Methods and apparatus to perform symbol-based watermark detection
Methods, apparatus, systems and articles of manufacture are disclosed to perform symbol-based watermark detection. An example method includes, in response to determining that a first rate of occurrence of a first potential symbol equals a second rate of occurrence of a second potential symbol, a first accumulated signal to noise ratio value corresponding to occurrences of the first potential symbol value is determined. A second accumulated signal to noise ratio value corresponding to occurrences of the second potential symbol value is determined. One of the first potential symbol value or the second potential symbol value having a greatest accumulated signal to noise ratio value as the likely symbol value is selected. The likely symbol value is concatenated with other likely symbol values corresponding to other symbols of the watermark to detect the watermark.
1. A symbol-based watermark detection method comprising:
determining a first rate of occurrence of a first potential symbol value within a history of potential symbol values corresponding to a first symbol within a watermark;
determining a second rate of occurrence of a second potential symbol value within the history of potential symbol values corresponding to the first symbol within the watermark;
in response to determining that the first rate of occurrence of the first potential symbol value equals the second rate of occurrence of the second potential symbol value, perform first operations including:
determining a first accumulated signal to noise ratio value corresponding to occurrences of the first potential symbol value;
determining a second accumulated signal to noise ratio value corresponding to occurrences of the second potential symbol value; and
selecting, by executing an instruction with a processor of an audience measurement device, one of the first potential symbol value or the second potential symbol value having a greatest accumulated signal to noise ratio value as a likely symbol value for the first symbol; and
concatenating the likely symbol value with other likely symbol values corresponding to other symbols of the watermark to detect the watermark.
2. The method of claim 1 , further including populating a symbol buffer with the history of potential symbol values corresponding to the first symbol.
3. The method of claim 2 , further including populating signal to noise ratio values corresponding to each of the potential symbol values in the symbol buffer.
4. The method of claim 2 , further including storing six historic values of each symbol of the watermark in the symbol buffer.
5. The method of claim 1 , wherein the first operations are performed in response to the determining that the first rate of occurrence equals the second rate of occurrence, and that the first rate of occurrence exceeds an occurrence threshold and that the second rate of occurrence exceeds the occurrence threshold, and further including:
in response to determining that at least one of the first rate of occurrence or the second rate of occurrence does not meet the occurrence threshold:
determining whether a pattern can be identified in the history of potential symbol values corresponding to the first symbol; and
selecting one of the history of potential symbol values as the likely symbol value when the pattern can be identified.
6. The method of claim 5 , wherein the pattern is an incrementing value corresponding to incrementing timestamps within data conveyed by the watermark.
7. The method of claim 5 , wherein the selected one of the history of potential symbol values is a most recently identified symbol value that matches the pattern.
8. The method of claim 1 , further including determining that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than a signal to noise difference threshold, and the first potential symbol value is selected in response to the determination that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than the signal to noise difference threshold.
9. The method of claim 1 , further including in response to one of the first potential symbol value or the second potential symbol value having a greatest rate of occurrence, selecting one of the first potential symbol value or the second potential symbol value having the greatest rate of occurrence as the likely symbol value.
10. An apparatus of to perform symbol-based watermark detection, the apparatus comprising:
a symbol buffer analyzer to:
determine a first rate of occurrence of a first potential symbol value within a history of potential symbol values corresponding to a first symbol within a watermark;
determine a second rate of occurrence of a second potential symbol value within the history of potential symbol values corresponding to the first symbol within the watermark;
in response to a determination that the first rate of occurrence of the first potential symbol value is the same as the second rate of occurrence of the second potential symbol value:
determine a first accumulated signal to noise ratio value corresponding to occurrences of the first potential symbol value;
determine a second accumulated signal to noise ratio value corresponding to occurrences of the second potential symbol value; and
select one of the first potential symbol value or the second potential symbol value having a greatest accumulated signal to noise ratio value as a likely symbol value for the first symbol; and
a watermark constructor to concatenate the likely symbol value with other likely symbol values corresponding to other symbols of the watermark to detect the watermark.
