Recording and playback system based on multimedia content fingerprints
View Patent ↗A method for recording media content based on media content fingerprints is described. A media device records content received in a content stream from a scheduled start time of a media content to a scheduled end time of the media content to create a content recording. The media device derives one or more fingerprints from the content recording. A fingerprint database is queried with the one or more fingerprints to determine that a first portion of the content recording comprises an advertisement and a second portion of the content recording comprises the media content. In response to a request to play the content recording, starting playback of the content recording at the beginning of the second portion of the content recording.
1. A method comprising:
responsive to a request to record specific content, recording, by a media device, content received in a content stream from at least a scheduled start time of a media content to at least a scheduled end time of the media content to create a content recording;
deriving, by the media device, one or more first fingerprints from a first portion of the content recording and one or more second fingerprints from a second portion of the content recording;
based on the one or more second fingerprints, recognizing one or more faces in the second portion of the content recording, the one or more faces associated with the specific content;
based on the one or more first fingerprints, determining that the one or more faces associated with the specific content are not recognized in the first portion of the content recording;
in response to a request to play the content recording, based on having recognized the one or more faces in the second portion but not the first portion, starting playback of the content recording at the beginning of the second portion of the content recording, skipping over the first portion.
2. The method as recited in claim 1 , wherein the scheduled start time is based on information associated with an electronic programming guide (EPG).
3. The method as recited in claim 1 , wherein the specific content is a television program for which the media device was requested to create the content recording.
4. The method as recited in claim 1 , wherein the media device derives the one or more first fingerprints and one or more second fingerprints concurrently with recording the content received in the content stream.
5. The method as recited in claim 1 , further comprising deleting the first portion from the content recording based on determining that the one or more faces are not recognized in the first portion of the content recording, while continuing to store the second portion of the content recording.
6. One or more non-transitory computer-readable storage media, storing instructions, which when executed by one or more processors cause performance of:
responsive to a request to record specific content, recording, by a media device, content received in a content stream from at least a scheduled start time of a media content to at least a scheduled end time of the media content to create a content recording;
deriving, by the media device, one or more first fingerprints from a first portion of the content recording and one or more second fingerprints from a second portion of the content recording;
based on the one or more second fingerprints, recognizing one or more faces in the second portion of the content recording, the one or more faces associated with the specific content;
based on the one or more first fingerprints, determining that the one or more faces associated with the specific content are not recognized in the first portion of the content recording;
in response to a request to play the content recording, based on having recognized the one or more faces in the second portion but not the first portion, starting playback of the content recording at the beginning of the second portion of the content recording, skipping over the first portion.
7. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the scheduled start time is based on information associated with an electronic programming guide (EPG).
8. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the specific content is a television program for which the media device was requested to create the content recording.
9. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the media device derives the one or more first fingerprints and one or more second fingerprints concurrently with recording the content received in the content stream.
10. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the instructions, when executed by the one or more processors, further cause deleting the first portion from the content recording based on determining that the one or more faces are not recognized in the first portion of the content recording, while continuing to store the second portion of the content recording.
11. An apparatus comprising:
one or more processors;
a memory storing instructions, which when executed by the one or more processors, cause the apparatus to:
responsive to a request to record specific content, record, by a media device, content received in a content stream from at least a scheduled start time of a media content to at least a scheduled end time of the media content to create a content recording;
derive, by the media device, one or more first fingerprints from a first portion of the content recording and one or more second fingerprints from a second portion of the content recording;
based on the one or more second fingerprints, recognize one or more faces in the second portion of the content recording, the one or more faces associated with the specific content;
based on the one or more first fingerprints, determine that the one or more faces associated with the specific content are not recognized in the first portion of the content recording;
in response to a request to play the content recording, based on having recognized the one or more faces in the second portion but not the first portion, start playback of the content recording at the beginning of the second portion of the content recording, skipping over the first portion.
12. The apparatus of claim 11 , wherein the scheduled start time is based on information associated with an electronic programming guide (EPG).
13. The apparatus of claim 11 , wherein the specific content is a television program for which the media device was requested to create the content recording.
14. The apparatus of claim 11 , wherein the media device derives the one or more first fingerprints and one or more second fingerprints concurrently with recording the content received in the content stream.
15. The apparatus of claim 11 , wherein execution of the instructions further causes the apparatus to delete the first portion from the content recording based on determining that the one or more faces are not recognized in the first portion of the content recording, while continuing to store the second portion of the content recording.
16. The method of claim 1 , further comprising identifying the first portion and the second portion using searching for any of a plurality of faces associated with the specific content in time windows within the content recording until at least one of the plurality of faces is detected.
17. The method of claim 1 , wherein the one or more faces correspond to actors listed for the specific content, the specific content being a television show, the first portion corresponding to other content in which the actors do not appear, the first portion including at least one of another television show or an advertisement.
18. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the instructions, when executed by the one or more processors, further cause identifying the first portion and the second portion using searching for any of a plurality of faces associated with the specific content in time windows within the content recording until at least one of the plurality of faces is detected.
19. The one or more non-transitory computer-readable storage media as recited in claim 6 , wherein the one or more faces correspond to actors listed for the specific content, the specific content being a television show, the first portion corresponding to other content in which the actors do not appear, the first portion including at least one of another television show or an advertisement.
20. The apparatus of claim 11 , wherein the memory further stores instructions, which when executed by the one or more processors, cause the apparatus to identify the first portion and the second portion using searching for any of a plurality of faces associated with the specific content in time windows within the content recording until at least one of the plurality of faces is detected.