KR20100001064A - Method and system for searching contents using image recognition at internet protocol televition - Google Patents

Abstract

PURPOSE: A method and a system for searching contents using image recognition in an internet protocol television are provided to analyze image data obtained from a set top box to generate a search tag, thereby generating contents using the generated tag. CONSTITUTION: A data transceiver(110) receives image data from a set top box. An image processor(120) extracts an image feature included in the image data. A tag for contents search is generated through the extracted feature. A contents database(140) matches one or more tags with the contents. A contents searcher(130) searches contents related to the image data.

Description

METHOD AND SYSTEM FOR SEARCHING CONTENTS USING IMAGE RECOGNITION AT INTERNET PROTOCOL TELEVITION}

The present invention relates to a system and method for searching for content using image recognition in iPi Yi, and more particularly, to a system and method for acquiring an image and analyzing the acquired image to search for content.

Recently, the IPTV service is widely spread, and in particular, the VOD (vedio on demend) download and play (DnP) type service currently being provided by IPTV is expected to be serviced in the future. When a streaming real-time channel broadcasting service is provided to a subscriber, it is expected that the number of users increases.

Conventional IP content search technology uses a menu-based or keyword-based search technology. In the case of the menu-based search technology, the user is provided with the convenience of content search, but the content search is performed step by step, which takes a relatively long time. In particular, when the content to be searched for does not exist in the menu, the user may spend a lot of time for searching and may not acquire the desired content.

In addition, in the case of a keyword-based search technology, a user may search for content quickly and accurately by inputting a keyword to be searched. However, if the user does not recognize the keyword, content search is not easy. In addition, when the keyword input interface is inconvenient, the search using the keyword is not easy.

For this reason, in addition to a menu-based or keyword-based search, a search technique for inputting an image and performing a search based on the input image is required.

Korean Patent Laid-Open Publication No. 2006-0118167 discloses an invention that searches for image contents through image pattern search for an image acquired by a camera of a mobile terminal and induces access to detailed information on the retrieved image contents. In addition, Korean Patent Laid-Open No. 2008-0034248 discloses an invention of searching for a photo stored in a mobile terminal by analyzing a face acquired by a camera of the mobile terminal.

The prior art discloses a method of searching contents by comparing an image acquired by a camera of a mobile terminal with an image to be searched. However, when comparing an image and an image, there is a problem in that re-search is difficult because a keyword is not generated.

In addition, in transmitting an image for retrieval, there is a problem in that a high-speed data service can not be provided smoothly even though a user can be charged a lot because of using radio resources.

An embodiment of the present invention is to generate a tag for searching by analyzing an image obtained from a mobile terminal or a set-top box, and to search for and provide content by comparing the generated tag with a tag included in the search target content.

As a technical means for achieving the above technical problem, the first aspect of the present invention (a) matching and storing at least one tag that can be extracted from the image for the provided content, (b) a set-top box ( receiving image data from a set-top box (STB); (c) analyzing the image data to generate a content search tag; and (d) comparing the content search tag with a tag matching the content. The method may provide a content retrieval method using image recognition in an IPTV including searching for content related to the image data.

In addition, a second aspect of the present invention is a data transceiver for receiving image data from the set-top box, an image processing unit for extracting the features of the image included in the image data to generate a content search tag, from the image for each content And a content search unit for searching for content related to the image data in the content database using the content database and the content search tag, and matching and storing at least one tag that can be extracted with the content. The unit may provide a content retrieval system using image recognition in IPTV, which searches for the content by comparing the content search tag with a tag included in the content.

In addition, a third aspect of the present invention provides an image input unit for providing an input of a search image, an image transmitter for transmitting the image to an IPTV system through a return channel, and a search result from the IPTV system. A set-top box (STB) for providing content search may be provided using image recognition including a search result output unit for receiving a corresponding content list and providing a selection of content.

