Arrangements for increasing detection confidence

Patent metadata

Field	Value
Publication number	US-9449358-B2
Application number	US-201514681574-A
Country	US
Kind code	B2
Filing date	Apr 8, 2015
Priority date	Oct 20, 2011
Publication date	Sep 20, 2016
Grant date	Sep 20, 2016

Abstract

In one embodiment, a first set of digital data (e.g., an image) is tested for the presence of a certain feature (e.g., a certain face), yielding one of two outcomes (e.g., not-present, or present). If the testing yields the first outcome, no additional testing is performed. If, however, the testing yields the second outcome, further testing is performed to further check this outcome. Such further testing is performed on a second set of digital data that is based on, but different from, the first set of data. Only if the original testing and the further testing both yield the same second outcome is it treated as a valid result. A variety of other features and arrangements are also detailed.

First claim

We claim:

1. A method comprising the acts:
receiving first content data;
altering the first content data to yield second content data;
applying a first test to the first content data to determine whether the first content data has a first characteristic;
applying a second test to the second content data to determine whether the second content data has said first characteristic; and
after said first and second tests have been applied, concluding that the first content data has said first characteristic only if the second content data was also determined to have said first characteristic;
wherein the method employs hardware circuitry to perform one or more of said acts.

2. The method of claim 1 in which the first and second tests comprise the same test.

3. The method of claim 1 in which the content data comprises sampled audio, still image, or moving image data, and the altering comprises discarding or altering one or more of said samples.

4. The method of claim 1 in which the content data comprises coefficients representing audio or visual content in a frequency domain, and the altering comprises discarding or altering one or more of said coefficients.

5. The method of claim 1 in which the altering comprises resampling the content data.

6. The method of claim 1 in which the first test comprises a digital watermark decoding process.

7. The method of claim 1 in which the first test comprises a pattern recognition process.

8. The method of claim 1 in which the content data comprises image data representing rows and columns of pixel data, and the altering comprises discarding or altering data representing one or more of said rows and/or columns.

9. The method of claim 1 in which the content data comprises image data, and the altering comprises virtually rotating the image data.

10. The method of claim 1 that includes performing said acts of altering of the first content data, and applying said second test to the second content data, after applying said first test.

11. The method of claim 1 that includes performing said acts of altering of the first content data, and applying said second test to the second content data, after applying said first test, and only if said first test determines that the first content data has said first characteristic.

12. A non-transitory computer readable medium containing software instructions for configuring a programmable system to perform acts including:
receiving first content data;
altering the first content data to yield second content data;
applying a first test to the first content data to determine whether the first content data has a first characteristic;
applying a second test to the second content data to determine whether the second content data has said first characteristic; and
after said first and second tests have been applied, concluding that the first content data has said first characteristic only if the second content data was also determined to have said first characteristic.

13. The non-transitory computer readable medium of claim 12 in which the first and second tests comprise the same test.

14. The non-transitory computer readable medium of claim 12 in which the content data comprises sampled data, and the altering comprises discarding or altering one or more of said samples.

15. The non-transitory computer readable medium of claim 12 in which the content data comprises coefficients representing audio or image content in a frequency domain, and the altering comprises discarding or altering one or more of said coefficients.

16. The non-transitory computer readable medium of claim 12 in which the altering comprises resampling the content data.

17. The non-transitory computer readable medium of claim 12 in which the first test comprises a digital watermark decoding process.

18. The non-transitory computer readable medium of claim 12 in which the first test comprises a pattern recognition process.

19. The non-transitory computer readable medium of claim 12 in which the content data comprises image data representing rows and columns of pixel data, and the altering comprises discarding or altering data representing one or more of said rows and/or columns.

20. The non-transitory computer readable medium of claim 12 in which the content data comprises image data, and the altering comprises virtually rotating the image data.

21. The non-transitory computer readable medium of claim 12 that includes performing said acts of altering of the first content data, and said applying said second test to the second content data, after applying said first test.

22. The non-transitory computer readable medium of claim 12 that includes performing said acts of altering of the first content data, and said applying said second test to the second content data, after applying said first test, and only if said first test determines that the first content data has said first characteristic.

23. A system comprising a processor, a memory, an input for receiving content data and an output for providing result data, the memory containing software instructions for configuring the system to perform acts including:
receiving first content data from the input;
altering the first content data to yield second content data;
applying a first test to the first content data to determine whether the first content data has a first characteristic;
applying a second test to the second content data to determine whether the second content data has said first characteristic; and
after said first and second tests have been applied, concluding that the first content data has said first characteristic only if the second content data was also determined to have said first characteristic, and outputting a result to the output based on said conclusion.

Assignees

• Digimarc Corp

Inventors

• Rhoads Geoffrey B
• Stach John

Classifications

• G06T1/0021 Primary

  Image watermarking · CPC title

• G06K9/685

  Physics · mapped topic

• G06T2201/0065

  Extraction of an embedded watermark; Reliable detection · CPC title

• G06K2009/6871

  Physics · mapped topic

• G10L19/018

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