KR100894016B1 - System and method for providing motion picture searching service by object color information - Google Patents

Abstract

The present invention relates to a method and a system for providing a video search service using object color information. The method for providing a video search service using object color information of a video according to the present invention includes: receiving a search request with a video attached from a user; ; Capturing a screen of the attached video in a predetermined time unit or frame unit and selecting a specific object for each captured screen; Extracting color information of each selected object; Expressing color information of each extracted object as a graph; And searching for a video having the same or similar graph as the expressed graph and providing the same to the user.

Color information, object, time unit, video server, graph

Description

Method and system for providing video search service using object color information {SYSTEM AND METHOD FOR PROVIDING MOTION PICTURE SEARCHING SERVICE BY OBJECT COLOR INFORMATION}

The present invention relates to a video search, and more particularly, to a method and system for providing a video search service using object color information for searching a video by comparing color information of a video object.

Currently, video data is increasing due to the spread of camcorders, wireless communication terminals capable of recording video, and the spread of webcams of personal computers. In addition, user-created content, UCC (User Created Content), has become a mega trend, and video data is becoming huge.

However, the method of searching exponentially increasing video data has not escaped the existing search method by text. Looking at an example of such a video search method, a user who wants to provide a video accesses a video server and searches for a video. At this time, the user searches for a video by inputting text into the search box. Then, the video server receives the text from the user, retrieves the tag information in which the video file name or the video title, the copyright holder, and the like entered by the video provider are input, and transmits the matching (or similar) search result to the user. . The user then receives a plurality of search results and selects one of them to be provided with a video.

In addition, recently, various video search technologies have been proposed to analyze and use video information.

Korean Patent Laid-Open Publication No. 2000-47363 (name of the invention: an apparatus and method for extracting color image descriptors and an apparatus and method for searching multimedia data using the same) proposes an image data retrieval method using color-space information of image data.

Republic of Korea Patent Publication No. 2001-11701 (name of the invention: a method for extracting feature vector from a color image and an image retrieval method using the same) is a feature vector that takes into account the color and shape information of the image data at the same time We propose a video search method.

Korean Patent Laid-Open Publication No. 2001-60994 (name of the invention: a content-based video retrieval method) divides image data into shot units and subdivids them into sub-shot units to determine the color of the re-divided image. After extracting color and motion features, a method of searching for a video based on the extracted information is proposed.

Korean Patent Laid-Open Publication No. 2002-59951 (name of the invention: image search method based on a combination of color and texture) obtains a color distance and a texture distance between a query image and a data image, and adds weights to the color distance and texture. After obtaining a specific distance combining distances, a method of searching for an image similar to a query image using the specific distance is proposed.

Korean Patent Laid-Open Publication No. 2003-9674 (name of the invention: a content-based image retrieval apparatus and method) proposes a method of calculating a feature based on color, texture, and shape of image data and retrieving a video using the same.

However, the above-described conventional video retrieval technique uses the search information input by the subject of the video provider, so that a user may receive a search result that is less objectively accurate.

In addition, the above-described video search technology method of the Republic of Korea Patent Publication, since the search for the video using the space, vector, motion, texture distance, shape, etc. of the image data, a complex algorithm is required, and the search speed is also reduced.

The present invention has been proposed to solve the above problems, receives a video search request with a video attached from the subscriber, captures the attached video screen by a predetermined time unit, and analyzes the object color information of each captured screen The purpose of this is to provide subscribers with video search results that match them.

Other objects and advantages of the present invention can be understood by the following description, and will be more clearly understood by the embodiments of the present invention. Also, it will be readily appreciated that the objects and advantages of the present invention may be realized by the means and combinations thereof indicated in the claims.

According to a first aspect of the present invention, a method for providing a video search service using object color information of a video includes: (a) receiving a search request with a video attached from a user; (b) capturing a screen of the attached video at predetermined time units or frame units and selecting a specific object for each captured screen; (c) extracting color information of each of the selected objects; (d) expressing color information of each extracted object in a graph; And (e) searching for a video having the same or similar graph as the above-described graph and providing the same to the user.