According to the above-described problem solving means of the present invention, it is possible to generate a search tag by analyzing the image data obtained from the set-top box, it is possible to search the content using the generated tag.

In addition, according to the above-described problem solving means of the present invention, by providing a search tag containing a keyword when searching for an image to compare the search tag and the tag included in the content can improve the search speed and fast re-search is possible In addition, the load of the content retrieval system can be reduced.

1 is a block diagram showing the configuration of an IPTV broadcasting system to which an embodiment of the present invention can be applied.

The IPTV broadcasting system according to the related art includes a broadcaster 1000, a headend system 2000, a network network 3000, and a user terminal 4000.

In addition, the headend system 2000 includes a baseband system 2010, a compression multiplexing system 2020, a conditional access system (CAS) 2030, a back office system 2040, a monitoring system 2050, A media management core (MOC) 2060, a subscriber management system 2070, a data broadcasting system 2080, an electronic program guide (EPG) system 2090, and a return path server system 2100.

The broadcaster 1000 serves to produce, edit, and change broadcast content to provide to the headend system 2000. The broadcaster 1000 may include a program provider (PP), a terrestrial wave, or a content provider (CP). In addition, the broadcast content provided by the broadcaster 1000 may include existing broadcast content and rich content on the Internet.

The headend system 2000 receives and manages broadcast content from the broadcaster 1000 and distributes content to the user terminal 4000 to provide broadcast / recording / playback services. The received broadcast content may include related additional information and an EPG for such additional information.

The head-end system 2000 includes EPG information (PSIP / PSI /) including a subscriber concentrator, a broadcast video and audio signal, data broadcasting data, and a program recommendation service menu through a router supporting a multicast routing protocol. SI information) can be transmitted to IP set-top boxes of multiple subscribers by multicasting.

The baseband system 2010 receives an MPEG2 broadcast signal from an external program provider (PP) or an analog broadcast signal from terrestrial waves, converts the received source broadcast signal into a SDI (Serial Digital Interface) signal, and converts a frame ( Frames), and distributes video and audio signals from multiple broadcast channels (e.g. 100 channels) via a routine switcher, subtitle generator (CG) and automatic program controller (APC). At least one of an advertisement, a logo, or a subtitle is inserted into the broadcast video and audio signal (signal editing and processing) and transmitted to the compression multiplexing system 2020.

The SDI (Serial Digital Interface) signal is, for example, a digital signal standard having a transmission rate of 270 Mbps, and a composite digital video and four channels of digital audio signals may be mixed.

The baseband system 2010 is basically a tuner for receiving analog broadcast signals through a receiving device (eg, a DS-3 station, a Yagi antenna, and an IRD) for receiving broadcast signals such as a program provider (PP) and terrestrial waves, respectively. (Tuner)), a frame synchronizer for converting and correcting a source signal received from a receiving device into an SDI signal, synchronizing frames, and A connecting / centralizing all broadcast signal channels for operation management. A signal splitter such as a / V router and a subtitle generator for inserting an advertisement, a logo, and a subtitle into the SDI signal to edit and process the signal.

The compression multiplexing system 2020 uses an A / V encoder (A / V Encoder) for broadcasting video and audio signals (Video, Audio) received from the baseband system 2010 for each broadcasting channel (eg, 100 channels). ) To compress the SDI (Serial Digital Interface) video signal to H.264, and to compress the audio signal to MPEG-2 AAC to generate MPEG-2 TS (Transport Stream), and to compress compressed broadcast video and audio -2 after multiplexing data broadcasting data and EPG information (PSIP / PSI / SI information) generated by a data encoder and a PSI / SI generator together with the TS signal When the received MPEG-2 TS signal is used in the reception restriction technique, the TS-2 may be inputted to a scrambler, encrypted, and finally IP packetized to transmit an IP packetized TS (Transport Stream) broadcast signal.

Also, optionally, the reception restriction system 2030 may be used to prevent illegal viewing and illegal copying of program recommended content.

