.

The child content authentication module 321 receives a unique encryption authentication key from the user terminal 100, stores the encryption authentication key in the database 330 together with the terminal number of the user terminal 100, and then stores the encryption authentication key in the encryption authentication key. The transmission and reception unit 310 may be controlled to transmit the authentication result to the user terminal 100 through the network 200 by performing authentication through an error checking method.

Here, the children's content authentication module 321 decrypts the encryption authentication key, and may perform an error check method for analyzing whether the authentication key is an adult upload or a child upload. If the video content for children can be received.

The child content verification module 322 receives the IP header and the child video content payload by the authenticated user terminal 100 and packetizes the packetized IP data to extract payload length information included in the IP header. Subsequently, it may be analyzed whether it is equal to or less than the preset payload length information, and when verification is equal to or less than the preset payload length information, verification may be completed.

That is, the video content for children provided by the user terminal 100 is generally set to have a shorter running time than the adult video content, thereby verifying whether the video content for children, the child video content providing server 300 ) To manage the channel for data transmission and reception.

In addition, the child content verification module 322 may separate the payload information from the received packet data and perform image analysis in real time.

The children's content verification module 322 extracts one frame image of a frame for a predetermined time during image analysis, and then extracts keywords based on sensibility, violence, fear, imitation, caption, and voice recognition from the extracted frame image. Verification can be performed.

Here, the children's content verification module 322 is a big data-based sensational image set DB, violent image set DB, fear image set stored in the big data collection server 500 when performing verification on sensibility, violence, fear, imitation Can be determined by searching DB, imitation image set DB.

That is, the child content verification module 322 transmits and receives an image search request and at least one frame image for at least one of sensibility, violence, fear, and imitation to the big data collection server 500 through the network 200. After controlling the unit 310, the verification result data may be received from the big data collection server 500 as return information.

Accordingly, the big data collection server 500 stores various pattern images corresponding to sensibility, violence, fear, and imitation for verification of the received frame image. Various pattern image information or various pattern images are stored. Compares the patterns included in the frame image with the tilted, inverted, pre-determined angles, enlarged, and reduced angles to determine the sensibility, violence, fear, and imitation in the frame image. .

On the other hand, when the big data collection server 500 receives the image information for a predetermined time from the children's content verification module 322, not a frame image of the video content for children, the specific of the pixel included in the image information, that is, The characteristics of the pixel can be extracted from the intensity of the pixel, the color of the pixel, the lines formed by the pixel, and the shape in which the pixel changes over time. In addition, the big data collection server 500 determines that the pixel including the image information and the characteristics similar to the characteristics of the pixel for each pattern image are similar ranges. That is, the big data collection server 500 judges the pixel from which the feature is extracted as the reference pixel, and determines the similarity between the reference pixel and the neighboring pixels, and if it is determined to be similar, selectivity, violence, fear, and imitation. You can judge by. Here, the similarity is a concept including a difference in contrast between pixels or a distance between pixels.

The children's content collection module 323 has no sensibility, violence, fear, or imitation by the children's content verification module 322, and even in extracted keywords based on subtitles and voice recognition, sensibility, violence, fear, mimicry If it is determined that there is no, the children's video content payload information received from the user terminal 100 in real time by the children's content verification module 322 to the database 330 using the terminal number of the user terminal 100 as metadata. Can be stored.

In contrast, the child content collection module 323 detects at least one or more of sensibility, violence, fear, and imitation by the child content verification module 322. If at least one of sensibility, violence, fear, and imitation is also detected in the extracted keyword according to subtitles and voice recognition, the children's video content page is received in real time from the user terminal 100 by the children's content verification module 322. After performing the graphic operation to delete the frame image or the video information or the audio information detected from the load information, or to cover the viewing mark with the corresponding pattern image, or to add a noise voice signal to the audio information, the user terminal 100 ) Can be stored in the database 330 using the terminal number as metadata.

Children content providing module 324 is a real-time streaming method or download method for the video content for children stored in the database 330 by the keyword or category search by a plurality of user terminals 100 constituting the user terminal set (100g). The transceiver 310 may be controlled to receive the transmission request through the network 200.

To this end, the child content providing module 324 may be configured as a user terminal according to a child content transmission request by one user terminal 100 from the user terminal set 100g including a plurality of user terminals 100 through the network 200. The transmitter / receiver 310 may be controlled to transmit the authentication request message for 100.

The child content providing module 324 receives a unique encryption authentication key from the user terminal 100, stores the encryption authentication key in the database 330 together with the terminal number of the user terminal 100, and then stores the encryption authentication key in the encryption authentication key. By performing authentication through an error check method for the authentication, the transmission and reception unit 310 may be controlled to transmit the child video content requested to be transmitted through the network 200 to the user terminal 100 when the authentication is completed.

