JP2013073392A - Display control device, display control program, and display control method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To display information of a desired person in persons appearing in a program, on all programs in a versatile manner.SOLUTION: A display control device 8 includes: an information acquiring unit 164 that acquires image data and feature data of persons included in a supplied image, from a route different from a supply route for supplying the image; performer information 152 that stores the image data and the feature data acquired by the information acquiring unit 164 for every person; a face recognition unit 167 that detects a face image located nearest to a position specified to the image; a display information generating unit 166 that specifies the person of the face image detected by the face recognition unit 167 on the basis of the image data of the person stored in the performer information 152; and a display unit 13 that displays the feature data of the specified person.

Description

  The present invention relates to a display control device and the like.

  A viewer of a television program may want to know information about performers in the viewing screen. In such a case, when the face of the target person in the viewing screen is enclosed by the cursor display, the person in the image data of the enclosed face is specified based on the person information table, and the person information about the specified person Is extracted from the person information table and displayed. In the person information table, person specifying information and person information for a plurality of persons are stored in advance. Thereby, the viewer can know the personal information regarding the performer who wants to know.

  In addition, there is a technique for reproducing and displaying a moving image based on moving image data including a display object in which an action is defined in a video player that reproduces a television program. In such a technique, when the video player receives a selection of a display object included in the reproduced and displayed moving image from the viewer, the video player automatically displays the description information defined in the display object that has received the selection. Thereby, the viewer can know the explanatory information regarding the performer who wants to know in the display object which accepted selection.

JP 2008-250654 A JP 2008-66925 A

  However, there is a problem that information on a desired person among persons appearing in the program cannot be displayed universally for all programs. In other words, if a conventional video player that plays a television program includes a display object in which an action is defined in a video that is played back and displayed for the program, the description of a desired person included in the display object selected by the viewer Information can be displayed. That is, the video player can display the information of the target person only for a program that is created by a moving image and includes a display object. Further, if the video player does not include a display object in the video reproduced and displayed for the program, even if the viewer surrounds the face of the desired person with the cursor display, the information on the enclosed person cannot be displayed. is there.

  In addition, the said subject arises similarly not only in the person who appears in the program but with the goods which appear in the program.

  It is an object of the disclosed technique to display information on a desired person among persons appearing in a program for all programs.

  In one aspect, the display control device acquires the image data and feature data of the person included in the supplied image from a different route from the supply route for supplying the image, and the image acquired by the acquiring unit. Based on a storage unit that stores data and feature data for each person, a detection unit that detects a face image closest to a specified position with respect to the image, and person image data stored in the storage unit A specifying unit that specifies a person of the face image detected by the detecting unit, and a display unit that displays characteristic data for the person specified by the specifying unit.

  According to one aspect of the display control device disclosed in the present application, information on a desired person among persons appearing in a program can be displayed for all programs.

FIG. 1 is a functional block diagram illustrating the configuration of the display control system according to the embodiment. FIG. 2 is a diagram illustrating an example of a data structure of program information. FIG. 3 is a diagram illustrating an example of a data structure of performer information. FIG. 4 is a diagram for explaining the frame structure of MPEG2. FIG. 5 is a diagram for explaining a motion compensation block and a motion vector of a P frame. FIG. 6 is a diagram (1) illustrating a method for calculating coordinates corresponding to the I frame when the P frame is touched. FIG. 7 is a diagram (2) for explaining a method of calculating coordinates corresponding to the I frame when the P frame is touched. FIG. 8 is a diagram for explaining a method of calculating the corresponding coordinates of each frame. FIG. 9 is a flowchart illustrating the processing procedure of the information acquisition unit according to the embodiment. FIG. 10 is a flowchart (1) illustrating the processing procedure of the face recognition unit according to the embodiment. FIG. 11 is a flowchart (2) illustrating the processing procedure of the face recognition unit according to the embodiment. FIG. 12 is a flowchart (3) illustrating the processing procedure of the face recognition unit according to the embodiment. FIG. 13 is a diagram illustrating an example of a display screen of the display control apparatus according to the embodiment. FIG. 14 is a diagram illustrating an example of a computer that executes a display control program.

  Hereinafter, embodiments of a display control device, a display control program, and a display control method disclosed in the present application will be described in detail with reference to the drawings. However, the present invention is not limited to the present embodiment.

  FIG. 1 is a functional block diagram illustrating the configuration of the display control system according to the embodiment. As shown in FIG. 1, the display control system 1 includes a broadcast station 2, a video server 3, a program information server 4, a search engine 5, an information providing server 6, a network 7, and a display control device 8. Have. The display control device 8 is connected to the broadcasting station 2 and is connected to the search engine 5 and the information providing server 6 via a network 7 such as the Internet. The broadcasting station 2 is connected to the video server 3 and the program information server 4.

  The broadcast station 2 distributes digital television broadcast data through satellite broadcast waves, terrestrial waves, cable television networks, or data communication networks.

  The video server 3 stores video data of digital television broadcast distributed from the broadcast station 2. Video data is compressed according to the MPEG standard. For example, MPEG2 (Moving Picture Experts Group phase 2) compression method is adopted.

  The program information server 4 provides digital TV broadcast program information (program guide) distributed from the broadcasting station 2. The program information includes, for example, a program name, broadcast date and time, program contents, performer information, and the like. That is, the broadcast station 2 mixes the program information provided from the program information server 4 with the broadcast data, and distributes the mixed broadcast data. This service providing program information is called an electronic program guide (EPG). The EPG is defined in the ARIB standard ARIB STD-B10 “program arrangement information used for digital broadcasting” and the ARIB technical data ARIBTR-B14 “terrestrial digital television broadcasting operation regulations”. The EPG provides program information in a data format called EIT (Event Information Table).

  The search engine 5 includes a server or system that provides a function of searching for information such as images on the network 7. For example, in the case of an image search, the search engine 5 includes a Google image search, a Yahoo image search, a Bing image search, and a Baidu image search. The information providing server 6 is a server that provides various types of information. For example, the information providing server 6 provides information related to a person or information related to a product.

  The display control device 8 includes a tuner 11, a network interface unit 12, a display unit 13, an input unit 14, a storage unit 15, and a control unit 16. The tuner 11 receives broadcast data distributed from the broadcast station 2. Then, the tuner 11 outputs video data of the received broadcast data to the video processing unit 161, and outputs program information of the received broadcast data to the data processing unit 163.

