Apparatus and methods for visual summarization of videos
AssigneeVideo Notebook Inc.
InventorsMichael Lanza, Eran Steinberg
Life of this patent
Estimating the term…
Abstract
generally comprises obtaining one or more images from the video as the video is played, locating a presence of a shape or text from each of the one or more images, determining whether the shape or text corresponds to a prior shape or text from a prior base image, determining whether each of the one or more images comprises a corresponding slide, presenting the one or more images as one or more slides upon an interface displayed to a user, providing a timestamp upon each of the one or more slides, whereby selection of the timestamp by the user plays the video at a location which correlates to the timestamp within the video, and presenting the one or more slides including the timestamp to the user.
Claims36
A method for visually summarizing a video, comprising:
- obtaining one or more images from the video;
- locating a presence of a shape or text from each of the one or more images;
- determining whether the shape or text corresponds to a prior shape or text from a prior base image;
- determining whether each of the one or more images comprises a corresponding slide;
- presenting the one or more images as one or more slides upon an interface displayed to a user;
- providing a timestamp upon each of the one or more slides, whereby selection of the timestamp by the user plays the video at a location which correlates to the timestamp within the video;
- and
- presenting the one or more slides including the timestamp to the user.
A method of presenting a video notebook, comprising:
- presenting one or more video summaries upon a display to a user as a corresponding thumbnail image, wherein each of the one or more video summaries provide one or more searchable keywords corresponding to a content of the video summary, and
- wherein creation of each of the one or more video summaries comprises:
- obtaining one or more images from a video;
- locating a presence of a shape or text from each of the one or more images;
- determining whether the shape or text corresponds to a prior shape or text from a prior base image;
- determining whether each of the one or more images comprises a corresponding slide;
- presenting the one or more images as one or more slides upon an interface displayed to the user;
- providing a timestamp upon each of the one or more slides, whereby selection of the timestamp by the user plays the video at a location which correlates to the timestamp within the video;
- and
- presenting the one or more slides including the timestamp to the user.
Dependencies are inferred from the claim text.