System for identifying content of digital data

• US 9,268,921 B2
• Filed: 04/04/2014
• Issued: 02/23/2016
• Est. Priority Date: 07/27/2007
• Status: Active Grant

• Current Assignee: Audible Magic Corporation
• Original Assignee: Audible Magic Corporation
• Inventors: Wold, Erling
• Primary Examiner(s): Chai, Longbit
• Application Number:
  US14/245,630
• Publication Number:
  US 20140215643A1
• Time in Patent Office: 690 Days
• Field of Search: 726/32
• US Class Current: 1/1
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06F 21/10 Protecting distributed programs or content, e.g. vending or licensing of copyrighted material protection in video systems or pay television H04N7/16 ; Digital rights management [DRM]
• CPC Class Codes: G06F 21/16 Program or content traceability, e.g. by watermarking

Abstract

A computing system selects a portion of data of an unknown work and detects each event in the portion of data of the unknown work. An event is a perceptual occurrence in a work successively positioned in time. The system determines an event metric between each successive event in the portion of data in the unknown work and generates a list of event metrics between the events for the unknown work. The system compares the list of event metrics for the unknown work to a list of event metrics for a known work and determines the unknown work is a copy of the known work responsive to a match between the list of event metrics of the unknown work and the list of event metrics for the known work.

Claims

1. A method comprising:

detecting, by a hardware processor, a plurality of events in a portion of image data of an unknown video work, wherein each of the plurality of events comprises a visually perceptual occurrence at a time location in the unknown video work, the plurality of events comprising at least one of a scene change between neighboring scenes in the portion of image data, a blank frame preceding or following a non-blank frame, or a first frame having pixels with a first color distribution preceding a second frame having pixels with a second color distribution that differs from the first color distribution by a threshold amount;

determining, by the hardware processor, one or more metrics between each pair of adjacent events from the plurality of events;

generating a first list comprising the plurality of events detected from the portion of image data of the unknown work and the one or more metrics between each pair of adjacent events from the plurality of events;

comparing the first list to a second list comprising events and metrics between events for a known work to determine a first quantity of hits and a second quantity of misses, wherein a hit is determined for a match between an event or metric in the first list and a corresponding event or metric in the second list and a miss is determined for an event or metric in the first list that fails to match an event or metric in the second list;

determining whether the first list matches the second list based on the first quantity of hits and the second quantity of misses; and

determining that the unknown video work is a copy of the known work responsive to a determining that the first list matches the second list.

2. The method of claim 1, further comprising:

generating a set of known works that is likely to contain the portion of image data of the unknown video work; and

selecting the known work from the set for comparison.

3. The method of claim 2, further comprising:

responsive to a determination that the first list does not match the second list, performing the following comprising;

selecting an additional known work from the set for comparison;

comparing the first list to a third list of events and metrics between events for the additional known work; and

determining the unknown video work is a copy of the additional known work responsive to a match of the first list to the third list.

4. The method of claim 1, further comprising:

determining whether the unknown video work is an authorized copy of the known work responsive to a determination that the unknown video work is a copy of the known work; and

reporting that the unknown video work is an unauthorized copy responsive to determining that the unknown video work is an unauthorized copy.

5. The method of claim 1, further comprising:

performing a secondary test to verify an identity of the unknown video work responsive to a determination that the first list matches the second list.

6. The method of claim 1, wherein the comparing comprises:

determining whether the first quantity of hits at least equals a threshold; and

returning a match responsive to the first quantity of hits being at least equal to the threshold.