  The network interface unit 12 is a processing unit that performs data communication with the search engine 5 and the information providing server 6 via the network 7.

  The display unit 13 is a display device that displays video and information related to the video. For example, the display unit 13 corresponds to a display and a touch panel. The input unit 14 is an input device for the viewer to input various information to the display control device 8. With this input unit 14, the viewer can specify and operate the video displayed on the display unit 13 (hereinafter also referred to as touch). In other words, the input unit 14 inputs the person or product that the viewer wants to know in the video displayed on the display unit 13 or a position where the vicinity is touched to the display control device 8. For example, the input unit 14 corresponds to a keyboard, a mouse, and a touch panel.

  The storage unit 15 stores program information 151 and performer information 152. The storage unit 15 corresponds to, for example, a semiconductor memory device such as a random access memory (RAM), a read only memory (ROM), and a flash memory, or a storage device such as a hard disk or an optical disk.

  The program information 151 is program information provided by EPG. The program information 151 is composed of EIT. Here, the data structure of the program information 151 will be described with reference to FIG. As shown in FIG. 2, the program information 151 is associated with a program name 151a, an item name 151b, and an item content 151c.

  The item name 151b and the item content 151c are repeated by the number of the item names 151b. The program name 151a is the name of the program, and is represented by, for example, 96 bytes or less and 40 characters or less. The item name 151b is a name of various items related to the program, and is represented by, for example, 16 bytes or less and 8 characters or less. For example, in addition to “appearance” indicating the performer and “moderator” indicating the moderator, the words and phrases listed in the item name 151b include casters, reporters, commentators, commentators, announcers, live commentaries, narrators, voice appearances, interpreters, There are guests. The item content 151c is the content of the item corresponding to the item name, and is represented by, for example, 440 bytes or less and 200 full-width characters or less.

  The program information 151 has the following data structure, for example. The item name 151b is enclosed in parentheses such as “[]” and “<<”. In the example of FIG. 2, “[]” is adopted. Further, delimiters such as ‘,’ and ‘,’ are used as a delimiter between the program name 151a and the item name 151b, and as a delimiter between the item content 151c and the item name 151b. In the example of FIG. 2, ',' is adopted.

  As an example, when the program name 151a is “ABCDEF”, “[Appearance]” is described as the first item name 151b, and “Taro Yamada” is described as the item content 151c. “[Appearance]” is described as the second item name 151b, and “Jiro Yamada” is described as the item content 151c. “[Caster]” is described as the third item name 151b, and “Yamada Hanako” is described as the item content 151c.

  The performer information 152 is information regarding performers who appear in the program. Here, the data structure of the performer information 152 will be described with reference to FIG. As shown in FIG. 3, performer name 152a, performer image 152b, and feature information 152c are associated with performer information 152. The performer name 152a is the name of the performer. The performer image 152b is a still image of the performer's face indicated by the performer name 152a. The characteristic information 152c is characteristic information of the performer, and includes, for example, the date of birth, birthplace, and URL (Uniform Resource Locator) of the site related to the performer. Various types of information included in the performer information 152 are acquired by the information acquisition unit 164 via the network 7 and managed by the data management unit 165.

  As an example, when the performer name 152a is “Taro Yamada”, the face image of Taro Yamada is stored in the performer image 152b. The feature information 152c stores “born July 1, 1985” as the date of birth, “born in Tokyo” as the place of birth, and “http: // ~ yamadataro” as the site related to the performers.

  The control unit 16 includes a video processing unit 161, a video output unit 162, a data processing unit 163, an information acquisition unit 164, a data management unit 165, a display information generation unit 166, and a face recognition unit 167. For example, the control unit 16 corresponds to an integrated device such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). Moreover, the control part 16 respond | corresponds to electronic circuits, such as CPU (Central Processing Unit) and MPU (Micro Processing Unit), for example.

  The video processing unit 161 performs video processing on the video data output from the tuner 11 and outputs the video data subjected to the video processing to the video output unit 162. The video output unit 162 outputs the video data processed by the video processing unit 161 to the display unit 13.

  The data processing unit 163 performs data processing on the program information output from the tuner 11, and outputs the data processed program information to the information acquisition unit 164.

  The information acquisition unit 164 acquires program information from the data processing unit 163, analyzes the acquired program information, and extracts performer names as keywords from the analyzed program information. For example, the information acquisition unit 164 extracts a person name (item content) of a person who appears in the program from the program information.

  In addition, the information acquisition unit 164 acquires a still image of the face of the person name using a person name extracted from the program information as a keyword from a route different from the delivery route for distributing the video of the program. That is, the information acquisition unit 164 acquires a still image of the face of the person name as a keyword from a location different from the broadcast station 2 that distributes the video of the program. For example, the information acquisition unit 164 uses the search engine 5 connected to the network 7 to search for a still image of a face with a person name using the extracted person name as a keyword. Further, the information acquisition unit 164 searches the information providing server 6 connected to the network 7 for information related to the person with the person name using the extracted person name and the still image searched from the person name as a keyword. Information related to a person includes a site related to the person with the date of birth, hometown, and person name.

  The information acquisition unit 164 acquires the program information before the program itself included in the program information is distributed from the broadcast station 2. And the information acquisition part 164 searches the information regarding the person who concerns on the said program until the program itself contained in program information is delivered, and memorize | stores the searched information in the memory | storage part 15 by the data management part 165 mentioned later. .

  The data management unit 165 stores the program information analyzed by the information acquisition unit 164 in the program information 151 of the storage unit 15. Further, the data management unit 165 stores the still image of the person's face searched by the information acquisition unit 164 and information about the person in the performer information 152 of the storage unit 15 as performer information. In addition, when there is a request for various data from the display information generation unit 166 described later, the data management unit 165 reads the requested data from the performer information 152 and delivers the read data.

  The display information generation unit 166 causes the face recognition unit 167, which will be described later, to detect the face image closest to the specified position with respect to the image of the video, and to perform face recognition on the detected face image. Then, the display information generation unit 166 receives the face recognition result, and specifies the person (performer name) of the face image whose matching is matched based on the performer image stored in the performer information 152. Then, the display information generation unit 166 generates display information based on the feature information stored in the performer information 152 in order to display the feature information for the specified person.

