Content recognition employing fingerprinting at different resolutions

Patent metadata

Field	Value
Publication number	US-9280977-B2
Application number	US-201414565315-A
Country	US
Kind code	B2
Filing date	Dec 9, 2014
Priority date	May 21, 2009
Publication date	Mar 8, 2016
Grant date	Mar 8, 2016

Abstract

Content fingerprints and watermarks are combined in various ways for content identification applications. Fingerprints are used to identify content generally while watermarks provide more detailed localization of parts within the content, and vice versa. Fingerprint techniques are further used for signal synchronization and other pre-processing steps to assist in digital watermark decoding. A variety of fingerprint/watermark techniques identify characteristics of the channel of content from content samples.

First claim

I claim:

1. A method of content recognition comprising:
receiving an audio signal captured from a microphone;
sampling the audio signal at a first resolution to provide a first sampled audio signal;
with a processor, computing at least a first audio fingerprint from the first sampled audio signal;
transferring the first audio fingerprint to a remote server, and in response, receiving metadata identifying a TV show, advertisement, movie or song from which the audio signal has been captured;
sampling the audio signal at a second resolution to provide a second sampled audio signal;
with a processor, computing at least a second audio fingerprint from the second sampled audio signal;
transferring the second audio fingerprint to a remote server, and in response to transferring the second audio fingerprint, receiving metadata to distinguish between distinct versions of the TV show, advertisement, movie or song from which the audio signal has been captured; wherein the first and second fingerprints are derived from first and second different resolutions of the audio signal, corresponding to fingerprint databases corresponding to the first and second resolutions.

2. The method of claim 1 wherein at least the second fingerprint corresponds to a distinct pre-distorted version of the TV show, advertisement, movie or song from which the audio signal has been captured.

3. The method of claim 1 wherein the first and second fingerprints correspond to fingerprint databases formed based on audio signals at first and second bit-rates, respectively.

4. The method of claim 1 including:
extracting a multibit payload encoded in the audio signal;
transferring the multibit payload to a remote server, and in response to transferring the multibit payload, receiving metadata indexed by the multibit payload.

5. The method of claim 4 wherein the metadata indexed by the multibit payload is used to determine a distribution channel of the audio signal.

6. A method of content recognition comprising:
receiving an audio signal captured from a microphone;
sampling the audio signal at a first resolution to provide a first sampled audio signal;
with a processor, computing at least a first audio fingerprint from the first sampled audio signal;
transferring the first audio fingerprint to a remote server, and in response to transferring the first audio fingerprint, receiving metadata identifying a TV show, advertisement, movie or song from which the audio signal has been captured;
sampling the audio signal at a second resolution to provide a second sampled audio signal;
with a processor, computing at least a second audio fingerprint from the second sampled audio signal;
transferring the second audio fingerprint to a remote server, and in response to transferring the second audio fingerprint, receiving metadata to distinguish between distinct versions of the TV show, advertisement, movie or song from which the audio signal has been captured;
wherein at least the second fingerprint corresponds to a distinct pre-distorted version of the TV show, advertisement, movie or song from which the audio signal has been captured.

7. The method of claim 6 wherein the first and second fingerprints are derived from first and second different resolutions of the audio signal, corresponding to fingerprint databases corresponding to the first and second resolutions.

8. The method of claim 6 wherein the first and second fingerprints correspond to fingerprint databases formed based on audio signals at first and second bit-rates, respectively.

9. The method of claim 6 wherein the first audio fingerprint is derived from an audio signal characteristic that is channel independent, and where the second audio fingerprint is derived from a signal characteristic that is channel dependent.

10. The method of claim 6 including:
extracting a multibit payload encoded in the audio signal;
transferring the multibit payload to a remote server, and in response to transferring the multibit payload, receiving metadata indexed by the multibit payload.

11. The method of claim 10 wherein the metadata indexed by the multibit payload is used to determine a distribution channel of the audio signal.

12. A system for content recognition comprising:
a microphone for capturing an audio signal;
one or more processors programmed to:
sample the audio signal at a first resolution to provide a first sampled audio signal;
compute at least a first audio fingerprint from the first sampled audio signal;
transfer the at least first audio fingerprint to a remote server, and in response to the transfer of the first audio fingerprint, receive metadata identifying a TV show, advertisement, movie or song from which the audio signal has been captured;
sample the audio signal at a second resolution to provide a second sampled audio signal;
compute at least a second audio fingerprint from the second sampled audio signal; and
transfer the second audio fingerprint to a remote server, and in response to the transfer of the second audio fingerprint, receive metadata to distinguish between distinct versions of the TV show, advertisement, movie or song from which the audio signal has been captured; the one or more processors being programmed to derive the first and second fingerprints from first and second different resolutions of the audio signal, the first and second fingerprints having corresponding databases of fingerprints for the first and second resolutions.

13. The system of claim 12 wherein at least the second fingerprint corresponds to a distinct pre-distorted version of the TV show, advertisement, movie or song from which the audio signal has been captured.

14. The system of claim 12 wherein the first and second fingerprints correspond to fingerprint databases formed based on audio signals at first and second bit-rates, respectively.

15. The system of claim 12 wherein the microphone and one or more programmed processors are part of a cell phone, the cell phone further comprising a display for displaying the metadata.

16. A system for content recognition comprising:
a microphone for capturing an audio signal;
one or more processors programmed to:
sample the audio signal at a first resolution to provide a first sampled audio signal;
compute at least a first audio fingerprint from the first sampled audio signal;
transfer the at least first audio fingerprint to a remote server, and in response to the transfer of the first audio fingerprint, receive metadata identifying a TV show, advertisement, movie or song from which the audio signal has been captured;
sample the audio signal at a second resolution to provide a second sampled audio signal;
compute at least a second audio fingerprint from the second sampled audio signal; and
transfer the second audio fingerprint to a remote server, and in response to the transfer of the second audio fingerprint, receive metadata to distinguish between distinct versions of the TV show, advertisement, movie or song from which the audio signal has been captured; wherein at least the second fingerprint corresponds to a distinct pre-distorted version of the TV show, advertisement, movie or song from which the audio signal has been captured.

17. The system of claim 16 wherein the first and second fingerprints correspond to fingerprint databases formed based on audio signals at first and second bit-rates, respectively.

18. The system of claim 16 wherein the microphone and one or more programmed processors are part of a cell phone, the cell phone further comprising a display for d

Assignees

• Digimarc Corp

Inventors

• Sharma Ravi K

Classifications

• G06T1/0028 Primary

  Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking · CPC title

• G10L19/018 Primary

  Audio watermarking, i.e. embedding inaudible data in the audio signal · CPC title