US 12,217,506 B2
Methods and systems for scoreboard text region detection
Jeffrey Scott, Oakland, CA (US); Markus Kurt Peter Cremer, Orinda, CA (US); Nishit Umesh Parekh, Woodland Hills, CA (US); and Dewey Ho Lee, Berkeley, CA (US)
Assigned to Gracenote, Inc., New York, NY (US)
Filed by Gracenote, Inc., Emeryville, CA (US)
Filed on May 11, 2023, as Appl. No. 18/196,310.
Application 18/196,310 is a continuation of application No. 17/301,539, filed on Apr. 6, 2021, granted, now 11,798,279.
Application 17/301,539 is a continuation of application No. 16/257,339, filed on Jan. 25, 2019, granted, now 10,997,424, issued on May 4, 2021.
Prior Publication US 2023/0281989 A1, Sep. 7, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06V 20/40 (2022.01); G06T 7/13 (2017.01); G06V 20/62 (2022.01); H04N 21/2187 (2011.01)
CPC G06V 20/42 (2022.01) [G06T 7/13 (2017.01); G06V 20/62 (2022.01); H04N 21/2187 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a computing system, a time sequence of digital video frames that depict media content, wherein the computing system comprises a processing unit;
engaging, by the computing system, in digital image processing of the received time sequence of digital video frames to automatically generate data, wherein the digital image processing comprises:
(i) identifying a first frame region of the digital video frames based on the first frame region depicting a scoreboard,
(ii) executing a first machine-driven pattern recognition procedure that includes analyzing the identified first frame region to detect, within the identified first frame region, one or more second frame regions based on the second frame regions depicting text of the scoreboard,
(iii) in response to detecting the second frame regions, executing a second machine-driven pattern recognition procedure to recognize the text in at least one of the one or more second frame regions, and
(iv) based at least on the recognizing of the text, generating the data; and
in response to completing the digital image processing, carrying out, by the computing system, an action based on the generated data.