Red-eye filter method and apparatus

• US 8,203,621 B2
• Filed: 06/14/2010
• Issued: 06/19/2012
• Est. Priority Date: 10/09/1997
• Status: Expired due to Fees

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Corcoran, Peter, Bigioi, Petronel, DeLuca, Michael J
• Primary Examiner(s): LAM, HUNG H
• Application Number:
  US12/815,396
• Publication Number:
  US 20110080499A1
• Time in Patent Office: 736 Days
• Field of Search: 348/222.1, 348/239
• US Class Current: 348/222.1
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04N 1/6086 by scene illuminant, i.e. conditions at the time of picture capture, e.g. flash, optical filter used, evening, cloud, daylight, artificial lighting, white point measurement, colour temperature
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611
• CPC Class Codes: H04N 23/63 by using electronic viewfinders
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H04N 9/70 for colour killing

Abstract

A digital image acquisition system having no photographic film, such as a digital camera, has a flash unit for providing illumination during image capture and a red-eye filter for detecting a region within a captured image indicative of a red-eye phenomenon, the detection being based upon a comparison of the captured image and a reference image of nominally the same scene taken without flash. In the embodiment the reference image is a preview image of lower pixel resolution than the captured image, the filter matching the pixel resolutions of the captured and reference images by up-sampling the preview image and/or sub-sampling the captured image. The filter also aligns at least portions of the captured image and reference image prior to comparison to allow for, e.g. movement in the subject.

Claims

1. A portable digital camera device having no photographic film, comprising:

(a) an integral flash for providing illumination during image acquisition;

(b) a digital image capturing apparatus including one or more image sensors for capturing a main image including a face, and for acquiring one or more reference images at least approximately of said same scene as the main image including said face;

(c) a face filter for correcting a face defect within the main image based on analysis of at least one reference image;

(d) a dedicated hardware subsystem which is provided reference image data directly from at least one of the one or more image sensors;

(e) a main system memory which receives raw image data and metadata as implemented by the dedicated hardware subsystem; and

(f) wherein the main system memory is configured to receive metadata that comprises one or more identified face defect areas within the main image; and

(g) a subsampling module for changing the degree of said subsampling is determined based on a complexity of calculation for said filter.

2. The portable digital camera device of claim 1, wherein the one or more reference images comprise a relatively low resolution compared with the main image.

3. The portable digital camera device of claim 2, further comprising a subsampling module, and wherein the one or more relatively low resolution reference images comprise a subsample resolution representation of the main image.

4. The portable digital camera device of claim 3, wherein the subsampling module is configured for changing a degree of subsampling.

5. The portable digital camera device of claim 4, wherein said changing the degree of said subsampling is determined empirically.

6. The portable digital camera device of claim 4, wherein said changing the degree of said subsampling is determined based on a size of said image.

7. The portable digital camera device of claim 4, wherein said changing the degree of said subsampling is determined based on a region size.

8. The portable digital camera device of claim 3, wherein said subsample resolution representation is determined using spline interpolation.

9. The portable digital camera device of claim 3, wherein said subsample resolution representation is determined using bi-cubic interpolation.

10. The portable digital camera of claim 1, wherein one or more reference images comprise at least one precapture image.

11. The portable digital camera of claim 10, wherein the precapture image is captured just before the main image is captured.

12. The portable digital camera of claim 1, further comprising one or more further filters for correcting exposure, focus or composition of the main image, or combinations thereof, based on analysis of the reference image.

13. The portable digital camera of claim 1, further comprising a filter for aligning the one or more reference images with the main image.

14. The portable digital camera of claim 13, wherein the aligning comprises estimating camera or object movement, or both, in one or more intervals between capture of the main and reference images.

