METHODS AND SYSTEMS FOR DETERMINING IMAGE PROCESSING OPERATIONS RELEVANT TO PARTICULAR IMAGERY

• US 20140286542A1
• Filed: 02/25/2014
• Published: 09/25/2014
• Est. Priority Date: 03/19/2010
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Aller, Joshua V., Rodriguez, Tony F.
• Granted Patent: US 9,256,806 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06Q 30/0281 Customer communication at a business location, e.g. providing product or service information, consulting
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

Image data, such as from a mobile phone camera, is analyzed to determine a colorfulness metric (e.g., saturation) or a contrast metric (e.g., Weber contrast). This metric is then used in deciding which of, or in which order, plural different image recognition processes should be invoked in order to present responsive information to a user. A great number of other features and arrangements are also detailed.

Claims

1. A method comprising the acts:

analyzing received image data to determine a colorfulness metric, a color saturation metric, or a contrast metric; and

using said determined metric in deciding which plurality of different image recognition processes should be applied to image data captured by a smartphone camera, in order to present information derived from different types of imagery to a user from the smartphone.

2. The method of claim 1 that includes applying an image recognition process in accordance with said deciding act.

3. The method of claim 1 that that includes applying at least two of a barcode reading function, an optical character recognition function, a facial recognition function, and/or a watermark decoding function as a consequence of said deciding.

4. The method of claim 1 that that includes applying a barcode reading function as a consequence of said deciding.

5. The method of claim 1 that that includes applying an optical character recognition function as a consequence of said deciding.

6. The method of claim 1 that that includes applying a facial recognition function as a consequence of said deciding.

7. The method of claim 1 that that includes applying a watermark decoding function as a consequence of said deciding.

8. The method of claim 1 that includes receiving the image data from a camera system of a mobile phone device.

9. The method of claim 1 that further includes using said determined metric in deciding which of said plural image recognition processes not to invoke.

10. A mobile phone including a processor and a memory, the memory containing non-transitory software instructions causing the processor to perform the method of claim 1.

11. The method of claim 1 in which said using act includes:

comparing the determined metric with a threshold value;

if the determined metric is below the threshold value, applying one or more image recognition processes from a first set of processes; and

if the determined metric is above the threshold value, applying one or more image recognition processes from a second set of processes different than the first.

12. The method of claim 1 in which said using act includes:

applying the determined metric as an input to a rule-based process to determine which plurality of different recognition processes should be applied; and

applying the determined recognition processes to a set of image data.

13. The method of claim 1 that includes analyzing the received image data to determine a colorfulness metric.

14. The method of claim 1 that includes analyzing the received image data to determine a color saturation metric.

15. The method of claim 1 that includes analyzing the received image data to determine a contrast metric.

16. The method of claim 1 that includes analyzing the received image data to determine a color saturation metric, said analyzing including converting red/green/blue signals into another representation in which color is represented separately than luminance.

17. The method of claim 16 that includes determining whether more than 50% of the image data has a color saturation of less than 50%, in deciding which plurality of, or in which order plural, different image recognition processes should be applied to the image data captured by the smartphone camera.

18. The method of claim 16 that includes determining whether more than 50% of the image data has a color saturation of less than 50%, in deciding whether to apply a facial recognition operation to the image data.

19. A non-transitory computer readable storage medium having stored therein software instructions, said instructions being operative to cause a mobile phone processor programmed thereby to:

analyze received image data to determine a colorfulness metric, a color saturation metric, or a contrast metric; and

use said determined metric in deciding which plurality of different image recognition processes should be invoked by the mobile phone.

20. A method comprising:

analyzing received image data to determine a colorfulness metric, a color saturation metric, or a contrast metric;

comparing the determined metric with a threshold value;

if the determined metric is below the threshold value, applying one or more recognition processes from a first set of processes; and

if the determined metric is above the threshold value, applying one or more recognition processes from a second set of processes different than the first;

wherein the determined metric is used in deciding which plurality of different image recognition processes should be applied to image data captured by a smartphone camera, in order to present information derived from different types of imagery to a user from the smartphone.

21. The method of claim 20 in which one of said sets includes a barcode reading process, and the other of said sets includes a facial recognition process.

22. The method of claim 20 in which one of said sets includes a barcode reading process, and the other of said sets includes an object recognition process.

23. The method of claim 20 in which one of said sets includes an OCR process, and the other of said sets includes a facial recognition process.

24. The method of claim 20 in which one of said sets includes an OCR process, and the other of said sets includes an object recognition process.

25. The method of claim 20 that includes analyzing the received image data to determine a colorfulness metric.

26. The method of claim 20 that includes analyzing the received image data to determine a color saturation metric.

27. The method of claim 20 that includes analyzing the received image data to determine a contrast metric.

28. A method comprising:

analyzing a first set of image data to compute a colorfulness metric, a color saturation metric, or a contrast metric;

applying said computed metric as an input to a rule-based process to determine which of, or in which order, plural different recognition processes should be applied; and

applying the determined recognition process(es) to a set of image data;

wherein the computed metric is used in deciding which plurality of different image recognition processes should be applied to image data captured by a smartphone camera, in order to present information derived from different types of imagery to a user from the smartphone.

29. The method of claim 28 that includes applying the determined recognition processes to the first set of image data.

30. The method of claim 28 that includes applying the determined recognition processes to a second set of image data different than the first set of image data.

31. The method of claim 28 that includes analyzing the received image data to compute a colorfulness metric.

32. The method of claim 28 that includes analyzing the received image data to compute a color saturation metric.

33. The method of claim 28 that includes analyzing the received image data to compute a contrast metric.