Here, the child content providing module 324 decrypts the encryption authentication key, and may perform an error checking method for analyzing whether the authentication key is an adult download or a child download. If the video content for children can be provided.

3 is a diagram illustrating a video providing system 1 using content for children according to another embodiment of the present invention. 4 is a block diagram illustrating components of a child video content providing server 300 in the video providing system 1 using the child-targeted content of FIG. 1.

First, referring to FIG. 3, the video providing system 1 using content for children further includes a character commercialization terminal set 600g including a plurality of character commercialization terminals 600 in the components of FIG. 1, and each user. The terminal 100 may perform data transmission / reception with a headed mounted display device (hereinafter referred to as an HMD device) 100a in a short range wireless communication method.

Next, referring to FIG. 4, the controller 320 of the children's video content providing server 300 includes a character commercialization module 325, a VR content providing module 326, and a big data-based customized providing module in the component of FIG. 2. 327 may be further included.

Hereinafter, the children's video content providing server 300 will be described in detail based on components that are different from those of the controller 320 of FIG. 2.

The character commercialization module 325 extracts a character from the children's video content stored in the database 330 and requests the network 200 according to a request of one of the plurality of character division terminals 600 corresponding to the character division terminal set 600g. The transmission and reception unit 310 may be controlled to transmit to the requested character business unit terminal 600.

Accordingly, when the character commercialization module 325 receives the character commercialization request as a result of the self-determination by the character division terminal 600, the user terminal 100 corresponding to the metadata for the video content for children to the database 330. Through the character commercialization transaction request to the terminal number of may control the transceiver 310 to perform the copyright agreement.

As a result, when the copyright agreement is completed, the character commercialization module 325 may provide the user terminal 100 with a process of paying a preset fee for the character business in the character business through the copyright electronic contract agreement in the database 330.

The VR content providing module 326 is susceptible through a query for providing VR content through the network 200 to the user terminal 100 that provided the video content for children commercialized by the character commercialization module 325. If present, VR content may be generated and stored in the database 330.

To this end, the VR content providing module 326 determines two left and right focal positions and the number of focal points for the video content for children corresponding to the two-dimensional image, and then the two multiply corresponding to the determined two left and right focal positions and the number of foci. The focal length for the focal two-dimensional image content is calculated.

In addition, the VR content providing module 326 calculates a depth value proportional to a distance from the focal position of each of the two focal two-dimensional image contents to the center point of the focal position of the counterpart image content in the multi-focus two-dimensional image content. A multifocal two-dimensional image content is synthesized according to two depth values.

Subsequently, the VR content providing module 326 uses two multi-focus two-dimensional image contents and children's video contents corresponding to the existing two-dimensional images to zero-time parallax of the children's video contents corresponding to the two-dimensional images (Zero Parallax). ) As the image data, the multi-focus two-dimensional image content corresponding to the image corresponding to the left focus is set to the left parallax image data, and the multi-focus two-dimensional image content corresponding to the image corresponding to the right focus is set to the right parallax image data. The left eye image data is generated by identifying and applying left parallax direction pixel shift information based on a disparity angle of at least one left parallax image data based on the identified zero parallax, and at least one based on the identified zero parallax. Based on the right angle of the right parallax image data, the right direction pixel movement information is identified and applied. It generates data can be stored by the terminal number of the user terminal 100 in the database 330 with metadata.

Big data-based custom provision module 327 is a machine learning algorithm for the verification result data for the selection of keywords based on sensibility, violence, fear, imitation, subtitles and voice recognition for children's video content stored in the database 330 Analyze and issue delete management commands.

More specifically, the machine learning algorithm used in the big data-based custom provision module 327 may be one of a decision tree (DT) classification algorithm, a random forest classification algorithm, and a support vector machine (SVM) classification algorithm.

The big data-based customized provision module 327 analyzes the verification result data stored in the verification categories such as sensibility, violence, fear, imitation, keyword extraction, and the like in the database 330 and analyzes the verification result data, respectively. Additional verification result data may be derived as a result of extracting the information and learning the extracted feature information using at least one of a plurality of machine learning algorithms.

That is, the big data-based custom provision module 327 may apply an ensemble structure composed of a plurality of complementary machine learning algorithms to improve the accuracy of the verification result.