The reception restriction system 2030 performs encryption of the real-time channel and pre-encryption of the VOD content, and controls viewing authority so that only the authenticated user can use the channel and the content. In order to prevent illegal copying of IPTV contents, a digital rights management (DRM) scheme may be used instead of the reception restriction system 2030.

The back office system 2040 is a provisioning system and provides a billing processing function for use of an IPTV program service for each subscriber.

The monitoring system 2050 is a control system that monitors transmission failures of A / V broadcast signals for IPTV broadcasting, reception failures by monitoring downlinks of IPTV headend systems, and confirmation of subtitles and captions. can do.

The media management system 2060 is a system that manages various business process information (program organization information, location information, contract information, product information, etc.) for operating a broadcasting business. The media management system 2060 integrates and manages the information flow through organic coupling with each system in the center of the broadcasting center.

The media management system 2060 manages broadcast program organization information, content and media management information, contract information of a program provider (PP) and a content provider (CP), and product information, and manages each system in the center of a broadcasting center. Through organic integration, it can act as a coordinator to manage and manage the flow of information.

In addition, the media management system 2060 includes contract management, media and content metadata management, EPG information acquisition / management as broadcast schedule information, and real time broadcasting and VOD in terms of operation. It provides channel formation management, agent management, interworking with each subsystem, VOD catalog creation management, and various product management.In terms of analysis, marketing analysis reporting, delivery such as settlement of CP / CA, subscriber viewing propensity, etc. In terms of broadcasting transmission monitoring, video server transmission management and VOD subscriber authentication, transmission result recording / management for settlement with CP / CA, and data synchronization with each subsystem connected.

The subscriber management system 2070 provides a member subscription and termination for IPTV service and member information management.

The data broadcasting system 2080 authors, verifies, organizes, and transmits the data broadcasting data.

The data broadcasting system 2080 includes a data agent manager (PSI) for managing data encoding, a PSI / SI generator (PSI) for generating program specific information / service information (SI). / SI Generator), Data Server / Data Encoder for encoding data broadcasting data into broadcast video and audio signals, and Multiplexer Manager for managing multiplexing functions of data into the broadcast video and audio signals Manager) and a scheduler user interface (Scheduler UI).

In addition, the data broadcasting system 2080 may use the A / V encoder to provide the A / V data provided from the A / V server according to the terrestrial Application Configuration Access Protocol (ACAP) data broadcasting standard. Compresses the broadcast video and audio signals by using a data server / data encoder and PSI / SI (Program Specific Information / Service Information), and compresses the compressed video and audio signals from an application by the authoring tool. ) Is multiplexed by a multiplexer together with data broadcasting data and EPG information (PSIP / SI information) generated by the generator to encode and transmit broadcast program data and related information from the collection and storage of data broadcasting programs. .

The EPG system 2090 includes an EPG server and provides an electronic program guide (EPG) service to the user terminal 4000.

The return path server system 2100 processes bidirectional data by a data provider (DP), provides online bill transfer from the user terminal 4000, usage history / billing interworking processing of bidirectional data, and personalization authentication processing. , And receive bidirectional data for the program recommendation service and transmit the corresponding response data to the user terminal 4000 in unicasting.

The network 3000 receives the broadcast content from the headend system 2000 and delivers the received broadcast content to the user terminal 4000. The network network 3000 includes a backbone network and an access network, and the access network includes Ethernet, xDSL (ADSL, VDSL), Hybrid Fiber Coaxial Ca (HFC), and Fiber To The Curb), and may be configured in any one topology of a fiber to the home (FTTH) structure.

The user terminal 4000 is an apparatus for using an Internet broadcasting service, and generally includes an IPTV, a set top box, and a remote controller. IPTV outputs the broadcast content received from the headend system 2000 and transmits a user response signal received through the remote controller to the headend system 2000 through the return channel of the set top box.

The user terminal may use any one of a TV with an IP STB or an IP set-top box (IP STB), a computer, a notebook, or a personal portable terminal connected to the user's TV.

