US 12,148,231 B2
Systems and methods for extracting in-video moving text in live video streams
Vamsi Kavuri, Glen Allen, VA (US); Jignesh Rangwala, Glen Allen, VA (US); Santhi Sridharan, Glen Allen, VA (US); Muthukumaran Vembuli, Glen Allen, VA (US); Lee Adcock, Midlothian, VA (US); Mehulkumar Jayantilal Garnara, Glen Allen, VA (US); and Srikanth Reddy Sheshaiahgari, Richmond, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 8, 2022, as Appl. No. 17/818,293.
Prior Publication US 2024/0046669 A1, Feb. 8, 2024
Int. Cl. G06V 20/62 (2022.01); G06V 20/40 (2022.01); G06V 30/14 (2022.01); G06V 40/20 (2022.01); G10L 15/08 (2006.01); H04N 5/272 (2006.01)
CPC G06V 20/635 (2022.01) [G06V 20/41 (2022.01); G06V 30/1448 (2022.01); G06V 30/1456 (2022.01); G06V 40/20 (2022.01); G10L 15/08 (2013.01); H04N 5/272 (2013.01)] 20 Claims
OG exemplary drawing
 
2. A method comprising:
processing a video file associated with a video communication session to detect moving text to which a first user is referring in the video file;
determining, based on the detection of the moving text, location information associated with the moving text, the location information indicating spatial locations of the moving text; and
presenting, based on the location information, a graphical text location indicator simultaneously on both a first portion of a user interface of a user device and a second portion of the user interface such that:
(i) a first instance of the graphical text location indicator is presented proximate the moving text over the video file in the first portion of the user interface; and
(ii) a second instance of the graphical text location indicator is presented proximate selectable text that corresponds to the moving text in the second portion of the user interface.