Multimedia focalization
AssigneeOpenTV, Inc.
InventorEunsook An
Life of this patent
Estimating the term…
Abstract
Example implementations are directed to methods and systems for individualized multimedia navigation and control including receiving metadata for a piece of digital content, where the metadata comprises a primary image and text that is used to describes the digital content; analyzing the primary image to detect one or more objects; selecting one or more secondary images corresponding to each detected object; and generating a data structure for the digital content comprising the one or more secondary images, where the digital content is described by a preferred secondary image.
Claims18
A method comprising:
- receiving metadata for a piece of digital content, wherein the metadata comprises at least a primary image that is a representation of the piece of digital content;
- analyzing the primary image using at least facial recognition to detect at least a first face and a second face;
- determining that a first size of the first face in the primary image is larger than a second size of the second face in the primary image;
- selecting a first secondary image in the primary image corresponding to the first face;
- selecting a second secondary image in the primary image corresponding to the second face;
- and
- identifying the first secondary image as a preferred secondary image based at least on the first size of the first face being larger than the second size of the second face.
A system comprising:
- a memory;
- one or more processors coupled to the memory comprising instructions that when executed cause the one or more processors to perform operations to:
- receive a request to describe a piece of digital content;
- receive a set of user information that includes a user preference;
- receive metadata for the piece of digital content, wherein the metadata comprises an image that represents the piece of digital content;
- analyze the image using at least facial recognition to detect at least a first face and a second face;
- determine that a first size of the first face in the image is larger than a second size of the second face in the image;
- select a first secondary image in the image corresponding to the first face;
- select a second secondary image in the image corresponding to the second face;
- determine position information corresponding to positions of the first secondary image and the second secondary image in the image;
- and
- responsive to a user request and using at least the position information, cause presentation of the first secondary image as a preferred secondary image based at least on the first size of the first face being larger than the second size of the second face.
A non-transitory computer readable medium, comprising instructions that when executed by one or more processors, cause the one or more processors to perform operations to:
- receive metadata for a piece of digital content, wherein the metadata comprises at least a primary image that is used to describe the piece of digital content;
- analyze the primary image using at least facial recognition to detect at least a first face and a second face;
- determine that a first size of the first face in the primary image is larger than a second size of the second face in the primary image;
- select a first secondary image in the primary image corresponding to the first face;
- select a second secondary image in the primary image corresponding to the second face;
- and, wherein, in response to a user request,
- identify the first secondary image as a preferred secondary image based at least on the first size of the first face being larger than the second size of the second face.
Dependencies are inferred from the claim text.