The IP set-top box includes a hardware layer composed of STB hardware such as a CPU, a media processor, flash RAM, and an Ethernet module, a system software layer including a system driver such as a device driver and an operating system, a Java Virtual Machine (JVM), Middleware layer with Conditional Access System (CAS) module and Digital Rights Management (DRM) interface module, streaming protocol (RTP, RTSP), MPEG2, MPEG4, MPEG7, H.264, WMV- It may include four layers of an application layer that supports various multi codecs such as 9 and includes an electronic program guide (EPG) for selecting an IPTV service channel. In this case, the subscriber's IP set-top box may be assigned an IPv4 address or an IPv6 address.

2 is a block diagram illustrating a configuration of a content retrieval system using image recognition in an IP according to an embodiment of the present invention.

A content retrieval system using image recognition in an IP according to an embodiment of the present invention includes a mobile terminal 10, a set-top box (STB) 20, and a search server 100.

The mobile terminal 10 may generate image data using a mounted camera, and transmit a control command and the generated image data to the set-top box 20. The mobile terminal 10 may perform data transmission / reception with the set top box 20 using long distance communication such as short range wireless communication such as Bluetooth and infrared communication. Therefore, the mobile terminal 10 includes a terminal capable of capturing images such as a cellular phone and a remote controller equipped with a digital camera and performing short-range wireless communication.

In addition, the mobile terminal 10 may download and store image data from the Internet through wireless communication, and then transmit the stored image data to the set-top box 20. When using the pre-stored image data in this way, it is possible to shorten the content search time.

The mobile terminal 10 may transmit image data to the set-top box 20 through wired communication as well as wireless communication. For example, the mobile terminal 10 may be connected to the set-top box 20 in a wired manner by using a universal serial bus (USB) communication interface to transmit pre-stored image data to the set-top box.

The set-top box (STB) 20 acquires image data from the mobile terminal 10 by using wired or wireless communication, or acquires image data by itself using screen capture, and the like. The image data is transmitted to the search server 100 through an IP (internet protocol) network.

In addition, the set-top box 20 receives related content from the search server 100 and provides the content to a subscriber terminal (not shown) such as a television.

The search server 100 receives image data from the set-top box 20 through an IP network, and searches for related content using a tag extracted from the received image. The search server 100 transmits the searched related content to the set top box 20.

3 is a signal flow diagram illustrating a flow of a content retrieval method using image recognition in an IP according to an embodiment of the present invention.

In step S110, the mobile terminal 10 or the set top box 20 acquires an image and generates image data. The mobile terminal 10 may acquire an image using a built-in digital camera, or may acquire an image using wired or wireless communication.

In addition, the set-top box 20 may acquire an image through screen capture or the like, or may acquire an image through wired or short-range wireless communication.

In step S120, the mobile terminal 10 transmits the generated image data to the set top box 20. The mobile terminal 10 may transmit image data to the set-top box 20 using short-range wireless communication or wired communication.

In operation S130, the set-top box 20 transmits the image data generated in operation S110 or the image data received in operation S120 to the content server 100. The set top box 20 may transmit image data to the content server 100 through an internet protocol (IP) network.

In operation S140, the content server 100 analyzes the image data received in operation S130, extracts a feature, generates a recognition parameter, and generates a tag for content search. The content search tag is generated using a recognition parameter and may include, for example, an actor's name, a building's name, and the like. The content search tag may be generated through analysis of an image pattern, face recognition, and comparison with a pre-stored face image.

Analysis of the person during image data analysis may be performed by an algorithm for detecting and recognizing a face included in the image data.

Face detection may be performed by extracting an area of a face existing in the input image data and finding a location of an eye present in the extracted face. Face detection can be seen as a preprocessing process for face recognition and can be a useful application on its own.

The face detection may be performed by extracting an area of the face by using the texture characteristic of the face and removing a false-positive area by using skin color information of the face.