According to a second aspect of the present invention for achieving the above object, a database for storing a video file and a graph of the object color information of the video file; And receiving a search request to which a video is attached from a user, capturing a screen of the attached video by a predetermined time unit or a frame unit, and displaying color information of selected objects one by one for each captured screen as a graph. Expressing, the video providing server which searches for the video having the same or similar graph as the graph in the database and provides the video to the user.

According to a third aspect of the present invention, there is provided a video providing apparatus for providing a video search service to a user in association with a video file and a database storing an object color information graph of the video file. A receiver configured to receive an attached video search request; An object selecting unit for capturing the screen of the attached video by a predetermined time unit or a frame unit, classifying objects by the captured screens, and selecting objects that occupy the largest area by each screen. ; A graph representation unit extracting color information of each of the selected objects and expressing color information of each object in a graph; And a searching unit searching for the video having the same or similar graph as the graph in the database and providing the same to the user.

In the present invention as described above, when receiving a search request with a video file attached, by searching for a video that matches the object color information of the video file to provide to the subscriber, the subscriber more accurate search results than the existing video search method by text There are advantages that can be provided to.

In addition, according to the present invention, if a subscriber wants to search for a video similar to a video directly photographed, the subscriber can easily receive a search result by attaching the video and requesting a search.

The above objects, features and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, whereby those skilled in the art may easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a configuration of a video search service providing system using object color information according to an embodiment of the present invention.

As shown in FIG. 1, the video search service providing system using object color information according to an embodiment of the present invention includes a subscriber terminal 110, a video providing server 120, and a video database 130 (hereinafter referred to as “video DB”). ) And a wired terminal 140. These components are connected to each other through the mobile communication network 150 and the Internet 160. Herein, the mobile communication network 150 includes a base station (BTS / NodeB), a base station controller (BSC / RNC), a switch, a device for packet data service (PDSN, SGSN, IWF, etc.), and the present invention. Since it is a well-known technical element in the detailed description thereof will be omitted.

The subscriber may register the video with the video providing server 120 using the subscriber terminal 110 or the wired terminal 140. In addition, the subscriber may access the video providing server 120 using the subscriber terminal 110 or the wired terminal 140 to request a video search and receive the searched result. A method for requesting a search to a video providing server 120 by a subscriber is achieved by attaching a video stored in the subscriber terminal 110 or the wired terminal 140 to the video providing server 120 or inputting text into a search box. Can be. The subscriber station 110 includes a PDA, a cellular phone, a PCS phone, a GSM phone, a W-CDMA phone, a DMB phone, a Wibro phone, a Wifi phone, and the like, and the wired terminal 140 includes a general purpose computer.

The video providing server 120 receives a video file from a subscriber (ie, a video provider) who wants to provide a video. The video file may include video tag information such as a title and a copyright holder set by the subscriber. The video providing server 120 receiving the video file from the subscriber captures the screen of the video at a predetermined time unit (or frame unit). The video providing server 120 classifies objects in each captured screen and selects one object that occupies the largest area among the screens, one for each screen. For example, if the screen of the video is captured six times, the video providing server 120 selects one object for each of the six screens and has six object information as a whole.

The video providing server 120 selecting an object of each screen extracts color information RGB for each object. In addition, the video providing server 120 sets the X axis as a captured screen index and the Y axis as a color information value to express the color information RGB of each object as a graph. For example, if the color information value extracted from the first captured screen is 255, the color information is represented as (1,255) on the graph, and if the color information value of the object selected from the second captured screen is 100, the graph is (2, 100). The color information is represented. The video providing server 120 expressing the color information of the object for each screen of the video as a graph stores the corresponding video file, tag information, and graph information in the video DB 130.

