Comparing video sequences using fingerprints

1. A system configured to compare a first sequence of video images represented by a first sequence of fingerprints at a first image repetition rate with a second sequence of video images represented by a second sequence of fingerprints at a second image repetition rate, wherein the second image repetition rate is different from the first image repetition rate, in which the fingerprints are spatial fingerprints derived each from content of a single video image, temporal fingerprints derived each from a difference in content between two video images or a combination of spatial and temporal fingerprints, the system comprising an electronic processor configured to:

generate from the first sequence of fingerprints a converted sequence of fingerprints at the second image repetition rate or a common image repetition rate; and

perform a correlation between the converted sequence of fingerprints and the second sequence of fingerprints or a second converted sequence of fingerprints generated from the second sequence of fingerprints at the common image repetition rate;

wherein the converted sequence of fingerprints includes a combination of a number of neighbouring fingerprints in the first or second sequence of fingerprints, and

wherein the combination of the number of neighbouring fingerprints includes a weighted average based on a temporal location of the respective neighbouring fingerprints in the first sequence of fingerprints in which a temporal fingerprint in the first sequence of fingerprints is scaled in accordance with a ratio of the first and second image repetition rates.

2. The system of claim 1 , further comprising:

at least one fingerprint creation module configured to form the fingerprints;

a generation module configured to generate the converted sequence of fingerprints; and

a correlator configured to perform the correlation between the converted sequence of fingerprints and the second sequence of fingerprints.

3. The system of claim 1 , wherein the electronic processor is configured to detect shot changes in the first and/or second sequence of video images and wherein temporal fingerprints derived from video images across a shot change are ignored or given reduced prominence when the correlation is performed.

4. The system of claim 3 , wherein ignoring or giving reduced prominence to temporal fingerprints derived across the shot change comprises replacing the temporal fingerprints derived across the shot change with a temporal fingerprint selected from the group consisting of the temporal fingerprint immediately preceding it, the temporal fingerprint immediately succeeding it, and a combination of the two.

5. The system of claim 1 , wherein the electronic processor is configured to detect a cadence of any 3:2 or 2:2 repetition of video images resulting from a previous film to video conversion process and wherein temporal fingerprints derived from repeating video images are replaced by a temporal fingerprint selected from the group consisting of a neighbouring non-zero temporal fingerprint, an estimated value, and a re-constituting of the original temporal differences between the images.

6. The system of claim 5 , wherein the electronic processor is configured to detect the cadence by identifying temporal fingerprints with values of zero, or close to zero or that come in identical, or near identical sequential pairs.

7. The system of claim 1 , wherein the electronic processor is configured to perform the correlation between the converted sequence of fingerprints and the second sequence of fingerprints by performing one of: a discrete correlation function, a phase correlation process, a simple sum of absolute minimum differences as a function of offset, or an alternative matching function which compares the two inputs and returns a function which has an optimum point at an offset position.

8. A method for comparing video images, the method comprising:

comparing, with a video processor, a first sequence of fingerprints representing a first sequence of video images at a first image repetition rate with a second sequence of fingerprints representing a second sequence of video images at a second image repetition rate, the second image repetition rate different from the first image repetition rate, wherein the fingerprints are spatial fingerprints derived each from content of a single video image, temporal fingerprints derived each from a difference in content between two video images, and a combination of spatial fingerprints and temporal fingerprints;

generating from the first sequence of fingerprints a converted sequence of fingerprints at the second image repetition rate or a common repetition rate; and

performing a correlation between the converted sequence of fingerprints and the second sequence of fingerprints or a second converted sequence of fingerprints generated from the second sequence of fingerprints at the common image repetition rate;

wherein the generating of the converted sequence of fingerprints includes, for a fingerprint in the converted sequence, forming a combination of a number of neighbouring fingerprints in the first or second sequence of fingerprints, and

wherein the combination of the spatial fingerprints and temporal fingerprints includes a weighted average based on the temporal location of the respective neighbouring fingerprints in the first sequence of fingerprints with respect to the fingerprint in the converted sequence and in which a temporal fingerprint in the first sequence of fingerprints is scaled in accordance with a ratio of the first and second image repetition rates.

9. The method of claim 8 , further comprising detecting shot changes in the first and/or second sequence of video images, wherein temporal fingerprints derived from video images across a shot change are ignored or given reduced prominence when the correlation is performed.

10. The method of claim 9 , wherein the ignoring or giving reduced prominence to temporal fingerprints derived across the shot change comprises replacing the temporal fingerprints derived across the shot change with a temporal fingerprint selected from the group consisting of: the temporal fingerprint immediately preceding it, the temporal fingerprint immediately succeeding it, or a combination of the two.

11. The method of claim 8 , further comprising detecting a cadence of any 3:2 or 2:2 repetition of video images resulting from a previous film to video conversion process and replacing temporal fingerprints derived from repeating video images by a neighbouring non-zero temporal fingerprint, by re-constituting the original temporal differences between the images or other estimated value.

12. The method of claim 11 , wherein the detecting of the cadence comprises identifying temporal fingerprints with values of zero, or close to zero or that come in substantially identical sequential pairs.

13. The method of claim 8 , further comprising detecting the cadence of any 3:2 or 2:2 repetition of video images resulting from a previous film to video conversion process and wherein in the event cadence is detected, performing a scaling of the first temporal fingerprints is disabled.

14. The method of claim 8 , wherein the performing of the correlation between the converted sequence of fingerprints and the second sequence of fingerprints comprises performing one of: a discrete correlation function, a phase correlation process, a simple sum of absolute minimum differences as a function of offset, or an alternative matching function which compares the two inputs and returns a function which has an optimum point at an offset position.

15. The method of claim 8 , further comprising configuring the correlation of the converted sequence of fingerprints and the second sequence of fingerprints to measure the correlation or matching function to sub-sample precision.

16. A non-transitory computer-readable medium comprising computer-executable instructions that when executed by one or more processors cause the one or more processors to perform a method of comparing in a video processor a first sequence of fingerprints representing a first sequence of video images at a first image repetition rate with a second sequence of fingerprints representing a second sequence of video images at a second image repetition rate, different from the first image repetition rate, in which the fingerprints are spatial fingerprints derived each from content of a single video image, temporal fingerprints derived each from a difference in content between two video images or a combination of spatial and temporal fingerprints, wherein the performed method comprising the steps of:

generating from the first sequence of fingerprints a converted sequence of fingerprints at the second image repetition rate or a common repetition rate; and

performing a correlation between the converted sequence of fingerprints and the second sequence of fingerprints or a second converted sequence of fingerprints generated from the second sequence of fingerprints at the common image repetition rate,

wherein the generating of the converted sequence of fingerprints comprises, for a fingerprint in the converted sequence, forming a combination of values of a number of neighbouring fingerprints in the first or second sequence of fingerprints, and

wherein the combination of the values of the number of neighbouring fingerprints includes a weighted average based on a temporal location of the respective neighbouring fingerprints in the first sequence of fingerprints in which a temporal fingerprint in the first sequence of fingerprints is scaled in accordance with a ratio of the first and second image repetition rates.