Decision tree classification algorithm is a method of learning the tree structure to derive the result, it is easy to interpret and understand the result, the data processing speed is fast, and the rule can be derived based on the search tree. RF can be applied to improve the low classification accuracy of DT. The random forest classification algorithm is a method of slaughtering a result of ensemble of a plurality of DTs, and it is more difficult to understand the result than the DT, but the result accuracy may be higher than the DT. SVM can be applied to improve overfitting that can occur through DT or RF learning. The SVM classification algorithm classifies data belonging to different classifications on a plane basis, and generally has high accuracy and may have low sensitivity to overfitting.

After machine learning, the big data-based custom provision module 327 may perform deep learning by utilizing additional verification result data, which is refined data distributed and stored in each verification category. Here, the deep learning method is used when the verification request by the child content verification module 322 to the next big data collection server 500 for each verification category formed by analyzing the additional verification result data by the big data-based custom provision module 327. Transmitting / receiving unit 310 to provide the deep data execution result of the verification deep learning for the child video content provided on the child video content providing server 300 corresponding to the distributed system to the big data collection server 500 through the network 200 Can be controlled.

Accordingly, the big data collection server 500 minimizes a decrease in cycle time, which is a time required for one entire process, and a maximum time, Tact time, in the repetitive operation according to the image retrieval request. In this way, it can be upgraded and executed according to the conversion and application of the search program.

5 is a flowchart illustrating a video providing method based on a video providing system using content for children according to an embodiment of the present invention. Meanwhile, hereinafter, the process will be briefly described with reference to FIG. 5 only within a range that does not overlap with the above description with reference to FIGS. 1 to 4. Referring to FIG. 5, the child video content providing server 300 requests for providing child content by one user terminal 100 from a set of user terminals 100g including a plurality of user terminals 100 through a network 200. In step S11, the authentication request message for the user terminal 100 is transmitted.

After step S11, the child video content providing server 300 receives a unique encryption authentication key from the user terminal 100 and stores the encryption authentication key together with the terminal number of the user terminal 100 in the database 330. Thereafter, authentication is performed through an error checking method for the encryption authentication key and the authentication result is transmitted to the user terminal 100 through the network 200 (S12).

After step S12, the child video content providing server 300 performs verification on the child video content of the authenticated user terminal 100 (S13).

After the step S13, the child video content providing server 300 collects the child video content through the management of the channel for transmitting and receiving data on the child video content providing server 300 for the verified user terminal 100. (S14).

After operation S14, the child video content providing server 300 may search for the child video content stored in the database 330 by keyword or category search by the plurality of user terminals 100 forming the user terminal set 100g. A transmission request through a real time streaming method or a download method is received through the network 200 (S15).

After step S15, the child video content providing server 300 receives a unique encryption authentication key from the user terminal 100 and stores the encryption authentication key together with the terminal number of the user terminal 100 in the database 330. After that, authentication is performed through an error checking method for the encryption authentication key, and upon completion of authentication, the child video content requested for transmission through the network 200 is transmitted to the user terminal 100 (S16).

The invention can also be embodied as computer readable code on a computer readable recording medium. Computer-readable recording media include all kinds of recording devices that store data that can be read by a computer system.

Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, optical data storage devices, and the like, which are also implemented in the form of carrier waves (eg, transmission over the Internet). It also includes.

The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. And functional programs, codes and code segments for implementing the present invention can be easily inferred by programmers in the art to which the present invention belongs.

As described above, the present specification and drawings have been described with respect to preferred embodiments of the present invention, although specific terms are used, it is only used in a general sense to easily explain the technical contents of the present invention and to help the understanding of the present invention. It is not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention can be carried out in addition to the embodiments disclosed herein.

1: Video providing system using content for children
100: user terminal
100g: user terminal set
200: network
300: server providing video content for children
310: transceiver
320: control unit
321: Children's content authentication module
322 children's content verification module
323: Children's Content Collection Module
324: Children's content provision module
325: character commercialization module
326: VR content provision module
327: Big data based customized module
330: Database
400: VR content providing server
500: Big Data Collection Server

Claims (5)

