JP2008160354A - Video output device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a video output device capable of masking persons moving within a photographing area of a camera. <P>SOLUTION: The video output device comprises: a face recognition engine 22 for recognizing faces included in a video; a mask generation part 26 for generating a mask to be applied to areas of faces detected by the face recognition engine 22; a mask composition part 28 for composing the video and the mask; and a video signal output part 32 for outputting the composite video with the mask. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a video output device such as a camera or an encoder, and more particularly to a technique for masking a part of an image for privacy protection.

  Conventionally, there has been known a monitoring system that transmits video from a monitoring camera via a network and performs monitoring in a security room or the like. In the case of monitoring a public place using such a monitoring system, for example, an example in which masking (so-called private mask) is performed so that a nearby private house or the like is not displayed on the screen is known.

Patent Document 1 discloses a surveillance camera device that puts a private mask on a video of a surveillance camera. The surveillance camera described in Patent Document 1 is a surveillance camera that can rotate in a horizontal direction and a vertical direction. In Patent Document 1, first, an area to be masked by the operator is set using an input means such as a joystick. The surveillance camera holds data for specifying the set area, calculates coordinates to be masked when the surveillance camera rotates in the horizontal direction and the vertical direction, and masks the obtained coordinates.
JP2004-304847

  In the surveillance camera described in Patent Document 1, by changing the masking coordinate according to the rotation of the surveillance camera, there is an effect that the area set by the operator can be masked regardless of the change in the imaging angle. . However, in Patent Document 1, since the masking area is fixed to a preset area, a private mask cannot be applied if a person reflected on the surveillance camera protrudes from the fixed area.

  In view of the above background, an object of the present invention is to provide a video output apparatus capable of masking a person who moves within a shooting area of a camera.

  The video output device of the present invention includes a face recognition engine that recognizes a face included in a video, a mask generation unit that generates a mask to be applied to a face area detected by the face recognition engine, a video, and the mask And a video output unit for outputting the synthesized video with mask.

  With this configuration, the face included in the video is detected, and a mask applied to the detected face area is generated and combined with the video, so even if a person is moving in real time, the mask on the face To protect your privacy. In addition, since the masking process is performed in the video output device, it is possible to prevent the image without the mask from leaking outside. The risk that the video output from the video output device can be misused by a third party can be reduced, and privacy protection can be strengthened.

  The video output device of the present invention includes an output request receiving unit that receives a video output request, and whether to output a video with a mask or a video without a mask according to an authority level included in the output request. And a switching unit for switching.

  With this configuration, it is possible to change whether to output a video with a mask or an image without a mask according to the authority level.

  In the video output device of the present invention, the switching unit outputs a video without a mask when the number of faces appearing in the video is larger than a predetermined threshold or when the face area is smaller than the predetermined threshold. It has a configuration for switching.

  With this configuration, an image without a mask can be output when there is no privacy problem. That is, when the number of faces shown in the video is larger than a predetermined threshold, the people shown in the video are regarded as a crowd, so that a privacy problem does not occur even if video without a mask is output. Also, if the face area is smaller than the predetermined threshold, it is not possible to discriminate people from the face image, so there is no privacy problem even if an image without a mask is output.

  The video output apparatus of the present invention includes a synthesis ratio setting unit that sets a synthesis ratio of the video signal and the mask, and the mask synthesis unit masks the video according to the synthesis ratio set by the synthesis ratio setting unit. It has composition to synthesize.

  With this configuration, the strength of the mask can be set according to the application.

  The video output device of the present invention includes a face area cutout unit that cuts out a face area detected by the face recognition engine, and the video output unit outputs a clipped video clipped by the face area cutout unit as a facial image. It has the structure which transmits to the server which performs the process based on an image | video.

  With this configuration, the server can perform processing based on the face image without performing the process of cutting out the face image, thereby reducing the processing load. It is also possible to reduce the amount of data transmitted from the video output device to the server.

  The video output system of the present invention is a video output system including a video output device and a client terminal that receives and displays video from the video output device, and the video output device is transmitted from the client terminal. A request receiving unit that receives a video transmission request, a face recognition engine that recognizes a face included in the video, a mask generation unit that generates a mask to be applied to a face area detected by the face recognition engine, A mask synthesizing unit that synthesizes the image with the mask; and a video transmitting unit that transmits the image with the mask to the client terminal.

