61 patents in CPC class H04N
Embodiments disclosed herein generally relate to a method and system of generating text input via facial recognition. A computing system receives a video stream of a user operating an application on a client device. The video stream includes a time series of images of the user. The computing system parses the video stream to identify one or more visual cues of the user. The computing system identifies a current page of the application. The computing system maps the identified on or more visual cues to an operation available on the current page of the application. The computing system executes the mapped operation.
A display control system for a multi-layer display system including at least one multi-layer display unit. A multi-layer display unit includes multiple stacked or overlapped display layers each adapted to render display elements thereon for viewing through the uppermost display layer. The level of difficulty for a user to view an overlapped image differs depending on the colour, brightness or type of images (for example text-on-text) being displayed and also the layer in which the image is being displayed and whether the image is currently active. At least any overlapping portion of display elements from different display layers are adjusted (automatically or by a user) in order to improve the viewing experience for a viewer. Types of adjustment possible include moving the images within their display layer or to an alternative display layer or altering their visual properties (such as colour, brightness, contrast, etc.).
Disclosed are various embodiments for identifying and recommending events of interest in real-time media content. Individual ones of multiple media content streams are analyzed to determine whether events of interest are occurring in real-time. It is then determined that an event of interest is occurring in real-time in a particular media content stream of the multiple media content streams. A user interface is generated that recommends the particular media content stream based at least in part on the event of interest.