Methods and systems for scoreboard text region detection

A computing system comprising:

• a processing unit;
• non-transitory data storage;
• and
• program instructions stored in the non-transitory data storage and executable by the processing unit to carry out operations for automatically detecting, in a sequence of video frames, a video frame region that depicts a scoreboard, the operations comprising:
• receiving a time sequence of digital video frames that depict media content, wherein the computing system comprises a processing unit;
• engaging in digital image processing of the received 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 an action based on the generated data.

A non-transitory computer readable medium having stored thereon instructions executable by a processing unit to cause a computing system to perform operations 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 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.