Creating a narrative description of media content and applications thereof
AssigneeGoogle Inc.
InventorHyduke Noshadi
Life of this patent
Estimating the term…
Abstract
This invention relates to creating a narrative description of media content. In an embodiment, a computer-implemented method describes content of a group of images. The group of images includes a first image and a second image. A first object in the first image is recognized to determine a first content data. A second object in the second image is recognized to determine a second content data. Finally, a narrative description of the group of images is determined according to a parameterized template and the first and second content data.
Claims22
A method for describing content of a group of images, the group of images including a first image and a second image, comprising:
- (a) recognizing a first object in the first image to determine a first content data that identifies the first object;
- (b) recognizing a second object in the second image to determine a second content data that identifies the second object;
- and
- (c) generating, by a computer, a narrative description of the group of images according to a parameterized template that specifies how to construct the narrative description from the first and second content data,
- wherein each of the steps is performed on the computer.
A system for describing media content, comprising:
- a media database including a memory that stores a first image and a second image belonging to a group of images;
- an object recognition module that recognizes a first object in the first image to determine a first content data that identifies the first object and recognizes a second object in the second image to determine a second content data that identifies the second object;
- and
- a narrative compiler module that generates, by a computer, a narrative description of the group of images according to a parameterized template that specifies how to construct the narrative description from the first and second content data.
Dependencies are inferred from the claim text.