In addition, the video providing server 120 may receive a video search request from the subscriber. In this case, the video providing server 120 may receive a video search request to which a video file is attached and may receive only a video search request by text. If only the video search request by text is received from the subscriber, the video providing server 120 searches the video DB 130 for a file name that matches the text (or similar), or tag information of the video, and receives the search result accordingly. To provide. On the other hand, when receiving a video search request with a video file attached, the video providing server 120 displays the screen of the attached video at a predetermined time interval unit (or frame unit), as in the case of receiving a video from a video provider. Captures the objects on each screen, and selects one object for each screen that occupies the largest area.

The video providing server 120 extracts color information RGB of each selected object and expresses the extracted color information as a graph. That is, the video providing server 120 represents color information of each object extracted in a graph in which the X axis is a captured screen index and the Y axis is a color information (RGB) value. The video providing server 120 searches for the video DB 130 having the graph information corresponding to (or similar to) the graph. The video providing server 120 stores a search result and composes a callback message including address information (URL) directly accessible to the search result and transmits it to the subscriber. In addition, the video providing server 120 may write a search result in an MMS message and transmit the search result to the subscriber. The search result preferably includes a captured image of the searched video, color information similarity (ie, 100 to 0%), a file name, and video tag information.

2 is a flowchart illustrating a method for constructing a database for searching a video according to an embodiment of the present invention.

Referring to FIG. 2, the video provider requests the video providing server 120 to register the video using the subscriber terminal 110 or the wired terminal 140 (S201). At this time, the video providing server 120 receives a video tag and video tag information describing a video from a video provider. Then, the video providing server 120 captures the screen of the received video in a predetermined time unit or frame unit (S203). The video providing server 120 classifies the object for each captured screen. Subsequently, the video providing server 120 selects one object for each screen capturing the object (that is, the object having the largest area) among the objects classified in each screen (S205).

Subsequently, the video providing server 120 extracts color information (RGB) values 0 to 255 of each object selected per screen (S207). In addition, the video providing server 120 expresses the extracted color information for each object as a graph in which the Y-axis is set to the color information value as the index for each screen captured by the X-axis (S209). In this case, the video providing server 120 integrates the extracted RGB values (0 to 255) into one value, and then expresses them as one graph. Subsequently, the video providing server 120 stores the corresponding video file, tag information, and graph information in the video DB 130 (S211, S213).

Hereinafter, a method of providing a video search service using object color information according to an embodiment of the present invention will be described in more detail with reference to FIGS. 3 to 5.

3 is a flowchart illustrating a method for providing a video search service using object color information according to an embodiment of the present invention.

FIG. 4 is a diagram illustrating a screen capturing a video received by a video providing server according to an embodiment of the present invention on a predetermined time basis.

FIG. 5 is a graph illustrating color information of an object selected for each screen in a video providing server according to an exemplary embodiment of the present invention.

3 to 5, the video providing server 120 receives a video search request from the subscriber terminal 110 (S301). In this case, the video providing server 120 may receive a video search request to which a video file is attached from the subscriber terminal 110, and may receive only a video search request by text. When only the video search request by text is received from the subscriber terminal 110, the video providing server 120 searches for the file name or the tag information of the video that matches the text (or similar) in the video DB 130 and accordingly. Provide the search results to the subscriber. On the other hand, when receiving a video search request to which a video file is attached, the video providing server 120 captures the screen of the attached video in a predetermined time unit or frame unit (S303, # 1, # 2, FIG. 4). .., # 6).

The video providing server 120 classifies objects in each captured screen and selects one object (that is, the object having the largest area) among the screens, one for each screen (S305). Subsequently, the video providing server 120 extracts color information RGB values 0 to 255 of each selected object (S307). The video providing server 120 expresses the extracted color information of each object as a graph (S309). In this case, the video providing server 120 integrates the extracted RGB values (0 to 255) into one value, and then expresses them as one graph.