A user terminal set 100g including a plurality of user terminals 100, a network 200, a child video content providing server 300, and a big data collection server 500; And character commercialization terminal set 600g consisting of a plurality of character commercialization terminal 600; In the video providing system 1 using the child-targeted content, including, the child video content providing server 300,
Send an authentication request message for the user terminal 100 in response to a request for providing the child content by the user terminal 100 from the user terminal set 100g including the plurality of user terminals 100 through the network 200. Controls the transceiver 310, receives a unique encryption authentication key from the user terminal 100, and stores the encryption authentication key in the database 330 with the terminal number of the user terminal 100, the encryption authentication key A child content authentication module 321 for controlling the transceiver 310 to perform authentication through an error checking method for transmitting the authentication result to the user terminal 100 through the network 200;
The IP header and the child video content payload by the authenticated user terminal 100 receive the IP packetized packet data, extract payload length information included in the IP header, and then preset payload length information. If it is less than the preset payload length information by analyzing whether or not, the verification is completed, but the video content for children provided from the user terminal 100 is set to a state in which the running time is generally divided shorter than the adult video content To manage the channel for data transmission and reception on the child video content providing server 300 by verifying whether the video content for children using the dots,
Performs video analysis in real time by separating payload information from received packet data, extracts one frame image among frames for a preset time during video analysis, and then selects, violent, fears, and mimics the extracted frame image. , Verification including keyword extraction based on subtitles and voice recognition, but verification of sensibility, violence, fear, imitation, big data based sensational image set DB stored in big data collection server 500, violent images Determining by searching the set DB, fear image set DB, mimic image set DB,
After controlling the transceiver 310 to transmit an image search request and a frame image for at least one of sensibility, violence, fear, and imitation to the big data collection server 500 through the network 200, and then verifying A child content verification module 322 for receiving the result data from the big data collection server 500 as return information;
When the children's content verification module 322 verifies that there is no sensibility, violence, fear, or imitation, and extracted keywords based on subtitles and voice recognition do not have sensibility, violence, fear, or imitation, children's content The child video content payload information received from the user terminal 100 in real time by the verification module 322 is stored in the database 330 using the terminal number of the user terminal 100 as metadata,
As a result of the verification by the children's content verification module 322, at least one or more of sensibility, violence, fear, and imitation are detected, and at least one of sensibility, violence, fear, and imitation in the extracted keyword according to subtitles and voice recognition. If the abnormality is detected, the frame image or video information or audio information detected in the child video content payload information received in real time from the user terminal 100 by the child content verification module 322 is deleted or the viewing mark is deleted. After performing a graphic operation to cover the image or adding a noise voice signal to the voice information, the child content collection module 323 storing the terminal number of the user terminal 100 as a metadata in the database 330 );
The network 200 transmits a request for transmission through a real-time streaming method or a download method for video contents for children stored in the database 330 by keyword or category search by a plurality of user terminals 100 constituting the user terminal set 100g. While controlling the transceiver 310 to receive through,
Send an authentication request message for the user terminal 100 in response to a child content transmission request by one user terminal 100 of the user terminal set 100g including a plurality of user terminals 100 through the network 200. To control the transceiver 310,
Receive a unique encryption authentication key from the user terminal 100, and stores the encryption authentication key in the database 330 with the terminal number of the user terminal 100, and then authenticate through the error check method for the encryption authentication key When performing the authentication to control the transmission and reception unit 310 to transmit the video content for children requested through the network 200 to the user terminal 100,
After decrypting the encryption authentication key, an error checking method for analyzing whether the authentication key is an adult download or a child download is performed, and in the case of a child download, a child content provision module providing video content for children 324; And
The character business terminal which is requested through the network 200 according to a request of one of the plurality of character business terminal 600 corresponding to the character business terminal set 600g by extracting a character from the video content for children stored in the database 330 ( Control the transmission and reception unit 310 to transmit to 600, and when receiving the character commercialization request as a result of the self-determination by the character division terminal 600, the user corresponding to the metadata for the video content for children to the database 330 Controls the transceiver 310 to perform a copyright agreement through the character commercialization transaction request with the terminal number of the terminal 100, and when the copyright agreement is completed, it is set in advance in the character business through the copyright electronic contract agreement in the database 330 A character commercialization module 325 which provides the user terminal 100 with a process of paying a copyright fee of a ratio; Including;
When judging through the search for the big data based sensational image set DB, violent image set DB, fear image set DB, mimic image set DB stored in the big data collection server 500 by the children content verification module 322,
Big data collection server 500,
A plurality of pattern images corresponding to sensibility, violence, fear, and imitation are stored for verification of the received frame image, and the information of the plurality of pattern images themselves or the inclination of the pattern image, vice versa, Compare the patterns included in the frame image with the preset angles of inclination, enlargement, and reduction to determine the sensibility, violence, fear and imitation in the frame image.
When receiving the image information for a preset time from the child content verification module 322, not a frame image of the video content for children, the contrast of the pixels included in the image information, the color of the pixel, the line formed by the pixel, and The characteristics of the pixels are extracted from the shape of the pixels changing over time, and the pixels including the image information and the characteristics similar to the characteristics of the pixels for each pattern image are determined as similar ranges.
The pixel from which the feature is extracted is judged as the reference pixel, and the similarity between the reference pixel and the surrounding pixels is judged to be similar, and if it is determined to be similar, it is judged as sensational, violent, fearful, or mimic. Or as a concept including a difference in distance between pixels.
delete delete delete delete

Images