The face region extraction using the texture characteristics of the face may be performed using an object detection algorithm, and the skin color information of the face is defined in the RGB color space, so that an incorrectly detected region is removed according to the ratio of skin color pixels present in the face region. Can be.

Once the face area is detected, an eyemap is determined to find the eye position present in the face area. The eye map may be determined using luma and color information of the eye. The determined eye map is made into a binary image using an adaptive threshold.

Candidate regions corresponding to the eyes are classified from the created binary image, and the candidate region having the highest average eyemap value in the left and right regions is regarded as the final eye region. When the area of the left and right eyes is determined in this way, the center point of each area is set to the position of the eye.

Face recognition extracts face features from face images extracted from the input image data and normalized to a specific standard, and compares the extracted face features with trained models in each person's database, thereby making the face the person with the highest similarity. This can be done through a series of processes to identify.

Algorithms such as principal component analysis (PCA), Fisher linear discriminant analysis (FLDA) or Regularized linear discriminant analysis (RLDA) may be used for face recognition.

In operation S150, the content server 100 searches for a content including a tag that is the same as or similar to the content search tag or a tag determined to be related to the database included in the content server 100 or an external database.

In operation S160, the content server 100 transmits the retrieved content to the set top box 20.

In step S170, the set-top box 20 provides the user with the content received from the content server 100.

4 is a flowchart illustrating a method of searching for content by analyzing image data according to an embodiment of the present invention.

In operation S210, image data is received from the set-top box 210. The image data may include a person image or an object image as described above.

In step S220, it is determined whether the image data received in step S210 includes a person image. That is, it is determined whether the image data includes a person, for example, a movie star, and the like, and the case of including a person corresponds to a case in which only the face of the person is included as well as the face. Therefore, it is determined whether the image data includes a person image including a face.

In step S230, when it is determined in step S220 that the image data includes a person image, a feature of the person image is extracted from the image data to generate a person recognition parameter. The feature of the person image may be extracted using face recognition, and the person recognition parameter may include a name of the person detected from the feature of the person image, a keyword representing the person, and the like.

For example, when the image data includes the face of the movie actor "Hong Gil Dong", the face recognition may detect the face of "Hong Gil Dong" as a feature of the human image, so that the person recognition parameter is "Hong Gil Dong" as the word. Can be included as a keyword. In addition, the person recognition parameter may include a representative movie title of the movie actor "Hong Gil Dong".

In step S240, a person image tag, which is a tag for content search, is generated using the person recognition parameter generated in step S230. The content search tag is generated to compare with a tag corresponding to each content.

In step S250, it is determined whether the image data received in step S210 includes an object image. That is, it is determined whether the image data includes objects such as buildings, mountains, rivers, animals, and cars.

In operation S260, when it is determined in operation S250 that the image data includes an object image, an object recognition parameter is generated by extracting a feature of the object image from the image data. The feature of the object image may be extracted using object recognition, and the object recognition parameter may include a name detected from the feature of the object image, for example, a building name, an animal name, a model name of a vehicle, and the like. Can be.

For example, when the image data includes the building "Dongdaemun", the object recognition may detect the shape of "Dongdaemun" as a feature of the object image, so that the object recognition parameter is a word "Dongdaemun" as a keyword. It may include.

In operation S270, an object image tag, which is a tag for content search, is generated using the object recognition parameter generated in operation S260. As described above, the content search tag is generated for comparison with a tag corresponding to each content.

In step S280, the content related to the image data received in step S210 is searched using the person image tag generated in step S240 or the object image tag generated in step S270, and the retrieved content is set-top. It is provided in a box (not shown).

Content related to the image data may be searched by comparing a person image tag, an object image tag, or a tag including each tag with a tag attached to the content to be searched.

That is, the content to be searched for includes tags that provide summary information. Therefore, the content may be searched by comparing a tag included in the content with a tag generated from image data. The content retrieved and provided to the set-top box may include an image, a video, or a text file.

