US 11,863,806 B2
Systems and methods for correcting errors in caption text
Ajay Kumar Gupta, Andover, MA (US); and Abhijit Satchidanand Savarkar, Andover, MA (US)
Assigned to Rovi Guides, Inc., San Jose, CA (US)
Filed by Rovi Guides, Inc., San Jose, CA (US)
Filed on Oct. 5, 2020, as Appl. No. 17/063,373.
Application 17/063,373 is a continuation of application No. 16/067,036, granted, now 10,834,439, previously published as PCT/US2016/054689, filed on Sep. 30, 2016.
Prior Publication US 2021/0037274 A1, Feb. 4, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/234 (2011.01); H04N 21/488 (2011.01); H04N 21/2343 (2011.01); G06F 40/40 (2020.01); G06F 40/166 (2020.01); G06F 40/232 (2020.01)
CPC H04N 21/23424 (2013.01) [G06F 40/166 (2020.01); G06F 40/232 (2020.01); G06F 40/40 (2020.01); H04N 21/234336 (2013.01); H04N 21/4884 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for correcting an erroneous term in on-screen caption text of a media asset, comprising:
identifying an erroneous term in a text segment of the on-screen caption text;
extracting a video frame from a video stream of the media asset corresponding to the text segment;
identifying a non-textual visual object in the video frame associated with the erroneous term, wherein the non-textual visual object comprises an image of a person;
analyzing the non-textual visual object in the video frame, using image recognition, to determine a contextual term associated with the erroneous term, wherein the contextual term comprises the identity of the person;
accessing a data structure to identify a candidate correction for the erroneous term based on the contextual term and a portion of the text segment; and
replacing the erroneous term in the text segment of the closed captioning text with the candidate correction.