  Further, the display information generation unit 166 acquires the program information from the data processing unit 163 and is described in the program information so as to display the performers described in the acquired program information when a predetermined switch operation is performed. Display information including information is generated.

  The face recognizing unit 167 detects an object that can be recognized as a face in the image closest to the position designated with respect to the moving image. For example, when the face recognition unit 167 touches the image of the video displayed on the display unit 13 with the input unit 14, a basic frame ( Hereinafter, it is also referred to as an I frame). Then, the face recognition unit 167 calculates the coordinates of the I frame corresponding to the designated coordinates in the touched image.

  Here, a video frame configuration when the compression method is MPEG2 will be described. FIG. 4 is a diagram for explaining the frame structure of MPEG2. As shown in FIG. 4, an MPEG2 frame has three types of frames: an I frame (Intra-coded Frame), a P frame (Predicted Frame), and a B frame (Bidirectional Predicted Frame).

  The I frame is compressed by only a single frame and is generated so that the quality of the decoding result is high. That is, an I frame is a frame that is encoded without using inter-frame prediction. The P frame is generated with difference information from the referenced frame by referring to the I frame by inter-frame prediction in the time axis forward direction (forward direction). Depending on the bit rate distribution, the quality of the decoding result may be lower than that of the I frame. The B frame is generated with difference information from the referenced frame by referring to the preceding and following P frames or the preceding and following I frames by inter-frame prediction in the forward (forward) and backward (backward) directions of the time axis. The quality of the decoding result is lower than that of the I frame or P frame.

  It is assumed that there are four original frames (frames 1 to 4) in the forward direction under the MPEG2 frame configuration. In this case, in MPEG2, for example, the first original frame 1 in the forward direction is generated as an I frame. Therefore, when the face recognition unit 167 is touched with respect to the I frame of the video displayed on the display unit 13, the face recognition unit 167 identifies the touched I frame.

  The P frame is generated by difference information between the first original frame 1 and the original frame 4 for generating the I frame. Therefore, when the face recognition unit 167 is touched with respect to the P frame of the video displayed on the display unit 13, the face recognition unit 167 specifies the I frame referred to by the P frame.

  The first B frame is generated by difference information between the first original frame 1 for generating the I frame, the fourth original frame 4 for generating the P frame, and the original frame 2. Further, the next B frame is generated by difference information between the first original frame 1 for generating the I frame, the fourth original frame 4 for generating the P frame, and the original frame 3. Therefore, when the face recognition unit 167 is touched on the B frame of the video displayed on the display unit 13, the face recognition unit 167 specifies the P frame referred to by the B frame, and further specifies the I frame referred to by the P frame.

  In the inter-frame prediction, a “motion compensation” technique that compensates for the motion between frames is used. In order to perform this motion compensation, the difference information includes a “motion vector” that estimates the amount of motion of a portion (block) in which there is motion between images. For example, a block in which P frame motion compensation has been performed (hereinafter referred to as a motion compensation block) and a motion vector will be described with reference to FIG. FIG. 5 is a diagram for explaining a motion compensation block and a motion vector of a P frame. Here, it is assumed that the P frame refers to the I frame. The motion compensation block for the P frame is a position shifted from the motion compensation block in which the motion of the I frame to be referenced has moved by a motion vector plus. In the example of FIG. 5, the motion compensation block B1 in which the motion of the I frame has occurred is a rectangle generated from (xa1, ya1) and (xb1, yb1), and the motion vector V12 is (xa2-xa1, ya2-ya1) To do. Then, the motion compensation block B2 of the P frame becomes a rectangle generated from (xa2, ya2) and (xb2, yb2). In other words, the motion compensation block B1 of the I frame referred to by the P frame is a position shifted from the motion compensation block B2 of the P frame by a motion vector V12 minus, that is, a returned position.

  Next, a method of calculating the coordinates of the I frame corresponding to the touched coordinates when the P frame is touched under the same conditions as in FIG. 5 will be described with reference to FIG. 6 and 7 are diagrams illustrating a method for calculating coordinates corresponding to the I frame when the P frame is touched. FIG. 6 illustrates the case where the coordinates inside the motion compensation block are touched, and FIG. 7 illustrates the case where the coordinates outside the motion compensation block are touched.

  As shown in FIG. 6, when the touched coordinate P2 is within the motion compensation block B2 of the P frame, the face recognition unit 167 calculates the coordinate P1 corresponding to the I frame using the motion vector V12. That is, the face recognizing unit 167 calculates the position moved negatively by the motion vector V12 from the coordinate P2 touched in the motion compensation block B2 of the P frame, that is, the returned position as the corresponding coordinate P1 of the I frame.

  As shown in FIG. 7, when the touched coordinate P3 is outside the motion compensation block B2 of the P frame, the face recognition unit 167 has the same coordinate as the touched coordinate P3 because the coordinate P3 is not a portion that has moved. As the corresponding coordinates of the I frame.

  Returning to FIG. 1, the face recognition unit 167 detects all objects that can be recognized as faces in the specified I frame, and then selects the object closest to the corresponding coordinates of the I frame from the detected objects. To detect. In addition, the face recognition unit 167 performs face recognition by comparing the detected object with the performer image stored in the performer information 152 and notifies the display information generation unit 166 of the result of face recognition.

  Further, the face recognition unit 167 calculates coordinates corresponding to each frame that changes with time for the touched coordinates. For example, the face recognition unit 167 calculates the coordinates of each frame corresponding to the designated coordinates in the touched image in accordance with the type of the touched image frame.

  Here, a method of calculating the coordinates of each frame corresponding to the touched coordinates when the P frame is touched will be described with reference to FIG. FIG. 8 is a diagram for explaining a method of calculating the corresponding coordinates of each frame. The case where the touched frame is a P frame and the touched coordinates are coordinates P00 (xa0, ya0) in the motion compensation block B31 will be described.

  As shown in FIG. 8, the face recognition unit 167 calculates the coordinate P01 (xa1, ya1) corresponding to the I frame using the motion vector because the touched coordinate P00 is in the motion compensation block B31 of the P frame. Then, the calculated coordinates are set as the coordinates of the start frame. That is, the face recognizing unit 167 calculates the position moved negative by the motion vector from the coordinate P00 touched in the motion compensation block B31 of the P frame, that is, the returned position as the corresponding coordinate P01 of the I frame.