  With this configuration, as with the video output device described above, privacy can be protected by masking the face even when a person is moving in real time. In addition, since a video without a mask is not transmitted from the video output device to the client terminal, the risk of abuse of the video at the client terminal can be reduced, and privacy protection can be strengthened.

  In the video output system of the present invention, the video output device includes an authority information storage unit that stores an authority level and contents permitted at the authority level in association with each other. The information corresponding to the authority level included in the received transmission request is read from the authority information storage unit, it is determined whether or not the client terminal is permitted to display a video without a mask, and based on the result of the determination, It has a configuration for transmitting video with a mask or video without a mask to a client terminal.

  With this configuration, it is possible to change whether to output a video with a mask or to transmit a video without a mask according to the authority level of the client terminal.

  In the video output system of the present invention, the video output device includes a link information acquisition unit that acquires link information for accessing information related to a video to be transmitted in response to a transmission request received by the request reception unit, The video transmission unit has a configuration for transmitting the link information together with the video.

  With this configuration, by transmitting link information to the client terminal, the client terminal can access information related to video. Since the video output device has a configuration for acquiring and transmitting link information and does not store information about video, even if the video output device is stolen, for example, leakage of information about video such as personal information Can be prevented.

  In the video output system of the present invention, the video output device includes an authority information storage unit that stores an authority level and contents permitted at the authority level in association with each other, and the link information acquisition unit is connected to the request receiving unit. Information corresponding to the authority level included in the received transmission request is read from the authority information storage unit, and it is determined whether or not the client terminal is permitted to access the information related to the video. The link information is acquired.

  With this configuration, whether or not to transmit link information can be changed according to the authority level of the client terminal.

  In the video output system of the present invention, a network connecting the video output device and the client terminal is configured to be a LAN or the Internet.

  With this configuration, the video output device and the client terminal can be easily connected even when the client terminal is in a remote place.

  A video output system according to another aspect of the present invention is a video output system including a video output device and a client terminal that receives and displays a video from the video output device, wherein the client terminal is displayed. A coordinate instructing unit for instructing predetermined coordinates in the video; and a coordinate information transmitting unit for transmitting information indicating the coordinates instructed by the coordinate instructing unit to the video output device. A coordinate information receiving unit that receives information indicating the coordinates transmitted from the client terminal; a face region cutting unit that cuts out a face region included in the video based on the information indicating the coordinates; and the face And a video transmission unit that transmits the video of the face cut out by the region cutout unit to the client terminal.

  With this configuration, when a predetermined coordinate of the image displayed on the client terminal is designated, the instructed face cut-out image is transmitted to the client terminal. Thereby, for example, first, a low-resolution video is transmitted, and when a coordinate is instructed at the client terminal, a face video is cut out from the vicinity of the coordinate, a high-resolution face video is generated, It can be sent to the client terminal.

  In the video output system of the present invention, the coordinate designating unit is a keyboard or a pointing device.

  With this configuration, the coordinates in the video can be indicated by a simple interface.

  A collation system of the present invention is a collation system including a video output device and a collation server that collates video received from the video output device, and a face recognition engine that recognizes a face included in the video And a face area cutout unit that cuts out a face area detected by the face recognition engine, and a video transmission unit that transmits the video cut out by the face area cutout unit to the verification server. .

  With this configuration, the verification server can perform processing based on the face image without performing the process of cutting out the face image, thereby reducing the processing load. It is also possible to reduce the amount of data transmitted from the video output device to the server.

  According to the present invention, a configuration in which a face included in an image is detected, a mask applied to the detected face area is generated and combined with the image, even when a person is moving in real time, It has an excellent effect that it can protect the privacy by masking the face. Further, when the camera video is redistributed on the server side, a delay that occurs when the mask is generated and combined with the video does not occur.

  Hereinafter, a video output device and a video output system according to embodiments of the present invention will be described with reference to the drawings. In the following description, a camera is taken as an example of a video output device. The video output system outputs video shot by a camera to a client terminal connected via a network. For example, the camera is attached to the entrance of a building, takes a picture of the state near the entrance, and can monitor visitors and intruders by this image. Examples of the client terminal include a terminal for a general user in a building and a terminal for a security guard in a security room.