11. The apparatus of claim 10 , further including a symbol buffer to store the history of the potential symbol values corresponding to the first symbol.
12. The apparatus of claim 11 , the symbol buffer is further to store signal to noise ratio values corresponding to each of the potential symbol values.
13. The apparatus of claim 11 , the symbol buffer to store six values of history of each symbol of the watermark.
14. The apparatus of claim 10 , wherein the symbol buffer analyzer is further to:
determine that at least one of the first rate of occurrence or the second rate of occurrence exceeds an occurrence threshold;
in response to the determination that the at least one of the first rate of occurrence or the second rate of occurrence does not meet the occurrence threshold:
determine whether a pattern can be identified in the history of potential symbol values; and
select one of the history of potential symbol values as the most likely symbol value when the pattern can be identified.
15. The apparatus of claim 14 , wherein the pattern is an incrementing value corresponding to incrementing timestamps within data conveyed by the watermark.
16. The apparatus of claim 14 , wherein the symbol buffer analyzer is further to select one of the history of potential symbol values having a most recently identified symbol value that matches the pattern.
17. The apparatus of claim 10 , wherein the symbol buffer analyzer is further to determine that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than a signal to noise difference threshold, and the symbol buffer analyzer is to select the first potential symbol value in response to the determination that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than the signal to noise difference threshold.
18. The apparatus of claim 10 , the symbol buffer analyzer further to in response to one of the first potential symbol value or the second potential symbol value having a greatest rate of occurrence, select one of the first potential symbol value or the second potential symbol value having the greatest rate of occurrence as the likely symbol value.
19. A tangible machine-readable storage medium comprising instructions which, when executed, cause a machine to at least:
determine a first rate of occurrence of a first potential symbol value within a history of potential symbol values corresponding to a first symbol within a watermark;
determine a second rate of occurrence of a second potential symbol value within the history of potential symbol values corresponding to the first symbol within the watermark;
select one of the first potential symbol value or the second potential symbol value having the greatest rate of occurrence as a likely symbol value;
in response to the determination that the first rate of occurrence of the first potential symbol value equals the second rate of occurrence of the second potential symbol value:
determine a first accumulated signal to noise ratio value corresponding to occurrences of the first potential symbol value;
determine a second accumulated signal to noise ratio value corresponding to occurrences of the second potential symbol value; and
select one of the first potential symbol value or the second potential symbol value having a greatest accumulated signal to noise ratio value as the likely symbol value; and
concatenate the likely symbol value with other likely symbol values corresponding to other symbols of the watermark to detect the watermark.
20. The tangible machine-readable storage medium of claim 19 , wherein the instructions, when executed, further cause the machine to populate a symbol buffer with the history of potential symbol values corresponding to the first symbol.
21. The tangible machine-readable storage medium of claim 20 , wherein the instructions, when executed, further cause the machine to populate the symbol buffer with signal to noise ratio values corresponding to each of the potential symbol values.
22. The tangible machine-readable storage medium of claim 20 , wherein the symbol buffer is to store six values of history of each symbol of the watermark.
23. The tangible machine-readable storage medium of claim 19 , wherein the instructions, when executed, further cause the machine to:
determine that at least one of the first rate of occurrence or the second rate of occurrence exceeds an occurrence threshold; and
in response to the determination that the at least one of the first rate of occurrence or the second rate of occurrence does not meet the occurrence threshold:
determine whether a pattern can be identified in the history of potential symbol values, and
select one of the history of potential symbol values as the most likely symbol value when the pattern can be identified.
24. The tangible machine-readable storage medium of claim 23 , wherein the pattern is an incrementing value corresponding to incrementing timestamps within data conveyed by the watermark.
25. The tangible machine-readable storage medium of claim 23 , wherein the selected one of the history of potential symbol values is a most recently identified symbol value that matches the pattern.
26. The tangible machine-readable storage medium of claim 19 , wherein the instructions, when executed, further cause the machine to:
determine that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than a signal to noise difference threshold; and
select the first potential symbol value in response to the determination that the first accumulated signal to noise ratio value is greater than the second accumulated signal to noise ratio value by more than the signal to noise difference threshold.