Abstract: Systems methods and non-transitory computer-readable media can obtain a test content item having a plurality of video frames. At least one video fingerprint is determined based on a set of video frames corresponding to the test content item. At least one reference content item is determined using at least a portion of the video fingerprint. At least one portion of the test content item that matches at least one portion of the reference content item is determined based at least in part on the video fingerprint of the test content item and one or more video fingerprints of the reference content item.
1. A computer-implemented method comprising:
generating, by a computing system, at least one fingerprint based on a set of frames corresponding to a test content item;
generating, by the computing system, a set of distorted fingerprints using at least a portion of the fingerprint; and
determining, by the computing system, one or more reference content items using the set of distorted fingerprints, wherein the test content item is evaluated against at least one reference content item to identify matching content.
2. The computer-implemented method of claim 1, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
obtaining, by the computing system, a set of bits corresponding to a first frame in the set of frames from which the fingerprint was generated; and
generating, by the computing system, a set of binary string permutations for at least a portion of the set of bits.
3. The computer-implemented method of claim 2, wherein one or more bits are permuted in each binary string.
4. The computer-implemented method of claim 2, wherein generating the set of binary string permutations further comprises:
generating, by the computing system, a first set of binary string permutations for the portion of the set of bits, wherein one bit is permuted in each binary string;
determining, by the computing system, that no reference content items were identified using the first set of binary string permutations; and
generating, by the computing system, a second set of binary string permutations for the portion of the set of bits, wherein multiple bits are permuted in each binary string.
5. The computer-implemented method of claim 1, wherein determining one or more
reference content items using the set of distorted fingerprints further comprises:
obtaining, by the computing system, a set of bits corresponding to a first distorted fingerprint;
identifying, by the computing system, at least one candidate frame based at least in part on a portion of the set of bits; and
determining, by the computing system, at least one reference content item based on the candidate frame.
6. The computer-implemented method of claim 5, wherein identifying at least one
candidate frame based at least in part on a portion of the set of bits further comprises:
hashing, by the computing system, the portion of the set of bits to a bin in an inverted index, wherein the bin references information describing the at least one candidate frame and the reference content item.
7. The computer-implemented method of claim 1, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
determining, by the computing system, that identifying reference content items using the set of distorted fingerprints will not cause a central processing unit (CPU) load of the computing system to exceed a threshold load.
8. The computer-implemented method of claim 1, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
determining, by the computing system, that no reference content items were identified using the at least one fingerprint.
9. The computer-implemented method of claim 1, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
determining, by the computing system, at least one reference content item using the at least one fingerprint; and
determining, by the computing system, that no matches between the test content item and the reference content item were identified.
10. The computer-implemented method of claim 1, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
determining, by the computing system, at least one reference content item using the at least one fingerprint; and
determining, by the computing system, that a match between the test content item and the reference content item is within a threshold match distance.
11. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
generating at least one fingerprint based on a set of frames corresponding to a test content item;
generating a set of distorted fingerprints using at least a portion of the fingerprint; and
determining one or more reference content items using the set of distorted fingerprints, wherein the test content item is evaluated against at least one reference content item to identify matching content.
12. The system of claim 11, wherein generating the set of distorted fingerprints using at least
a portion of the fingerprint further causes the system to perform:
obtaining a set of bits corresponding to a first frame in the set of frames from which the fingerprint was generated; and
generating a set of binary string permutations for at least a portion of the set of bits.
13. The system of claim 12, wherein one or more bits are permuted in each binary string.
14. The system of claim 12, wherein generating the set of binary string permutations further causes the system to perform:
generating a first set of binary string permutations for the portion of the set of bits, wherein one bit is permuted in each binary string;
determining that no reference content items were identified using the first set of binary string permutations; and
generating a second set of binary string permutations for the portion of the set of bits, wherein multiple bits are permuted in each binary string.
15. The system of claim 11, wherein determining one or more reference content items
using the set of distorted fingerprints further causes the system to perform:
obtaining a set of bits corresponding to a first distorted fingerprint;
identifying at least one candidate frame based at least in part on a portion of the set of bits; and
determining at least one reference content item based on the candidate frame.