FIG. 1 is a diagram illustrating a configuration of a video output apparatus 10 according to the embodiment, and FIG. 2 is a diagram illustrating a configuration of a video output video output system 1 according to the embodiment.
As shown in FIG. 2, the video output system 1 according to the present embodiment includes a video output device 10, a face search server 50, and a client terminal 60. The video output device 10, the face search server 50, and the client terminal 60 are connected by a network 62. As the network 62, the Internet or a LAN can be used.

  The video output device 10 has a function of transmitting a captured video to the client terminal 60 in response to a request from the client terminal 60. The video output device 10 has a function of cutting out a face area and transmitting the cut-out video to the face search server 50 when a face is included in the shot video.

  The face search server 50 searches the database for a face image that matches the face image received from the image output device 10, and updates the visit history of the person if found. If a face that matches the received face is not found, it is registered in the database as a new visitor.

  The client terminal 60 is a terminal that displays a video shot by the video output device 10. The client terminal 60 is given a predetermined authority level, and displays according to the authority level. For example, in the case where the client terminal 60 is for general use, an authority is given to permit display of only images in which a private mask is applied to a human face. When the client terminal 60 is for a security room, the authority to permit display of video without a private mask is given.

  The configuration of the video output device 10 will be described with reference to FIG. The video output device 10 includes a lens 12 that collects light from a subject, an image sensor unit 14 that converts light transmitted through the lens 12 into an image signal, and a preprocessing unit that performs signal processing in accordance with the image sensor unit 14. 16, a YC separation processing unit 18 and an emphasis signal processing unit 20 that process a signal output from the preprocessing unit 16, and a control unit 36 that controls each component of the video output device 10. These signal processing units have the same configuration as that of a normal image processing apparatus. Although not shown in FIG. 1, the control unit 36 is connected to each component in the video output device 10.

  The video output apparatus 10 according to the present embodiment includes a face recognition engine 22, a face area cutout unit 24, a mask generation unit 26, and a mask composition unit 28.

  The face recognition engine 22 has a function of recognizing a face included in the video and a function of generating an ID and coordinates to be selected by the control unit 36. The face area extraction unit 24 has a function of generating a face image by extracting a plurality of areas of the face recognized by the face recognition engine 22 according to the designation of the ID of the control unit 36. The face image cut out by the face area cutout unit 24 is encoded by the encoding unit 30 and then output from the video signal output unit 32. The control unit 36 communicates with additional information for specifying by ID. It is transmitted to the face search server 50 via the unit 34.

  The mask generation unit 26 has a function of generating a mask to be applied to the face area recognized by the face recognition engine 22. The mask combining unit 28 has a function of combining the mask generated by the mask generating unit 26 with an image. The mask composition unit 28 refers to the setting value of the setting register 38 and switches whether to compose a mask with the video. A video with a mask in which the mask is synthesized by the mask synthesis unit 28 or a video without a mask in which the mask is not synthesized is encoded by the encoding unit 30 and then output from the video signal output unit 32, and the communication unit 34. To the client terminal 60. Note that the mask may be a mask in which the arrangement of the images is complicatedly changed.

  The control unit 36 is associated with a plurality of face area IDs of the face recognition engine 22 in cooperation with the client terminal 60 based on coordinates specified by a pointing device such as a mouse of a video displayed on the client terminal 60. it can. For example, when the coordinates double-clicked on the client terminal 60 are sent to the video output device 10, the video output device 10 causes the control unit 36 to specify the corresponding ID if there is a face cutout region close to the designated coordinates. By instructing the cutout unit 24, an image can be displayed on the client terminal 60 for the purpose of enlarging and displaying the area by designating the face.

  In addition, the video output device 10 includes a nonvolatile memory 40. The non-volatile memory 40 stores an authority table 42 indicating authority levels used in the video output system 1 and contents permitted at the authority levels.

  FIG. 3 is a diagram illustrating an example of the authority table 42. The authority table 42 shown in FIG. 3 stores five authority levels of authority level 1 to authority level 5. There are four types of authority, “link to face search server”, “enlarged face display”, “display without face mask”, and “camera image access”. “Link to face search server” indicates whether or not there is an authority to connect to face search server 50 and acquire information from face search server 50. “Face enlargement display” indicates whether or not the user has authority to enlarge and display the face image included in the image captured by the image output device 10. “Display without face mask” indicates whether or not the user has the authority to display the face portion included in the video captured by the video output device 10 without masking. “Camera video access” indicates whether or not there is an authority to access the camera video shot by the video output device 10.