Next, the face recognition unit 167 calculates the corresponding coordinates of each P frame after the start frame from the coordinates P00 of the start frame and the motion vector of each P frame. In FIG. 8, the face recognition unit 167 calculates coordinates P02 (xa2, ya2) from the coordinates P00 of the start frame and the motion vector for the corresponding coordinates of the P frame next to the start frame. Similarly, the face recognition unit 167 calculates corresponding coordinates of other P frames up to the next I frame. In FIG. 8, the face recognition unit 167 calculates the corresponding coordinates of the next P frame after the touched P frame as P04 (xa4, ya4), and further sets the corresponding coordinates of the next P frame as P05 (xa5, ya5). calculate. Then, the face recognition unit 167, based on the movement amount of the corresponding coordinates calculated from the corresponding coordinates P01 of the start frame and the corresponding coordinates P05 of the last P frame, the corresponding coordinates P06 (xa6, ya6) of the next I frame. Predict. In FIG. 8, the face recognition unit 167 can predict as follows.
xa6 = xa1 + (xa5-xa1) × 5/4
ya6 = ya1 + (ya5-ya1) × 5/4

  Returning to FIG. 1, the face recognition unit 167 further calculates coordinates for displaying information of each frame that changes over time. For example, the face recognition unit 167 calculates coordinates outside the area overlapping with the detected object as coordinates for displaying information. For example, for the start frame, the face recognition unit 167 calculates coordinates for displaying information so as not to overlap the detected object position based on the detected object position and the corresponding coordinates corresponding to the touched coordinates. To do. As an example, when the corresponding coordinate corresponding to the touched coordinate does not overlap the detected object position for the start frame, the face recognition unit 167 sets the coordinate for displaying information as the corresponding coordinate. Further, when the corresponding coordinates corresponding to the touched coordinates overlap the detected object position, the face recognition unit 167 sets the coordinates for displaying information to the coordinates that do not overlap the detected object position. Then, the face recognition unit 167 calculates coordinates for displaying the information of each frame using the coordinates for displaying the information of the start frame and the motion compensation of each frame. The method for calculating the coordinates of each frame corresponding to the coordinates for displaying the information of the I frame is the same as the method for calculating the coordinates of each frame corresponding to the touched coordinates as shown in FIG. Therefore, the description is omitted.

  Further, the face recognition unit 167 notifies the display information generation unit 166 of a calculation result including coordinates for displaying information of each frame.

[Processing Procedure of Information Acquisition Unit According to Embodiment]
Next, a processing procedure of the information acquisition unit according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating the processing procedure of the information acquisition unit according to the embodiment.

  First, the information acquisition unit 164 determines whether program information has been acquired (step S11). When it is determined that the program information has not been acquired (step S11; No), the information acquisition unit 164 repeats the determination process until the program information is acquired. On the other hand, when it determines with having acquired program information (step S11; Yes), the information acquisition part 164 extracts a performer name from the acquired program information.

  And the information acquisition part 164 searches the information about the performer's still image and the performer from the route different from the delivery route for delivering the video of the program, using the performer name extracted from the program information as a keyword (step S12). . For example, the information acquisition unit 164 uses the search engine 5 connected to the network 7 to search for a still image of the face of the performer name using the performer name as a keyword. And the information acquisition part 164 searches the information regarding the performer from the information provision server 6 connected to the network 7 by using the performer name and the searched still image as keywords.

  And the information acquisition part 164 memorize | stores the searched information in the performer information 152 through the data management part 165 (step S13). That is, the performer information 152 stores a still image of the performer's face and information about the performer.

[Processing procedure of face recognition unit according to embodiment]
Next, the processing procedure of the face recognition unit according to the embodiment will be described with reference to FIGS. 10 to 12 are flowcharts illustrating the processing procedure of the face recognition unit according to the embodiment. It is assumed that the video of the program is displayed on the display unit 13.

  First, the face recognition unit 167 determines whether or not a touch input has been made on the image of the video displayed on the display unit 13 (step S201). When it is determined that there is no touch input (step S201; No), the face recognition unit 167 repeats the determination process until there is a touch input. On the other hand, when it is determined that there is a touch input (step S201; Yes), the face recognition unit 167 identifies the basic frame (I frame) nearest to the coordinates specified by the touch input, and corresponds to the specified coordinates. The coordinates of the basic frame to be calculated are calculated (step S202).

  Then, the face recognition unit 167 performs face recognition processing with the identified basic frame (step S203). For example, the face recognizing unit 167 detects all objects that can be recognized as faces in the identified basic frame, and then detects an object closest to the calculated coordinates of the basic frame from the detected objects. Then, the face recognition unit 167 collates the detected object with the performer image of the performer information 152 and performs face recognition.

  Subsequently, the face recognizing unit 167 calculates the corresponding coordinates of each frame that changes over time with respect to the coordinates designated by the touch input (step S204). Further, the face recognition unit 167 calculates coordinates for displaying information of each frame that changes over time (step S205). For example, the face recognition unit 167 calculates coordinates for displaying information using the position of the object detected in the basic frame, the corresponding coordinates of each frame, and motion compensation between frames.

  Then, the face recognition unit 167 notifies the display information generation unit 166 of the result (step S206). That is, the face recognition unit 167 notifies the display information generation unit 166 of the result of face recognition and the calculation result of coordinates for displaying information of each frame.

  Thereafter, the face recognition unit 167 determines whether or not the display control process has ended (step S207). If it is determined that the display control process has not ended (step S207; No), the face recognition unit 167 proceeds to step S201. On the other hand, when it is determined that the display control process has ended (step S207; Yes), the face recognition unit 167 ends the face recognition process.

[Corresponding coordinate calculation processing of I frame]
Next, the corresponding coordinate calculation processing of the I frame corresponding to the designated coordinates shown in step S202 of FIG. 10 will be described with reference to FIG.

  First, the face recognition unit 167 determines whether or not the touched frame type is a P frame (step S21). When it is determined that the type of the touched frame is a P frame (step S21; Yes), the face recognition unit 167 identifies an I frame that is referred to by the P frame (step S22). Furthermore, the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S23). When the touched coordinate is within the motion compensation block (step S23; Yes), the face recognition unit 167 calculates the corresponding coordinate of the I frame corresponding to the touched coordinate using the motion vector (step S24). . On the other hand, when the touched coordinate is not within the motion compensation block (step S23; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the I frame (step S25). Then, the face recognition unit 167 ends the corresponding coordinate calculation processing for the I frame when the type of the touched frame is the P frame.