16. A computer-implemented method comprising:
generating, by a computing system, at least one fingerprint based on a set of frames corresponding to a test content item;
generating, by the computing system, a set of distorted fingerprints using at least a portion of the fingerprint; and
determining, by the computing system, one or more reference content items using the set of distorted fingerprints, wherein the test content item is evaluated against at least one reference content item to identify matching content.
17. The computer-implemented method of claim 16, wherein generating the set of distorted
fingerprints using at least a portion of the fingerprint further comprises:
obtaining, by the computing system, a set of bits corresponding to a first frame in the set of frames from which the fingerprint was generated; and
generating, by the computing system, a set of binary string permutations for at least a portion of the set of bits.
18. The computer-implemented method of claim 17, wherein one or more bits are permuted in each binary string.
19. The computer-implemented method of any of claim 17 or 18, wherein generating the set of binary string permutations further comprises:
generating, by the computing system, a first set of binary string permutations for the portion of the set of bits, wherein one bit is permuted in each binary string;
determining, by the computing system, that no reference content items were identified using the first set of binary string permutations; and
generating, by the computing system, a second set of binary string permutations for the portion of the set of bits, wherein multiple bits are permuted in each binary string.
20. The computer-implemented method of claim 20, including continuing the generation and
testing of distortions in stages until a threshold central processing unit (CPU) usage;
and/or
a threshold query time is reached.
21. The computer-implemented method of any of claims 16 to 20, wherein determining one
or more reference content items using the set of distorted fingerprints further comprises:
obtaining, by the computing system, a set of bits corresponding to a first distorted fingerprint;
identifying, by the computing system, at least one candidate frame based at least in part on a portion of the set of bits; and
determining, by the computing system, at least one reference content item based on the candidate frame;
preferably wherein identifying at least one candidate frame based at least in part on a portion of the set of bits further comprises:
hashing, by the computing system, the portion of the set of bits to a bin in an inverted index, wherein the bin references information describing the at least one candidate frame and the reference content item.
22. The computer-implemented method of any of claims 16 to 21, wherein generating the set
of distorted fingerprints using at least a portion of the fingerprint further comprises:
determining, by the computing system, that identifying reference content items using the set of distorted fingerprints will not cause a central processing unit (CPU) load of the computing system to exceed a threshold load; and/or
determining, by the computing system, that no reference content items were identified using the at least one fingerprint; and/or
determining, by the computing system, at least one reference content item using the at least one fingerprint; and
determining, by the computing system, that no matches between the test content item and the reference content item were identified; and/or
determining, by the computing system, at least one reference content item using the at least one fingerprint; and
determining, by the computing system, that a match between the test content item and the reference content item is within a threshold match distance.
23. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
generating at least one fingerprint based on a set of frames corresponding to a test content item;
generating a set of distorted fingerprints using at least a portion of the fingerprint; and
determining one or more reference content items using the set of distorted fingerprints, wherein the test content item is evaluated against at least one reference content item to identify matching content.
24. The system of claim 23, wherein generating the set of distorted fingerprints using at least
a portion of the fingerprint further causes the system to perform:
obtaining a set of bits corresponding to a first frame in the set of frames from which the fingerprint was generated; and
generating a set of binary string permutations for at least a portion of the set of bits;
preferably wherein one or more bits are permuted in each binary string; and/or
preferably wherein generating the set of binary string permutations further causes the system to perform:
generating a first set of binary string permutations for the portion of the set of bits, wherein one bit is permuted in each binary string;
determining that no reference content items were identified using the first set of binary string permutations; and
generating a second set of binary string permutations for the portion of the set of bits, wherein multiple bits are permuted in each binary string.