  In the example shown in FIG. 3, the authority level 1 is the highest authority level, and all of “link to face search server”, “enlarged face display”, “display without face mask”, and “camera image access” can be performed. Hereinafter, as the authority level number increases, the authority decreases.

  Upon receiving the video transmission request from the client terminal 60 through the communication unit 34, the video output device 10 extracts the authority level of the client terminal 60 included in the transmission request, refers to the authority table 42, and sets the authority level. A corresponding video is generated. For example, when the authority level is “4”, since the client terminal 60 cannot perform display without a face mask, the video output device 10 generates a video with a mask. Specifically, the control unit 36 sets a setting value indicating that mask composition is performed in the setting register 38. Thereby, the mask synthesizing unit 28 synthesizes the mask with the video. The video output device 10 transmits the combined video with a mask to the client terminal 60.

  FIG. 4 is a diagram illustrating the configuration of the face search server 50. The face search server 50 manages a communication unit 52 for communicating with the video output device 10 and the client terminal 60, a face database 56 storing face images taken by the video output device 10, and the face database 56. A database management unit (hereinafter referred to as “DBMS”) 54, and an operation unit 58 for operating the DBMS 54.

  FIG. 5 is a diagram illustrating an example of data stored in the face database 56. The face database 56 stores data relating to “ID”, “face image data”, “visit history”, “name”, and “affiliation”. “ID” is an identifier for identifying a person. The face image data is image data of the face of the person specified by the ID. The face database 56 may store, as face image data, in addition to a face image photographed from the front, images photographed from several directions, up, down, left, and right. Thereby, even when the face image received from the image output device 10 is not an image taken from the front, the face can be verified. “Visit history” is information on past visit dates and destinations of the person specified by the ID. “Name” and “Affiliation” are information indicating the name and affiliation of the person specified by the ID. FIG. 5 is an example of data stored in the face database, and data other than that shown in FIG. 5, for example, information such as gender, date of birth, and contact information may be stored in the face database.

  The DBMS 54 has a function of searching the face database 56 for a face image that matches the face cut-out image received from the image output device 10. When the DBMS 54 finds a matching face image from the face database 56, the DBMS 54 stores the time when the information about the clipped image is received as the visit time.

  The operation unit 58 has a function of accessing the face database 56 through the DBMS 54, registering a new face image of the person in the face database 56, and inputting information on a visit destination.

  Next, the operation of the video output system 1 of the present embodiment will be described. The video output system 1 according to the present embodiment includes (1) an operation of registering information of a face image captured by the image output device 10 in the face search server 50, and (2) an image captured by the image output device 10 as a client. The operation of displaying on the terminal 60 is performed. In the following description, the operation (1) will be described with reference to FIG. 6, and the operation (2) will be described with reference to FIGS.

  FIG. 6 is a diagram showing an operation of registering information about the face image captured by the image output device 10 in the face search server 50. The video output device 10 captures an image using the image sensor unit 14 (S10). The imaging element unit 14 continuously captures images while performing the following processing. The face recognition engine 22 of the video output device 10 performs face recognition processing on the video obtained by shooting and determines whether or not a face has been recognized (S12). When the face is not recognized (NO in S12), the video output device 10 performs face recognition processing on the newly obtained video (S12).

  When it is recognized that a face is included in the video (YES in S12), the face area cutout unit 24 of the video output apparatus 10 cuts out a face area (S14). The video output device 10 transmits the face video clipped by the face region cutout unit 24 to the face search server 50 (S16).

  The face search server 50 receives the face image transmitted from the image output device 10 (S18), and searches the face database 56 for a face image that matches the received face image (S20). If there is a face image matching the face database 56, the time when the face image is received is stored as the visit time of the corresponding person (S22). If there is no matching face image in the face database 56, a new ID is assigned and stored in the face database 56. Note that the related information for the newly stored face image is input from the operation unit 58 of the face search server 50.

  When the storage of information in the face database 56 is completed, the face search server 50 transmits a storage completion notification to the video output device 10 (S24). The video output device 10 receives the storage completion notification (S26), and the registration of information to the face search server 50 is completed. The video output system 1 always accumulates information in the face search server 50 by performing the operation shown in FIG.