  Returning to step S21, when it is determined that the touched frame type is not a P frame (step S21; No), the face recognition unit 167 determines whether the touched frame type is a B frame. (Step S26). When it is determined that the type of the touched frame is not the B frame (step S26; No), the face recognition unit 167 identifies the type of the touched frame as the I frame, and the touched coordinates are the corresponding coordinates of the I frame. (Step S27). Then, the face recognition unit 167 ends the corresponding coordinate calculation processing for the I frame when the type of the touched frame is the I frame.

  Returning to step S26, when it is determined that the type of the touched frame is the B frame (step S26; Yes), the face recognition unit 167 selects the front I frame or P frame referred to by the B frame ( Step S28). Then, the face recognition unit 167 determines whether or not the selected reference frame is an I frame (step S29). When it is determined that the reference frame is the I frame (step S29; Yes), the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S30). When the touched coordinate is within the motion compensation block (step S30; Yes), the face recognition unit 167 calculates the corresponding coordinate of the I frame corresponding to the touched coordinate using the motion vector (step S31). . On the other hand, when the touched coordinate is not within the motion compensation block (step S30; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the I frame (step S32). Then, the face recognition unit 167 proceeds to step S40.

  On the other hand, when it is determined that the frame is not an I frame, that is, a P frame (step S29; No), the face recognition unit 167 determines whether or not the touched coordinate is within the motion compensation block (step S33). When the touched coordinate is within the motion compensation block (step S33; Yes), the face recognition unit 167 calculates the corresponding coordinate of the P frame corresponding to the touched coordinate using the motion vector (step S34). . On the other hand, when the touched coordinate is not within the motion compensation block (step S33; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the P frame (step S35).

  Subsequently, the face recognizing unit 167 specifies the I frame referred to by the P frame (step S36). Furthermore, the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S37). When the touched coordinate is within the motion compensation block (step S37; Yes), the face recognition unit 167 calculates the corresponding coordinate of the I frame corresponding to the touched coordinate using the motion vector (step S38). The process proceeds to step S40. On the other hand, when the touched coordinate is not within the motion compensation block (step S37; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the I frame (step S39), and proceeds to step S40.

  In step S40, the face recognizing unit 167 determines whether or not the rear frame referred to by the B frame has been selected (step S40). When it is determined that the rear frame referred to by the B frame has not been selected (step S40; No), the face recognition unit 167 selects the rear I frame or P frame referred to by the B frame (step S41). Then, the face recognition unit 167 proceeds to step S29 in order to continue the corresponding coordinate calculation processing of the I frame. On the other hand, when it is determined that the rear frame to be referred to by the B frame is selected (step S40; Yes), the face recognition unit 167 calculates the corresponding coordinates of the I frame when the type of the touched frame is the B frame. End the process.

[Corresponding coordinate calculation processing of each frame]
Next, the corresponding coordinate calculation processing of each frame corresponding to the designated coordinates shown in step S204 of FIG. 10 will be described with reference to FIG.

  First, the face recognition unit 167 determines whether or not the type of the touched frame is an I frame (step S51). When it is determined that the type of the touched frame is the I frame (step S51; Yes), the face recognition unit 167 sets the touched frame as the start frame and the next I frame as the end frame (step S52). Then, the face recognition unit 167 sets the touched coordinates as the coordinates of the start frame (step S53). Then, the face recognition unit 167 proceeds to step S82 in order to calculate the coordinates of each frame.

  Returning to step S51, when it is determined that the touched frame type is not the I frame (step S51; No), the face recognition unit 167 determines whether the touched frame type is the P frame. (Step S54). When it is determined that the type of the touched frame is the P frame (step S54; Yes), the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S55). When the touched coordinate is within the motion compensation block (step S55; Yes), the face recognition unit 167 calculates the corresponding coordinate of the I frame corresponding to the touched coordinate using the motion vector, and the calculated coordinate Is the coordinates of the start frame (step S56). Then, the face recognition unit 167 proceeds to step S82 in order to calculate the coordinates of each frame. On the other hand, when the touched coordinate is not within the motion compensation block (step S55; No), the face recognition unit 167 sets the touched coordinate as the coordinate of the start frame (step S57). Then, the face recognition unit 167 proceeds to step S82 in order to calculate the coordinates of each frame.

  Returning to step S54, when it is determined that the type of the touched frame is not a P frame (step S54; No), the face recognition unit 167 determines whether or not the touched frame is a B frame (step S54). S58). When it is determined that the touched frame is not the B frame (step S58; No), the face recognition unit 167 ends the process because the frame is an unknown type.

  On the other hand, when it is determined that the touched frame is the B frame (step S58; Yes), the face recognition unit 167 determines whether or not the front reference frame is the I frame (step S59). When it is determined that the front reference frame is the I frame (step S59; Yes), the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S60). When it is determined that the touched coordinates are within the motion compensation block (step S60; Yes), the face recognition unit 167 calculates the corresponding coordinates of the I frame corresponding to the touched coordinates using the motion vector, The calculated coordinates are set as the coordinates of the start frame (step S61). On the other hand, when the touched coordinate is not within the motion compensation block (step S60; No), the face recognition unit 167 sets the touched coordinate as the coordinate of the start frame (step S62).

  Returning to step S59, when it is determined that the front reference frame is not an I frame, that is, a P frame (step S59; No), the face recognition unit 167 determines whether or not the touched coordinate is within the motion compensation block. Is determined (step S63). When it is determined that the touched coordinates are within the motion compensation block (step S63; Yes), the face recognition unit 167 calculates the corresponding coordinates of the P frame corresponding to the touched coordinates using the motion vector ( Step S64). On the other hand, when the touched coordinate is not within the motion compensation block (step S63; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the P frame (step S65).

  Furthermore, the face recognition unit 167 selects an I frame that is referred to by the P frame (step S66). Then, the face recognition unit 167 determines whether or not the corresponding coordinates of the P frame are within the motion compensation block (step S67). When it is determined that the corresponding coordinates of the P frame are within the motion compensation block (step S67; Yes), the face recognition unit 167 calculates the corresponding coordinates of the I frame using the motion vector, and uses the calculated coordinates as the start frame. Coordinate candidate 1 (step S68). On the other hand, when it is determined that the corresponding coordinate of the P frame is not within the motion compensation block (step S67; No), the face recognition unit 167 sets the corresponding coordinate of the P frame as the coordinate candidate 1 of the start frame (step S69).