25. The system of claim 23 or 24, wherein determining one or more reference content items
using the set of distorted fingerprints further causes the system to perform:
obtaining a set of bits corresponding to a first distorted fingerprint;
identifying at least one candidate frame based at least in part on a portion of the set of bits; and
determining at least one reference content item based on the candidate frame.
| # | Name | Date |
|---|---|---|
| 1 | 201947001855.pdf | 2019-01-16 |
| 2 | 201947001855-STATEMENT OF UNDERTAKING (FORM 3) [16-01-2019(online)].pdf | 2019-01-16 |
| 3 | 201947001855-POWER OF AUTHORITY [16-01-2019(online)].pdf | 2019-01-16 |
| 4 | 201947001855-FORM 1 [16-01-2019(online)].pdf | 2019-01-16 |
| 5 | 201947001855-DRAWINGS [16-01-2019(online)].pdf | 2019-01-16 |
| 6 | 201947001855-DECLARATION OF INVENTORSHIP (FORM 5) [16-01-2019(online)].pdf | 2019-01-16 |
| 7 | 201947001855-COMPLETE SPECIFICATION [16-01-2019(online)].pdf | 2019-01-16 |
| 8 | 201947001855-CLAIMS UNDER RULE 1 (PROVISIO) OF RULE 20 [16-01-2019(online)].pdf | 2019-01-16 |
| 9 | abstract 201947001855.jpg | 2019-01-18 |
| 10 | 201947001855-RELEVANT DOCUMENTS [14-05-2019(online)].pdf | 2019-05-14 |
| 11 | 201947001855-FORM 13 [14-05-2019(online)].pdf | 2019-05-14 |
| 12 | 201947001855-AMENDED DOCUMENTS [14-05-2019(online)].pdf | 2019-05-14 |
| 13 | 201947001855-FORM-26 [01-06-2019(online)].pdf | 2019-06-01 |
| 14 | Correspondence by Agent_General Power Of Attorney_06-06-2019.pdf | 2019-06-06 |
| 15 | 201947001855-FORM 3 [08-07-2019(online)].pdf | 2019-07-08 |
| 16 | 201947001855-FORM 18 [27-04-2020(online)].pdf | 2020-04-27 |
| 17 | 201947001855-Proof of Right [23-06-2020(online)].pdf | 2020-06-23 |
| 18 | 201947001855-PETITION UNDER RULE 137 [23-06-2020(online)].pdf | 2020-06-23 |
| 19 | 201947001855-FORM 3 [07-07-2020(online)].pdf | 2020-07-07 |
| 20 | 201947001855-FORM 3 [29-06-2021(online)].pdf | 2021-06-29 |
| 21 | 201947001855-FER.pdf | 2021-10-17 |
| 22 | 201947001855-Information under section 8(2) [02-12-2021(online)].pdf | 2021-12-02 |
| 23 | 201947001855-Information under section 8(2) [02-12-2021(online)]-1.pdf | 2021-12-02 |
| 24 | 201947001855-OTHERS [03-12-2021(online)].pdf | 2021-12-03 |
| 25 | 201947001855-FER_SER_REPLY [03-12-2021(online)].pdf | 2021-12-03 |
| 26 | 201947001855-DRAWING [03-12-2021(online)].pdf | 2021-12-03 |
| 27 | 201947001855-CORRESPONDENCE [03-12-2021(online)].pdf | 2021-12-03 |
| 28 | 201947001855-CLAIMS [03-12-2021(online)].pdf | 2021-12-03 |
| 29 | 201947001855-ABSTRACT [03-12-2021(online)].pdf | 2021-12-03 |
| 30 | 201947001855-RELEVANT DOCUMENTS [19-01-2022(online)].pdf | 2022-01-19 |
| 31 | 201947001855-POA [19-01-2022(online)].pdf | 2022-01-19 |
| 32 | 201947001855-FORM 13 [19-01-2022(online)].pdf | 2022-01-19 |
| 33 | 201947001855-AMENDED DOCUMENTS [19-01-2022(online)].pdf | 2022-01-19 |
| 34 | 201947001855-FORM 3 [22-06-2022(online)].pdf | 2022-06-22 |
| 35 | 201947001855-PatentCertificate04-09-2023.pdf | 2023-09-04 |
| 36 | 201947001855-IntimationOfGrant04-09-2023.pdf | 2023-09-04 |
| 1 | SearchStrategy_201947001855E_13-07-2021.pdf |