A method of representing color information of an object selected for each screen with a graph will be described with reference to FIGS. 4 and 5. FIG. 4 is a diagram illustrating an example in which a video providing server captures a screen of the attached video at a predetermined time unit when receiving a video search request to which a video file is attached. Here, # 1 to # 6 are indexes (index, 501) for distinguishing a screen capturing a video by a predetermined time unit, and are represented by the X axis in the graph of FIG. 5. FIG. 5 is a graph representing color information for each object selected on each screen of FIG. 4, and a Y-axis represents an RGB value 503 for each object selected on each screen # 1,..., And # 6. If the RGB value of each object selected for each captured screen is equal to 503 of FIG. 5 (255, 100, 255, 125, 255, 1), the color information graph is represented by 507, that is, the XY coordinate value is ( 1, 255), (2,100), (3, 255), (5, 125), (5, 255), (6,1), and the coordinate values are 507a, 507b, 507c, 507d, 507e, 507f, respectively. Corresponding to the graph 507 is represented.

In the above method, the video providing server 120 expressing the color information of the selected object for each screen # 1, # 2, ..., # 6 as a graph displays a video having graph information similar to the graph 507 information. The video is searched in the DB 130 (S311, S313). That is, the video providing server 120 compares the graph 505 stored in the video DB 130 with the object color information graph 507 of the attached video to extract a similar (or matching) video.

The video providing server 120 extracting matching (or similar) video information by comparing the expressed graph with a graph stored in the video DB 130 (S315) and stores the searched result. Meanwhile, when the video providing server 120 additionally receives a search word (that is, text) in addition to the attached video from the subscriber terminal 110, the video information server 120 displays the tag information and the file name of the video corresponding to the search word in the video DB 130. Search and store the search results along with the color information graph search results. Subsequently, the video providing server 120 composes and sends a callback message including address information (URL) to the subscriber station 110 so that the user of the subscriber station 110 can directly access the search result (S317). . In addition, the video providing server 120 may write the search result into an MMS message and transmit the search result to the subscriber station 110. The search result includes a captured image of a video, color information similarity (ie, 100 to 0%), a file name, tag information, and the like, and is stored in the order of high similarity.

The user of the subscriber station 110 receiving the callback message may access the video providing server 120 and check the search result by pressing the call (or access) button. In addition, the subscriber may download and confirm the corresponding video to his subscriber station 110 by selecting one of the search results.

In the description with reference to FIG. 3, the caller requesting the video search is described as the subscriber station 110. However, the present invention is not limited thereto, and it is apparent that the search request can be received from the user of the wired terminal 110. Then, the video providing server 120 determines whether the search request originator is the subscriber terminal 110 or the wired terminal 140, and if the wired terminal 140 is a wired terminal 140 without writing a callback message. To send).

As described above, the subscriber may receive a more accurate search result than the existing video search method by text by attaching a video file and transmitting the video file to the video providing server 120. In addition, when a subscriber wants to search for a video similar to a video captured directly, the subscriber can easily receive a search result by attaching the video and requesting a search to the video providing server 120.

6 is a diagram showing the configuration of a video providing server according to an embodiment of the present invention.

As shown in FIG. 6, the video providing server 120 according to an exemplary embodiment of the present invention includes a transceiver 601, an object selector 603, a graph presenter 605, and a searcher 607. .

The transceiver 601 receives a video registration request from a video provider. In addition, the transceiver 601 receives a video search request to which a video file is attached from a video user. The transceiver 601 transmits a video search result to the video user, and when the video user selects one of the search results, downloads the video to the user.

When the transceiver 601 receives a video registration request or a video search request to which a video file is attached, the object selecting unit 603 captures a screen of the received video in a predetermined time unit or frame unit. The object selecting unit 603 classifies objects for each of the captured screens and selects one object for each of the captured screens (ie, the object having the largest area) that occupies the largest area.