  Next, the face recognition unit 167 determines whether or not the rear reference frame is an I frame (step S70). When it is determined that the rear reference frame is the I frame (step S70; Yes), the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block (step S71). When it is determined that the touched coordinate is within the motion compensation block (step S71; Yes), the face recognition unit 167 calculates the corresponding coordinate of the I frame corresponding to the touched coordinate using the motion vector, The calculated coordinates are set as the coordinates of the end frame (step S72). On the other hand, when the touched coordinate is not within the motion compensation block (step S71; No), the face recognition unit 167 sets the touched coordinate as the coordinate of the end frame (step S73).

  Returning to step S70, when it is determined that the rear reference frame is not the I frame, that is, the P frame (step S70; No), the face recognition unit 167 determines whether or not the touched coordinates are within the motion compensation block. Is determined (step S74). When it is determined that the touched coordinate is within the motion compensation block (step S74; Yes), the face recognition unit 167 calculates the corresponding coordinate of the P frame corresponding to the touched coordinate using the motion vector ( Step S75). On the other hand, when the touched coordinate is not within the motion compensation block (step S74; No), the face recognition unit 167 sets the touched coordinate as the corresponding coordinate of the P frame (step S76).

  Further, the face recognition unit 167 selects an I frame that is referred to by the P frame (step S77). Then, the face recognition unit 167 determines whether or not the corresponding coordinates of the P frame are within the motion compensation block (step S78). When it is determined that the corresponding coordinates of the P frame are within the motion compensation block (step S78; Yes), the face recognition unit 167 calculates the corresponding coordinates of the I frame using the motion vector, and uses the calculated coordinates as the start frame. Coordinate candidate 2 (step S79). On the other hand, when it is determined that the corresponding coordinate of the P frame is not within the motion compensation block (step S78; No), the face recognition unit 167 sets the corresponding coordinate of the P frame as the coordinate candidate 2 of the start frame (step S80).

  The face recognizing unit 167 then selects the one in which the motion compensation block is designated from the coordinate candidates 1 and 2 of the start frame, and sets the selected coordinate candidate as the coordinates of the start frame (step S81).

  Subsequently, the face recognition unit 167 calculates the corresponding coordinates of the P frames after the start frame from the start frame to the end frame using motion compensation (step S82). Then, the face recognition unit 167 calculates the corresponding coordinates of the end frame corresponding to the touched coordinates (step S83). For example, the face recognition unit 167 predicts the corresponding coordinates of the end frame based on the movement amount of the corresponding coordinates calculated from the corresponding coordinates of the start frame corresponding to the touched coordinates and the corresponding coordinates of the last P frame. To do.

  Then, the face recognition unit 167 calculates the corresponding coordinates of the B frame corresponding to the touched coordinates (step S84). For example, the face recognition unit 167 calculates using the corresponding coordinates of the start frame, the end frame, and the P frame, and motion compensation. Then, the face recognition unit 167 ends the corresponding coordinate calculation process for each frame.

[Example of display screen of display control device]
Next, an example of the display screen of the display control device 8 will be described with reference to FIG. FIG. 13 is a diagram illustrating an example of a display screen of the display control apparatus according to the embodiment. In addition, the information regarding the person of the program related to the displayed video is assumed to be stored in the performer information 152 of the storage unit 15 before the program is distributed. As illustrated in FIG. 13, the face recognition unit 167 determines whether or not there is a touch input on the image G1 of the video displayed on the display unit 13. Here, it is determined that there is a touch input. . Then, the face recognition unit 167 sets the coordinates designated by the touch input as P11.

  Then, the face recognition unit 167 detects an object that can be recognized as a face in the image G1 that is closest to the coordinate P11 designated by the touch input. Here, the face recognition unit 167 detects an object O1 that can be recognized as a face in the image G1 that is closest to the coordinate P11. Then, the face recognition unit 167 performs face recognition by comparing the detected object O1 with the performer image of the performer information 152 stored in the storage unit 15.

  Then, the display information generation unit 166 identifies a person whose face matches as a result of face recognition by the face recognition unit 167 based on the performer information 152, and the feature information for the identified person does not overlap the face position. As shown in FIG. Here, the name of the performer “...” and the site “http :: // ...” related to the performer are displayed in the image G2 so as not to overlap the position of the face corresponding to the object O1. The

  Note that when the moving image is touched, the face recognition unit 167 detects an object that can be recognized as a face in the image closest to the touched position. In this case, the face recognizing unit 167 does not change the display speed of the distributed moving image even if the moving image is touched (single speed), and the face in the image closest to the touched position is detected. Detect recognizable objects. However, the face recognition unit 167 is not limited to this, and when a moving image is touched, the face recognition unit 167 shifts to a time shift state, and the face in the image closest to the touched position in the shifted state Recognizable objects may be detected. Here, the time shift state refers to a state where the display screen is paused and the distributed video is temporarily recorded. Even in the time shift state, the face recognizing unit 167 identifies the I frame referred to by the touched frame as in the case of 1 × speed, and is closest to the touched position using the identified I frame. What is necessary is just to detect a face image.

  Further, the face recognition unit 167 shifts to a slowly displaying state when a moving image is touched, and detects an object that can be recognized as a face in the image closest to the touched position in the shifted state. You may do it. Even in the state of slow display, the face recognition unit 167 identifies the I frame that is referred to by the touched frame, as in the case of the 1 × speed, and is closest to the touched position using the identified I frame. A certain face image may be detected.

[Effect of Example]
According to the above-described embodiment, the display control device 8 searches for information related to the still image of the performer's face and the performer's person included in the distributed moving image from a route different from the distribution route for distributing the moving image. And the display control apparatus 8 memorize | stores the information regarding the searched performer's face image and person in the performer information 152 for every performer. Then, the display control device 8 detects the face image closest to the position designated with respect to the moving image. Then, the display control device 8 specifies the person of the detected face image based on the performer's face image stored in the performer information 152. And the display control apparatus 8 displays the information regarding the specified person. According to such a configuration, the display control device 8 performs a search by searching for information on the face image and the person of the performer included in the distributed video from the search engine 5 on a different route from the distribution route for distributing the video. The information is stored in the person information 152. For this reason, the display control device 8 distributes the moving image information about the person of the corresponding face image by using the face image of the performer information 152 for comparison with the face image nearest to the position specified by the moving image. It can be displayed universally for any moving image without depending on the broadcasting station 2 to be used. That is, the display control device 8 can provide information on the desired performer among the performers appearing in the moving image, regardless of the broadcast station 2, regardless of the moving image.

