Back to results
US 8,559,720 B2Granted
Using a video processing and text extraction method to identify video segments of interest
AssigneeThomson Licensing
InventorsRuiduo Yang, Ying Luo, Claire-Hélène Demarty, Lionel Oisel
Life of this patent
Estimating the term…
Abstract
A video processing technique is performed on a video media service to identify video segments of interest. The video processing technique (200) is supplemented by a text extraction technique (245, 255, 270), as well. The resulting video segments of interest (289) can be stored as to produce a version of the media service which is shorter in time length than the original video media service.
Claims7
A method for classifying segments in a video media service comprising the steps of:
- performing an image analysis process on the video media service as to develop at least two video segments from said video media service;
- performing a text extraction process on metadata associated with the resulting at least two video segments to identify keywords in said metadata;
- automatically identifying video segments of interest from said text extraction process and said image analysis process;
- and
- automatically creating a digest version of a video media service by automatically deleting a video segment selected from said at least two video segments based on said identifying step that do not match at least one keyword criteria and at least one image shot criteria.
2 more elements
Dependencies are inferred from the claim text.