The graph representation unit 605 extracts color information RGB of each object selected by the object selection unit 603. The graph expression unit 605 expresses the extracted color information for each object, the X axis is a captured screen index, and the Y axis is a graph set to the color information value. When the video representing the object color information as a graph is a registered video, the graph representation unit 605 stores the graph information, the video file, and the tag information in the video DB 130. On the other hand, when the video representing the object color information as a graph is an attached video requested to be searched, the graph presenter 605 transmits the graph information to the searcher 607 to request a video search.

The search unit 607 receives the graph information from the graph representation unit 605 and searches for a video having graph information similar to the graph information in the video DB 130. The search results are stored by sorting the video information in the order of high similarity among the search results. Preferably, the search result includes a video file, video information, and a video captured image. The search unit 607 generates a callback message that directly accesses the search result and transmits the callback message to the video user through the transmission unit 601.

The method of the present invention as described above may be implemented as a program and stored in a recording medium (CD-ROM, RAM, ROM, floppy disk, hard disk, magneto-optical disk, etc.) in a computer-readable form. Since this process can be easily implemented by those skilled in the art will not be described in more detail.

The present invention described above is capable of various substitutions, modifications, and changes without departing from the technical spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawings.

1 is a diagram illustrating a configuration of a video search service providing system using object color information according to an embodiment of the present invention.

2 is a flowchart illustrating a method for constructing a database for searching a video according to an embodiment of the present invention.

3 is a flowchart illustrating a method for providing a video search service using object color information according to an embodiment of the present invention.

FIG. 4 is a diagram illustrating a screen capturing a video received by a video providing server according to an embodiment of the present invention on a predetermined time basis.

FIG. 5 is a graph illustrating color information of an object selected for each screen in a video providing server according to an exemplary embodiment of the present invention.

6 is a diagram showing the configuration of a video providing server according to an embodiment of the present invention.

<Explanation of symbols for the main parts of the drawings>

601: transceiver unit 603: object selection unit

605: graph expression unit 607: search unit

Claims (10)

As a method for providing a video search service using object color information of a video, (a) receiving a search request with a video attached from a user; (b) capturing a screen of the attached video by a predetermined time unit or a frame unit and selecting an object that occupies the largest area among the objects of the captured screen for each of the captured screens; (c) extracting color information of each of the selected objects; (d) expressing color information of each extracted object in a graph; And and (e) searching for a video having the same or similar graph as the expressed graph and providing the same to the user. The method of claim 1, Step (e), And creating and transmitting a callback message including address information directly accessible to a search result to the user. The method according to claim 1 or 2, Step (e), Method for providing a video search service using the object color information, characterized in that the search results are arranged in order of high similarity to the user. delete As a video search service providing system using video object color information, A database that stores a video file and a graph of object color information of the video file; And Receiving a search request with a video attached from a user, capturing the screen of the attached video in a predetermined time unit or frame unit, selecting an object occupying the largest area for each captured screen, and selecting the selected object. A video providing server for expressing each color information of each object as a graph and searching for a video having the same or similar graph as the graph in the database and providing the same to the user; a video searching service providing system using object color information including a . The method of claim 5, wherein The video providing server, System for providing a video search service using object color information, comprising: creating a callback message including address information directly accessible to a search result and transmitting the same to the user. The method according to claim 5 or 6, The video providing server, Video search service providing system using the object color information, characterized in that for sorting the search results in the order of high similarity provided to the user. A video providing device providing a video search service to a user by interworking with a database storing a video file and an object color information graph of the video file. A receiver configured to receive a video search request to which a video is attached from a user; An object selecting unit for capturing the screen of the attached video by a predetermined time unit or a frame unit, classifying objects by the captured screens, and selecting objects that occupy the largest area by each screen. ; A graph representation unit extracting color information of each of the selected objects and expressing color information of each object in a graph; And And a search unit searching for the video having the same or similar graph as the graph in the database and providing the same to the user. The method of claim 8, The search unit, And a callback message including address information directly accessible to a search result is transmitted to the user. The method according to claim 8 or 9, The search unit, Device for providing a video, characterized in that for sorting the search results in the order of high similarity provided to the user.

Images