  Moreover, according to the said Example, the display control apparatus 8 acquires the name of the performer contained in a moving image from the broadcast station 2, and uses the acquired performer's name as a keyword, and the person corresponding to the name of the performer concerned. Search for information about face images and people. According to this configuration, the display control device 8 uses the name of the performer included in the video to search for the face image of the person corresponding to the name of the performer and information about the person, so that the appearance can be easily performed. Information about the person corresponding to the person's name can be acquired.

  Further, according to the above-described embodiment, the display control device 8 specifies the basic frame with the largest amount of information that is referred to by the frame of the image whose position is specified, and determines the position corresponding to the position of the specified basic frame. calculate. Then, the display control device 8 detects the face image closest to the position calculated using the identified basic frame. And the display control apparatus 8 collates the performer's face image memorize | stored in the performer information 152, and the detected face image, and specifies a person. According to such a configuration, the display control device 8 detects the corresponding face image using the basic frame having the largest amount of information, which is referred to by the frame of the image whose position is specified, and therefore is stored in the performer information 152. It is possible to accurately collate with the performer's face image. As a result, the display control device 8 can provide accurate information regarding the person of the face image closest to the designated position.

  Moreover, according to the said Example, the display control apparatus 8 acquires the performer name contained in a moving image by the time a moving image is distributed, and uses the acquired performer name as a keyword and the person corresponding to the performer name. Search for information about face images and people before the video is distributed. And the display control apparatus 8 memorize | stores the information regarding the searched performer's face image and person in the performer information 152 for every performer. According to such a configuration, the display control device 8 acquires the performer name included in the video before the video is distributed, and searches for information using the acquired performer name as a keyword. For this reason, the display control apparatus 8 can display the information of a desired performer at high speed using the performer information 152 if it is reflected in the performer information 152 when the moving image is actually distributed. .

  Further, according to the above embodiment, when the position is specified for the moving image, the display control device 8 pauses and shifts to the time shift state, and is closest to the position specified in the shifted state. The face image at is detected. Then, the display control device 8 specifies the person of the detected face image based on the performer's face image stored in the performer information 152. According to such a configuration, the display control device 8 can specify the person of the detected face image based on the face image stored in the performer information 152 even when the display control apparatus 8 shifts to the time shift state. For this reason, the display control device 8 can display the person of the specified face image for any video regardless of the broadcast station 2 to which the video is distributed.

  In the above embodiment, the face recognition unit 167 detects the face image closest to the coordinates designated by the touch input when there is a touch input to the image of the image displayed on the display unit 13. Then, the detected face image is collated with the performer image of the performer information 152 to perform face recognition. Then, the display information generation unit 166 identifies the person whose face matches as a result of the face recognition by the face recognition unit 167 based on the performer information 152 and causes the display unit 13 to display the characteristic information for the identified person. . However, the display information generation unit 166 may replace the information to be displayed on the display unit 13 with the information about the person and use the information about the product. In this case, the product name is included in the program information distributed from the broadcasting station 2. And the information acquisition part 164 acquires program information, analyzes the acquired program information, and extracts the product name used as a keyword from the analyzed program information. Then, the information acquisition unit 164 acquires a still image of the product with the product name as a keyword and other feature information from a route different from the delivery route for distributing a program such as TV shopping, for example, and performs the performer information 152. Is stored in the product information corresponding to. Then, when there is a touch input on the image of the image displayed on the display unit 13, the face recognition unit 167 detects the image of the product closest to the coordinates specified by the touch input and detects Pattern recognition is performed by comparing the product image with the still image of the product in the product information. Then, if the display information generation unit 166 identifies a product that matches as a result of pattern recognition by the face recognition unit 167 based on the product information, the display unit 13 displays characteristic information for the identified product. good.

  Further, in the above embodiment, the display control device 8 targets a moving image, and displays information about a face near the coordinates specified by the touch input when there is a touch input on the image of the moving image. . However, the display control device 8 may target a still image and display information related to a face near the coordinates specified by the touch input when a touch input is performed on the still image.

  In the above embodiment, the display control device 8 targets the video distributed from the broadcasting station 2 and relates to a face near the coordinates specified by the touch input when the touch input is performed on the video image. Information was displayed. However, the display control device 8 targets the video supplied from the video, and displays information about the face near the coordinates specified by the touch input when there is a touch input on the video image. Also good. In this case, the information acquisition unit 164 acquires program information corresponding to the title from the information providing server 6 on a different route from the supply route through which the video is supplied, using the title of the video to be played as a keyword. And the information acquisition part 164 should just analyze the acquired program information, and should extract the person name used as a keyword from the analyzed program information. As a result, the display control device 8 can search for information on a person's face image corresponding to the person name and information on the person using the person name included in the video to be played back, and can easily acquire such information. . As a result, the display control device 8 does not depend on the video of the video supply source for the information on the desired performer among the performers appearing in the video of the video. Can be provided.

[Programs]
The display control device 8 is equipped with functions such as the information acquisition unit 164, the data management unit 165, the display information generation unit 166, and the face recognition unit 167 in an information processing apparatus such as a known personal computer or workstation. Can be realized.

  In addition, each component of each illustrated apparatus does not necessarily need to be physically configured as illustrated. That is, the specific mode of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the information acquisition unit 164 and the data management unit 165 may be integrated as one unit. On the other hand, the face recognition unit 167 includes a calculation unit that calculates coordinates corresponding to a basic frame of designated coordinates, a face recognition unit that recognizes a face using basic frames, and a calculation unit that calculates coordinates corresponding to each frame of designated coordinates; Alternatively, it may be distributed to a calculation unit that calculates coordinates corresponding to each frame of display coordinates. Further, a storage unit that stores performer information 152 and the like may be connected as an external device of the display control device 8 via the network 7.

  The various processes described in the above embodiments can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. Therefore, in the following, an example of a computer that executes a display control program having the same function as the control unit 16 of the display control device 8 illustrated in FIG. 1 will be described with reference to FIG.

