The present invention relates generally to using images of viewers to establish an emotion ranking for a video being viewed by the imaged viewers.
Television displays have been a source of entertainment for friends and families for decades, but the viewers must be together in the same room to share laughter, words, or facial emotions without the use of supplemental equipment such as phones or cameras. Some computers have implemented cameras into the housing or chassis that the user's image can be captured on and streamed over the Internet and viewed by a friend or family member, but this is not a common feature on TVs. As understood herein, it would be desirable to enable friends or family members who are not viewing the same TV to share facial expressions with one another via a network such as the Internet.
As understood herein, facial recognition software is able to detect emotion of a person based on an image taken of them. Present principles recognize that the emotion information can be converted into animated images, or “emoticons,” or descriptive words that correspond to the detected emotion to, e.g., allow a TV viewer's image to be converted into an emoticon and sent to a friend's TV display.
Accordingly, a system includes a viewer video display and a processor coupled to the viewer video display. The processor can also communicate with a camera and can execute logic on a computer readable storage medium to generate an image of the viewer using the camera and to upload the image to a ranking mechanism. The processor can receive back from the ranking engine the original image of the viewer and an emotion rank pertaining to a video presented on the display and can overlay the image of the viewer and/or emotion rank onto the video. The emotion rank can be an emoticon emulating the viewer's face or descriptive words that correspond to the detected emotion.
The processor can present a user interface (UI) on the display, thereby enabling a viewer to select items, i.e. image of viewer or emotion rank, that can be used for further action. The processor's presentation of a UI can enable a viewer to also select to have an image of his or her face and/or emotion rank uploaded to a viewer-defined social networking site on the Internet. The presentation of the UI can thirdly enable a viewer to select to have the emotion rank received from the ranking engine or the original image of the viewer's face presented on the display.
The UI presented by the processor on the display can enable a viewer to vote on images of viewer faces downloaded from the ranking engine and presented on the display. The images of viewer faces may pertain to the video presented on the display. The UI can enable a viewer to vote on a “best” face at least in part by clicking on one of the images of viewer faces downloaded from the ranking engine and presented on the display. The UI further can enable a viewer to vote on a face based on the face presenting a particular emotion listed on the UI.
In another aspect, a method includes generating an image of a viewer of a TV using a camera associated with the TV, providing the image to a ranking mechanism, and receiving back from the ranking engine the image and an emotion rank pertaining to a video presented on the display. The method also includes overlaying the original image and/or emotion rank onto the video. The emotion rank is an emoticon emulating the viewer's face and/or descriptive words that correspond to the detected emotion.
In another aspect, an apparatus has a viewer video display, a processor coupled to the viewer video display, and a camera communicating with the processor. The processor executes logic on a computer readable storage medium to, responsive to a viewer selection to capture a picture of his or her face, causing an image of the viewer to be captured. The processor also provides the image to a ranking engine and receives from the ranking engine an emotion rank. The processor, responsive to user command, overlays the image and/or the emotion rank onto a video being played on the display to enable a viewer to watch the video being played and view the image and/or emotion rank simultaneously.
Example implementation details of present principles are set forth in the description below, in which like numerals refer to like parts, and in which:
Referring initially to
Components inside the chassis 14 can include a TV tuner 16 (when the display device is implemented by a TV), a computer readable storage medium 18 such as disk-based or solid state storage, and a processor 20. A display/circuitry driver(s) 22 can be included to receive signals from the processor 20 to drive the image on the video display 12 and an audio circuitry 24 can be included to receive signals from the processor 20 to output audio on the speakers 26.
A microphone 28, a camera 30, and an input device 32 can be included and communicate data external to the chassis 14 collected at the user's discretion to the processor 20. In some implementations, the microphone 28 and camera 30 can be built into the display chassis 14. In other embodiments, the microphone 28 and camera 30 are provided separately from the chassis 14 and communicate with the processor 20 over a wired path such as a USB path or a wireless path such as a Bluetooth path. The input device 32 may be a keyboard, keypad, mouse, voice recognition device, etc. but in the embodiment shown is a TV remote control and also communicate with the processor 20 over a wired path or a wireless path. In other implementations, multiple input devices 32 can be included.
A network interface 34 may be a wired or wireless modem and communicates with a friend's video display 36 over a wide area network (WAN) 38 such as the Internet. Alternatively, the network interface 34 may be a cable interface and can communicate with a cable head end and thence to the display devices of other users, such as the friend's video display 36. In both cases, multiple friend displays may be used in accordance with the principles below. A computer server on the Internet with one or more processors and one or more computer readable storage media may host the ranking engine discussed below.
Moving in reference to
A selector element 40 allows the user to select one or plural items from a list on the UI. The viewer selects an item by highlighting or clicking on a box adjacent to an item, i.e. the viewer image checkbox 42. The items available for selection are the original image captured by the camera 30 and the emotion rank in the form of both an emoticon and descriptive words. Once the item(s) is selected, the viewer can then choose what to do with the items by clicking on successive selector elements.
A selector element 44 allows the user to send the image of his or her face and/or the emotion rank to a social networking website on the Internet, whose address is predetermined by the viewer. Alternatively, the viewer may present the image of his or her face and/or emotional rank of the current show on the display 12 by choosing selector element 46. By choosing selector element 46, the processor 20 would resume showing of the video previously playing and overlay the image of the viewer and/or the emotion rank onto that video.
A selector element 48 allows the user to vote on the “best” face pertaining to the video currently being played. The faces that the viewer can vote on are faces downloaded from the ranking engine and presented on the display 12. The voting occurs at least in part by clicking on one of the images of viewer faces downloaded from the ranking engine and presented on the display 12. The UI further enables the viewer to vote on a face based on the face presenting a particular emotion listed on the UI.
Now referring to the screen shot of
Moving in reference to the screen shot of
The flow chart of
The viewer may direct the processor 20, by using the UI displayed by the processor 20 in response to image capture, to overlay the image of his or her face or the emotion rank onto the video currently being played on the display 12 at block 56. This would enable the viewer to watch the video being played and view the image and/or emotion rank simultaneously.
Moving to block 58, the viewer may make an alternate selection on the UI to direct the processor 20 to download thumbnails 52 of other viewer's faces from the Internet. Once downloaded, the processor 20 would display the thumbnails 52 so that the viewer may vote on them. The processor 20 receives the viewer's vote via input device 32 at block 60 in terms of categories, e.g., “best,” “funniest,” etc.
Results of the vote and/or ranking may be displayed on an Internet website, on other viewer's displays, e.g., on peer displays, etc.