All content such as IPTV related movies, dramas, etc. may include a poster representing the content. Most of these posters have main characters and images that can visualize the characteristics of the contents. Content may be searched for such a poster using image analysis.

For example, if you use a character image of a lead or supporting actor included in a poster and an object image of a sky, a mountain, a building, a tree, an animal, a fish, a car, etc., the content desired by a viewer Can be simply retrieved.

In addition, if information about an actor or a car displayed on the screen is required while watching an IPTV, the IPTV user may use screen capture to generate image data about the actor or the car and search for related content. Can be.

5 is a block diagram showing the configuration of a search server according to an embodiment of the present invention.

Search server 100 according to an embodiment of the present invention includes a data transmission and reception unit 110, an image processing unit 120 and a content search unit 130.

The data transmission / reception unit 110 receives image data from a set-top box (not shown), and transmits the content searched by the content search unit 130 to the set-top box.

The image processor 120 analyzes the image data received by the data transceiver 110, extracts a feature, generates a recognition model parameter, and extracts a related tag from the generated recognition model parameter. The extracted tag is a content search tag, and may be composed of keywords related to image data.

The image processor 120 may extract a tag by analyzing at least one of a face image and an object image included in the image data. In addition, when a tag is extracted from each of the face image and the object image, the image processor 120 may combine the respective tags to generate a tag.

The content search unit 130 searches the content database 140 for content including a tag determined to be the same, similar, or related to the tag generated by the image processing unit 120.

The content database 140 stores various contents, and the contents stored in the content database 140 each include an associated tag. There may be more than one such tag.

In addition, the content search unit 130 may search for content using a content search tag from an external database server (not shown) including the content as well as the content database 140.

6 is a block diagram illustrating a configuration of an image processor according to an exemplary embodiment of the present invention.

The image processing unit 120 according to an embodiment of the present invention includes a person image extraction module 121, an object image extraction module 122, and a tag generator 123.

The person image extraction module 121 extracts a feature from the person image included in the image data and generates a person recognition parameter. The person recognition parameter generated from the person image may be a person name.

For example, when the image data includes a face of a movie star, the person image extraction module 121 may generate a person recognition parameter using the name of the movie star.

The object image extraction module 122 generates an object recognition parameter by extracting a feature from an object image that is an image excluding a person image among images included in the image data. The object image may include, for example, an image of a building, a mountain, a sky, a river, and the sea, which are surrounding background images. Accordingly, the object recognition parameter generated from the object image may be a name of a building, a mountain, a river, or the like.

For example, when the image data includes an image of a famous building, the object image extraction module 122 may generate an object recognition parameter using the name of the famous building.

The tag generator 123 generates a tag for content search using the person recognition parameter or the object recognition parameter generated from the person image extraction module 121 or the object image extraction module 122.

7 is a block diagram showing the configuration of a set-top box (STB) according to an embodiment of the present invention.

Set-top box (STB) 20 according to an embodiment of the present invention is the image input unit 21, the image transmitter 22, the search result output unit 23, the communication interface 24 and the capture unit 25 Include.

The image input unit 21 receives an input of image data from a mobile terminal (not shown) or receives captured image data of a screen of the subscriber terminal from the capture unit 25.

The image transmitter 22 transmits the image data received by the image input unit 21 to an IPTV system (not shown) or a content server (not shown) through an internet protocol (IP) network. In particular, the image transmitter 22 may transmit image data to an IPTV system or a content server through a return channel.

The search result output unit 23 outputs a search result performed by an IPTV system or a content server. More specifically, the search result output unit 23 receives a content list corresponding to a search result by an IPTV system or a content server, and outputs the received content list to a user of the IPTV. Provide a selection of content.

Accordingly, the user of the iPyiyi can select the desired content by using the output search result.

The communication interface 24 provides an interface for wired or short-range wireless communication with a mobile terminal (not shown). For example, the communication interface 24 may provide a communication interface for USB, infrared or Bluetooth communication.