  FIG. 14 is a diagram illustrating an example of a computer that executes a display control program. As shown in FIG. 14, the computer 200 includes a CPU 201 that executes various arithmetic processes, an input device 202 that receives input of data from a user, and a display 203. The computer 200 also includes a reading device 204 that reads a program and the like from a storage medium, and an interface device 205 that exchanges data with other computers and the like via a network. The computer 200 also includes a RAM 206 that temporarily stores various information and a hard disk device 207. Furthermore, the computer 200 includes a tuner 208 that receives broadcast data distributed from a broadcasting station. The devices 201 to 208 are connected to the bus 209.

  The hard disk device 207 stores a display control program 207a having the same function as the control unit 16 shown in FIG. The hard disk device 207 stores display control related information 207b corresponding to various information stored in the storage unit 15 shown in FIG.

  Then, the CPU 201 reads the display control program 207a from the hard disk device 207 and develops it in the RAM 206, so that the display control program 207a functions as the display control process 206a. Then, the display control process 206a expands the information read from the display control related information 207b and the like in an area allocated to itself on the RAM 206 as appropriate, and executes various data processing based on the expanded data.

  Note that the display control program 207a and the display control related information 207b are not necessarily stored in the hard disk device 207 from the beginning. For example, the display control program 207a and the like are stored in a “portable physical medium” such as a flexible disk (FD), a CD-ROM, a DVD disk, a magneto-optical disk, and an IC card inserted into the computer 200. Then, the computer 200 may read and execute the display control program 207a and the like from these.

  The following supplementary notes are further disclosed with respect to the embodiments including the above examples.

(Supplementary Note 1) An acquisition unit that acquires image data and feature data of a person included in a supplied image from a route different from a supply route for supplying an image;
A storage unit for storing image data and feature data acquired by the acquisition unit for each person;
A detection unit that detects a face image closest to a position designated with respect to the image;
A specifying unit for specifying the person of the face image detected by the detection unit based on the image data of the person stored in the storage unit;
And a display unit that displays characteristic data for the person specified by the specifying unit.

(Additional remark 2) The said acquisition part acquires the name of the person included in the said image from the supply path | route to which the said image is supplied, or a different path | route from the said supply path | route, and the person corresponding to the said name is acquired from the acquired person's name. The display control apparatus according to appendix 1, wherein image data and feature data are acquired.

(Additional remark 3) The said acquisition part specifies the basic frame with the most information content which the flame | frame of the image by which the said position was designated references, calculated the position corresponding to the said position of the specified basic frame, and specified Using a basic frame to detect the face image closest to the calculated position,
The display control apparatus according to appendix 1 or appendix 2, wherein the specifying unit specifies the person by collating the image data of the person with the face image detected by the detection unit.

(Supplementary Note 4) The acquisition unit acquires a name of a person included in the image until the image is distributed, and acquires image data and feature data of the person corresponding to the name from the acquired name of the person. The display control apparatus according to appendix 2, characterized by:

(Supplementary Note 5) When the position is specified for the image, the detection unit pauses and shifts to a time shift state, and detects a face image closest to the position specified in the shifted state. The display control device according to any one of appendix 1 to appendix 4, wherein the display control device is detected.

(Appendix 6)
Obtain image data and feature data of the person included in the supplied image from a different route from the supply route for supplying the image,
Storing the acquired image data and feature data for each person;
Detecting the face image closest to the specified position relative to the image;
Based on the stored image data of the person, the person of the detected face image is specified,
A display control program for executing processing for displaying characteristic data for the specified person.

(Appendix 7) A display control method in which a computer controls display,
Obtain image data and feature data of the person included in the supplied image from a different route from the supply route for supplying the image,
Storing the acquired image data and feature data for each person;
Detecting the face image closest to the specified position relative to the image;
Based on the stored image data of the person, the person of the detected face image is specified,
A display control method comprising a process of displaying characteristic data for the specified person.

DESCRIPTION OF SYMBOLS 1 Display control system 2 Broadcasting station 3 Video server 4 Program information server 5 Search engine 6 Information provision server 7 Network 8 Display control apparatus 11 Tuner 12 Network interface part 13 Display part 14 Input part 15 Storage part 151 Program information 152 Performer information 16 Control unit 161 Video processing unit 162 Video output unit 163 Data processing unit 164 Information acquisition unit 165 Data management unit 166 Display information generation unit 167 Face recognition unit

Claims (6)

An acquisition unit for acquiring image data and feature data of a person included in the supplied image from a different route from the supply route for supplying the image;
A storage unit for storing image data and feature data acquired by the acquisition unit for each person;
A detection unit that detects a face image closest to a position designated with respect to the image;
A specifying unit for specifying the person of the face image detected by the detection unit based on the image data of the person stored in the storage unit;
And a display unit that displays characteristic data for the person specified by the specifying unit.   The acquisition unit acquires a name of a person included in the image from a supply path through which the image is supplied or a path different from the supply path, and image data and characteristics of the person corresponding to the name from the acquired person name The display control apparatus according to claim 1, wherein data is acquired. The acquisition unit specifies a basic frame having the largest amount of information that is referred to by a frame of an image with the specified position, calculates a position corresponding to the position of the specified basic frame, and uses the specified basic frame To detect the face image closest to the calculated position,
The display control apparatus according to claim 1, wherein the specifying unit specifies the person by collating the image data of the person with the face image detected by the detection unit.   The acquisition unit acquires a name of a person included in the image until the image is distributed, and acquires image data and feature data of the person corresponding to the name from the acquired name of the person. The display control apparatus according to claim 2. On the computer,
Obtain image data and feature data of the person included in the supplied image from a different route from the supply route for supplying the image,
Storing the acquired image data and feature data for each person;
Detecting the face image closest to the specified position relative to the image;
Based on the stored image data of the person, the person of the detected face image is specified,
A display control program for executing processing for displaying characteristic data for the specified person. A display control method in which a computer controls display,
Obtain image data and feature data of the person included in the supplied image from a different route from the supply route for supplying the image,
Storing the acquired image data and feature data for each person;
Detecting the face image closest to the specified position relative to the image;
Based on the stored image data of the person, the person of the detected face image is specified,
A display control method comprising a process of displaying characteristic data for the specified person.

Images