  FIG. 7 is a diagram illustrating an operation until a video is displayed on the client terminal 60 in response to a video transmission request from the client terminal 60. The client terminal 60 transmits a video transmission request to the video output device 10 (S30). Information indicating the authority level of the client terminal 60 is included in the transmission request.

  The video output device 10 receives the transmission request transmitted from the client terminal 60 (S32), and extracts the authority level included in the received transmission request (S34). Based on the authority level, the video output apparatus 10 determines whether the client terminal 60 has the authority to link to the face search server 50 (S36). If the client terminal 60 does not have the right to link to the face search server 50 (NO in S36), the process proceeds to step S46 of video generation without performing data transmission / reception with the face search server 50 described below. To do.

  If it is determined that the client terminal 60 has the right to link to the face search server 50 (YES in S36), the video output device 10 transmits a link information acquisition request to the face search server 50 (S38). The link information acquisition request includes a cut-out video of the face shown in the video currently being shot.

  When receiving the link information acquisition request (S40), the face search server 50 generates link information to information related to the face image included in the received acquisition request. Specifically, the face search server identifies a person corresponding to the face image included in the acquisition request, and generates link information indicating the storage location of the related information of the person. The face search server 50 transmits the generated link information to the video output device 10 (S42), and the video output device 10 receives the link information transmitted from the face search server 50 (S44).

  Next, the video output device 10 generates a video corresponding to the authority level (S46). Here, a description will be given with reference to the authority table 42 shown in FIG. For example, when the authority level is “4”, access to the camera video is permitted, but display without a face mask is prohibited, so the video output device 10 generates a video with a mask. Specifically, by setting a setting value with a mask in the setting register 38, the mask composition unit 28 synthesizes the mask with the image and generates an image with a mask. For example, when the authority level is “2”, display without a mask and face enlargement display are permitted, so that an image in which a face is enlarged is added to an image without combining a mask. For example, when the authority level is “1”, since the link to the face search server 50 is permitted, the link information acquired from the face search server 50 is embedded in the video. In this way, the video output device 10 generates a video corresponding to the authority level of the client terminal 60 (S46).

  Next, the video output device 10 transmits the generated video to the client terminal 60 (S48). The client terminal 60 receives the video transmitted from the video output device 10 (S50), and displays the received video (S52).

  FIG. 8 is a diagram illustrating an example of an image displayed on the client terminal 60 at the authority level 4. As shown in FIG. 8, an image including a person is displayed on the screen. A person's face is covered with a mask so that no one can be identified.

  FIG. 9 is a diagram illustrating an example of an image displayed on the client terminal 60 at the authority level 1. As shown in FIG. 9, an image including a person is displayed on the screen, but no mask is put on. The face is enlarged and displayed in the sub-window 72 at the lower right of the screen. In addition, link information 74 is displayed on the lower side of the screen. By clicking the link information 74, information related to the person displayed on the screen can be displayed. Further, the sub window 72 can be switched by clicking and specifying the vicinity of the face in the screen with the mouse pointer 76. Note that the ID display for each person in FIG. 9 may be combined on either the video output device 10 side or the client terminal 60 side.

  FIG. 10 is a diagram illustrating an operation until displaying the related information of the video on the client terminal 60 in response to the click of the link information.

  The client terminal 60 displays a video with link information as shown in FIG. 9 (S52). The operation until the video with link information is displayed is as described with reference to FIG. When the user clicks the link, the client terminal 60 transmits a connection request to the address specified for the link (S54). When receiving the connection request from the client terminal 60 (S56), the face search server 50 determines whether or not the client terminal 60 that has transmitted the connection request has been authenticated (S58). If it has been authenticated (YES in S58), the process proceeds to step S74 in which related information is transmitted.

  If not authenticated (NO in S58), the face search server 50 transmits an NG response to the connection request (S60). Upon receiving an NG response from the face search server 50 (S62), the client terminal 60 displays a user ID and password input screen (S64). The client terminal 60 receives input of the user ID and password (S66), and transmits the input user ID and password to the face search server 50 (S68).

  The face search server 50 receives the user ID and password transmitted from the client terminal 60 (S70), and performs authentication processing of the client terminal 60 using the received user ID and password (S72). After the client terminal 60 is authenticated, the face search server 50 transmits the related information stored in the location designated by the link to the client terminal 60 (S74). The client terminal 60 receives the related information (S76), and displays the received related information (S78).