7. A system comprising:

a memory; and

a hardware processor coupled with the memory to;

detect a plurality of events in a portion of image data of an unknown video work, wherein the plurality of events comprises visually perceptual occurrences at time locations in the unknown video work, the plurality of events comprising at least one of a scene change between neighboring scenes in the portion of image data, a blank frame preceding or following a non-blank frame, or a first frame having pixels with a first color distribution preceding a second frame having pixels with a second color distribution that differs from the first color distribution by a threshold amount;

determined one or more metrics between each pair of adjacent events from the plurality of events;

occurring at instances in time;

generate a first list of comprising the plurality of events detected from the portion of image data of the unknown work and the one or more metrics between each pair of adjacent events from the plurality of events;

compare the first list to a second list comprising events and metrics between events for a known work to determine a first quantity of hits and a second quantity of misses, wherein a hit is determined for a match between an event or metric in the first list and a corresponding event or metric in the second list and a miss is determined for an event or metric on the first list that fails to match an event or metric in the second list;

determine whether the first list matches the second list based on the first quantity of hits and the second quantity of misses; and

determine that the unknown video work is a copy of the known work responsive to determining that the first list matches the second list.

8. The system of claim 7, wherein the hardware processor is further to:

generate a set of known works that is likely to contain the portion of image data of the unknown video work; and

select the known work from the set for comparison.

9. The system of claim 7, wherein the hardware processor is further to:

responsive to a determination that the first list does not match the second list, perform the following comprising;

select an additional known work from the set for comparison;

compare the first list to a third list of events and metrics between events for the additional known work; and

determine the unknown video work is a copy of the additional known work responsive to a match of the first list to the third list.

10. The system of claim 7, wherein the hardware processor is further to:

determine whether the unknown video work is an authorized copy of the known work responsive to a determination that the unknown video work is a copy of the known work; and

report that the unknown video work is an unauthorized copy responsive to determining that the unknown video work is an unauthorized copy.

11. The system of claim 7, wherein the hardware processor is further to:

perform a secondary test to verify an identity of the unknown video work responsive to a determination that the first list matches the second list.

12. The system of claim 7, wherein the hardware processor is further to:

determine whether the first quantity of hits at least equals a threshold; and

return a match responsive to the first quantity of hits being at least equal to the threshold.

13. A non-transitory computer readable storage medium that provides instructions that, when executed on a hardware processor, cause the hardware processor to perform operations comprising:

detecting, by the hardware processor, a plurality of events in a portion of image data of an unknown video work, wherein the plurality of events comprises visually perceptual occurrences at time locations in the unknown video work, the plurality of events comprising at least one of a scene change between neighboring scenes in the portion of image data, a blank frame preceding or following a non-blank frame, or a first frame having pixels with a first color distribution preceding a second frame having pixels with a second color distribution that differs from the first color distribution by a threshold amount;

determining, by the hardware processor, one or more metrics between each pair of adjacent events from the plurality of events;

generating a first list comprising the plurality of events detected from the portion of image date of the unknown work and the one or more metrics between each pair of adjacent events from the plurality of events;

comparing the first list to a second list comprising events and metrics between events for a known work to determine a first quantity of hits and a second quantity of misses, wherein a hit is determined for a match between an event or metric in the first list and a corresponding event or metric in the second list and a miss is determined for an event or metric in the first list that fails to match an event or metric in the second list;

determining whether the first list matches the second list based on the first quantity of hits and the second quantity of misses; and

determining that the unknown video work is a copy of the known work responsive to determining that the first list matches the second list.

14. The non-transitory computer readable storage medium of claim 13, the operations further comprising:

generating a set of known works that is likely to contain the portion of image data of the unknown video work; and

selecting the known work from the set for comparison.

15. The non-transitory computer readable storage medium of claim 14, the operations further comprising:

responsive to a determination that the first list does not match the second list, performing the following comprising;

selecting an additional known work from the set for comparison;

comparing the first list to a third list of events and metrics between events for the additional known work; and

determining the unknown video work is a copy of the additional known work responsive to a match of the first list to the third list.

16. The non-transitory computer readable storage medium of claim 14, the operations further comprising:

determining whether the unknown video work is an authorized copy of the known work responsive to a determination that the unknown video work is a copy of the known work; and

reporting that the unknown video work is an unauthorized copy responsive to determining that the unknown video work is an unauthorized copy.

17. The non-transitory computer readable storage medium of claim 14, wherein the comparing comprises:

determining whether the first quantity of hits at least equals a threshold; and

returning a match responsive to the first quantity of hits being at least equal to the threshold.