In addition, the communication interface 24 is connected to the image input unit 21 to transfer the image data received from the mobile terminal to the image input unit.

The capturer 25 captures a screen of the subscriber station connected to the set top box 20 to generate image data. That is, the capture unit 25 captures an image of the content being broadcast on the screen of the subscriber terminal, and generates image data using the captured image. The image data generated by the capture unit 25 is transferred to the image input unit 21.

One embodiment of the present invention can also be implemented in the form of a recording medium containing instructions executable by a computer, such as a program module executed by the computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery media.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The foregoing description of the present invention is intended for illustration, and it will be understood by those skilled in the art that the present invention may be easily modified in other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is shown by the following claims rather than the above description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be construed as being included in the scope of the present invention. do.

1 is a block diagram showing the configuration of an IPTV broadcasting system to which an embodiment of the present invention can be applied;

FIG. 2 is a block diagram illustrating a configuration of a content retrieval system using image recognition in an IP according to an embodiment of the present invention; FIG.

3 is a signal flow diagram illustrating a flow of a content retrieval method using image recognition in an IP according to an embodiment of the present invention;

4 is a flowchart illustrating a method of searching for content by analyzing image data according to an embodiment of the present invention;

5 is a block diagram showing the configuration of a search server according to an embodiment of the present invention;

6 is a block diagram showing a configuration of an image processing unit according to an embodiment of the present invention;

7 is a block diagram showing the configuration of a set-top box (STB) according to an embodiment of the present invention.

Claims (13)

In the content retrieval method using image recognition in IPTV, (a) matching and storing at least one tag that can be extracted from an image with respect to provided content, (b) receiving image data from a set-top box (STB), (c) analyzing the image data to generate a tag for content search; and (d) searching for content related to the image data by comparing the content search tag with a tag matching the content Content search method comprising a. The method of claim 1, And the image data is stored in the set top box (STB) through short-range communication from an external device. The method of claim 2, And the external device is a mobile terminal having a camera. The method of claim 1, And the image data is generated by capturing a screen of a subscriber station connected to the set top box (STB). The method according to claim 2 or 4, (e) providing a content list for viewing the retrieved content Content search method further comprising. The method according to claim 2 or 4, In step (b), (b1) generating a person image tag by extracting a feature of the person image when the image data includes a person image Including, The content search tag includes the person image tag. The method according to claim 2 or 4, (b2) if the image data includes an object image, generating an object image tag by extracting features of the object image Including, The content search tag comprises the object image tag. In a content retrieval system using image recognition in IPTV, A data transceiver for receiving image data from the set-top box, An image processor extracting a feature of an image included in the image data and generating a content search tag; A content database that matches and stores at least one tag that can be extracted from an image for each content; A content searching unit that searches for contents related to the image data in the contents database using the contents searching tag; Including, And the content search unit searches for the content by comparing the content search tag with the tag included in the content. The method of claim 8, The image processing unit, A person image extraction module for generating a person recognition parameter from the person image included in the image data; An object image extraction module for generating an object recognition parameter from the object image included in the image data; Tag generation unit for generating a content search tag using the person recognition parameter or the object recognition parameter. Content retrieval system comprising a. In a set-top box (STB) that provides content retrieval using image recognition, An image input unit providing an input of an image for search, An image transmitter for transmitting the image to an IPTV system through a return channel; Search result output unit for receiving a list of content corresponding to the search results from the IPTV system to provide a selection of content Set top box providing a content search comprising a. The method of claim 10, The search result is a set-top box for providing a content search that is generated by comparing the tag extracted from the input image and the tag matching each content. The method of claim 10, Short-range communication interface connected to the image input unit Set top box to provide a content search further comprising. The method of claim 10, Capture unit for capturing an image of the content being broadcast More, And the image captured by the capture unit is delivered to the image input unit.

Images