FIG. 11 is a diagram illustrating an example of related information displayed on the screen of the client terminal 60. As shown in FIG. 11, the name, company name, department, and past visit history are displayed on the screen as related information of the face image. FIG. 11 shows an example of a screen displaying related information, and the related information may include information other than that shown in FIG.
The video output system 1 and the video output device 10 according to the present embodiment have been described above.

  The video output apparatus 10 according to the present embodiment detects a face included in the video by the face recognition engine 22, generates a mask to be applied to the detected face area, and synthesizes it with the video, so that a person can perform real-time processing. Even if you ’re on the move, you can wear a mask to protect your privacy.

  In addition, when receiving a video transmission request from the client terminal 60, the video output device 10 according to the present embodiment transmits a video with a mask or a video without a mask according to the authority level included in the transmission request. . The video output device 10 generates and transmits a video with a mask in the device, and does not transmit a video without a mask to an unauthorized client terminal 60. Therefore, the video is abused by a third party. Risk can be reduced and privacy protection can be strengthened.

  In addition, since the video output device 10 of the present embodiment cuts out a face video from the video and transmits it to the face search server 50, the face search server 50 can omit the process of cutting out the face from the video. The load of verification processing can be reduced.

  In the video output system 1 according to the present embodiment, link information is transmitted from the video output device 10 to the client terminal 60, and the face search server 50 is accessed from the authenticated client terminal 60 using the link information. For the first time, video related information is transmitted to the client terminal 60. Therefore, even if the link information is wiretapped, if the user does not have the authority to access the face search server, the related information will not be leaked, and security can be improved.

  Although the video output system and the video output method of the present invention have been described above, the present invention is not limited to the above-described embodiments.

  In the embodiment described above, the face recognition engine 22 recognizes a plurality of faces and generates IDs, and recognizes the number of persons based on the number of IDs. ) When the above faces are included, the masking may be omitted. When a face with a predetermined threshold or more is included in the video, it is less necessary to protect the privacy than when a single face image is included. Is possible.

  Further, when the face image included in the image is smaller than a predetermined size, the masking may be omitted. Here, the predetermined size is such a size that a person cannot be identified from the face image.

  In the above embodiment, a camera having an imaging function has been described as an example of a video output device. However, the present invention can also be applied to a video output device other than a camera. For example, the present invention can be applied to an encoder.

  In the above embodiment, the authority table 42 storing authority levels 1 to 5 has been described as an example. However, the authority table 42 may store various authority levels.

  FIG. 12 is a diagram illustrating another example of the authority level table. In the example illustrated in FIG. 12, information indicating whether or not the authority of “setting”, “access to face detection history”, and “camera turntable / zoom / focus control” is added to the example illustrated in FIG. 3. The authority level is also set more finely from level 1 to level 8. “Setting” indicates whether or not there is an authority to change the setting of the video output device. “Access to face detection history” indicates whether or not there is an authority to access information of the detection history of the face search server 50. “Camera turntable / zoom / focus control” indicates whether or not the user has authority to control the camera turntable of the video output device, zoom control, and focus control.

  In the above-described embodiment, the mask composition unit 28 may be configured to set a composition ratio when compositing a mask with an image. The setting of the composition ratio may be performed by an input unit (not shown) provided in the video output device 10 or may be performed from the client terminal 60 having an authority level for changing the setting of the video output device 10.

  In the embodiment, an example is shown in which one of a plurality of face images is selected and sent to the face search server 50. However, a plurality of face images in the detected image are sequentially sent together with an ID. be able to. In any case, based on the ID generated by the face recognition engine 22 and the image size, by comparing with a preset size so as not to send an image smaller than or larger than the image size required by the face search server 50 The control unit 36 performs transmission determination.

  As described above, the present invention can protect privacy by masking even when a person is moving in real time, and video such as a camera that masks a part of an image for privacy protection. Useful as an output device.

The figure which shows the structure of the video output apparatus of embodiment The figure which shows the structure of the video output system of embodiment The figure which shows the example of the data memorize | stored in the authority table The figure which shows the structure of a face search server The figure which shows the example of the data memorize | stored in the face database The figure which shows the operation | movement which registers information into a face search server based on the image | video of the face image | photographed with the video output device. The figure which shows operation | movement until it displays an image | video on a client terminal according to the transmission request of the image | video from a client terminal. The figure which shows the example of the image | video displayed on a client terminal The figure which shows the example of the image | video displayed on a client terminal The figure which shows the operation | movement which displays the relevant information of an image | video on a client terminal The figure which shows the example of the related information displayed on the screen of the client terminal Figure showing another example of authority level table

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Image | video output system 10 Image | video output device 12 Lens 14 Image pick-up element part 16 Pre-processing part 18 YC separation processing part 20 Enhancement signal processing part 22 Face recognition engine 24 Face area extraction part 26 Mask generation part 28 Mask composition part 30 Encoding part 32 Video signal processing unit 34 Communication unit 36 Control unit 38 Setting register 40 Non-volatile memory 42 Authority table 50 Face search server 52 Communication unit 54 DBMS
56 face database 58 operation unit 60 client terminal 62 network 70 mask 72 subwindow 74 link information 76 mouse pointer

Claims (13)

A face recognition engine that recognizes a face included in the video;
A mask generation unit for generating a mask to be applied to the face area detected by the face recognition engine;
A mask synthesizer for synthesizing the image and the mask;
A video output unit that outputs the synthesized video with mask;
A video output device. An output request receiving unit for receiving a video output request;
According to the authority level included in the output request, a switching unit that switches whether to output video with a mask or video without a mask,
The video output device according to claim 1, further comprising:   3. The video according to claim 2, wherein the switching unit switches to output a video without a mask when the number of faces appearing in the video is larger than a predetermined threshold or when the face area is smaller than the predetermined threshold. Output device. A composition ratio setting unit that sets the composition ratio of the video signal and the mask is provided.
The video output device according to claim 1, wherein the mask composition unit synthesizes a mask with an image based on the composition ratio set by the composition ratio setting unit. A face area cutout unit that cuts out a face area detected by the face recognition engine;
The video output device according to claim 1, wherein the video output unit transmits the clipped video clipped by the face region cutout unit to a server that performs processing based on a face video. A video output system comprising: a video output device; and a client terminal that receives and displays video from the video output device,
The video output device
A request receiving unit for receiving a transmission request for video transmitted from the client terminal;
A face recognition engine that recognizes a face included in the video;
A mask generation unit for generating a mask to be applied to the face area detected by the face recognition engine;
A mask synthesizer for synthesizing the image and the mask;
A video transmission unit for transmitting a video with a mask to the client terminal;
Video output system with The video output device
An authority information storage unit storing the authority level and the content permitted at the authority level in association with each other;
The video transmission unit reads information corresponding to the authority level included in the transmission request received by the request reception unit from the authority information storage unit, and whether or not the client terminal is permitted to display a video without a mask. The video output system according to claim 6, wherein a video with a mask or a video without a mask is transmitted to the client terminal based on a result of the determination. The video output device
A link information acquisition unit for acquiring link information for accessing information related to a video to be transmitted in response to a transmission request received by the request reception unit;
The video output system according to claim 6, wherein the video transmission unit transmits the link information together with the video. The video output device
An authority information storage unit storing the authority level and the content permitted at the authority level in association with each other;
The link information acquisition unit reads information corresponding to the authority level included in the transmission request received by the request reception unit from the authority information storage unit, and whether or not the client terminal is permitted to access information related to the video. The video output system according to claim 8, wherein the link information is acquired when it is determined that the link information is permitted. A video output system comprising: a video output device; and a client terminal that receives and displays video from the video output device,
The client terminal is
A coordinate designating unit for designating predetermined coordinates in the displayed video;
A coordinate information transmission unit that transmits information indicating the coordinates instructed by the coordinate instruction unit to the video output device,
The video output device
A coordinate information receiving unit for receiving information indicating the coordinates transmitted from the client terminal;
A face area cutout unit that cuts out a face area included in the video based on the information indicating the coordinates;
A video transmission unit that transmits a video of the face cut out by the face region cut-out unit to the client terminal;
Video output system with   The video output system according to claim 10, wherein the coordinate instruction unit is a keyboard or a pointing device.   The video output system according to claim 6, wherein a network connecting the video output device and the client terminal is a LAN or the Internet. A collation system comprising: a video output device; and a collation server that collates video received from the video output device,
A face recognition engine that recognizes a face included in the video;
A face area cutout unit that cuts out a face area detected by the face recognition engine;
A video transmission unit that transmits the video clipped by the face area cutout unit to the verification server;
A collation system with

Images