15. A method of correcting an image defect within a digital image, comprising:

providing illumination during image acquisition with a flash;

acquiring a main image and one or more reference images of at least approximately the same scene as the main image with the main image sensor;

identifying a face and a defect associated with said face within at least one of the one or more reference images;

identifying the same face and correcting the approximately same defect in the main image based on an analysis of the face and the defect in the at least one reference image by a face filter;

providing reference image data directly from the at least one sensor to a dedicated hardware subsystem;

receiving raw image data at a main image memory, along with metadata as implemented by the dedicated hardware subsystem; and

wherein the metadata comprises one or more candidate defect regions identified in the at least one reference image each having a certain enhanced probability of appearing as a defect in the main image; and

determining the degree of a subsampling by a subsampling module, based on a complexity of calculation for said filter.

16. The method of claim 15, wherein the one or more reference images comprise a relatively low resolution compared with the main image.

17. The method of claim 16, wherein the one or more relatively low resolution reference images comprise a subsample resolution representation of the main image.

18. The method of claim 17, further comprising changing a degree of subsampling of said subsample resolution representation.

19. The method of claim 18, further comprising determining the degree of said subsampling is empirically.

20. The method of claim 18, further comprising determining the degree of said subsampling based on a size of said image.

21. The method of claim 18, further comprising determining the degree of said subsampling based on a region size.

22. The method of claim 17, further comprising determining said subsample resolution representation using spline interpolation.

23. The method of claim 17, further comprising determining said subsample resolution representation using bi-cubic interpolation.

24. The method of claim 16, further comprising capturing the one or more relatively low resolution reference images before capturing the main image.

25. The method of claim 15, further comprising correcting exposure, focus or composition of the main image, or combinations thereof, based on analysis of the at least one reference imager.

26. The method of claim 15, further comprising aligning the at least one reference image with the main image.

27. The method of claim 26, wherein the aligning comprises estimating camera or object movement, or both, in one or more intervals between capture of the main and reference images.

28. One or more digital non-transitory storage media having code embodied therein for programming one or more processors of a portable digital camera that includes at least one image sensor to perform a method of correcting an image defect within a digital image, wherein the method comprises:

providing illumination during image acquisition with a flash;

acquiring a main image and one or more reference images of at least approximately the same scene as the main image with the main image sensor;

identifying a face and a defect associated with said face within at least one of the one or more reference images;

identifying the same face and correcting the approximately same defect in the main image based on an analysis of the face and the defect in the at least one reference image by a face filter;

providing reference image data directly from the at least one sensor to a dedicated hardware subsystem;

receiving raw image data at a main image memory, along with metadata as implemented by the dedicated hardware subsystem; and

wherein the metadata comprises one or more candidate defect regions identified in the at least one reference image each having a certain enhanced probability of appearing as a defect in the main image; and

determining the degree of a subsampling based on a complexity of calculation for said filter.

29. The one or more non-transitory storage media of claim 28, wherein the one or more reference images comprise a relatively low resolution compared with the main image.

30. The one or more non-transitory storage media of claim 29, wherein the one or more relatively low resolution reference images comprise a subsample resolution representation of the main image.

31. The one or more non-transitory storage media of claim 30, wherein the method further comprises changing a degree of subsampling of said subsample resolution representation.

32. The one or more non-transitory storage media of claim 31, wherein the method further comprises determining the degree of said subsampling is empirically.

33. The one or more non-transitory storage media of claim 31, wherein the method further comprises determining the degree of said subsampling based on a size of said image.

34. The one or more non-transitory storage media of claim 31, wherein the method further comprises determining the degree of said subsampling based on a region size.

35. The one or more non-transitory storage media of claim 30, wherein the method further comprises determining said subsample resolution representation using spline interpolation.

36. The one or more non-transitory storage media of claim 30, wherein the method further comprises determining said subsample resolution representation using bi-cubic interpolation.

37. The one or more non-transitory storage media of claim 29, wherein the method further comprises capturing the one or more relatively low resolution reference images before capturing the main image.

38. The one or more non-transitory media of claim 28, wherein the method further comprises correcting exposure, focus or composition of the main image, or combinations thereof, based on analysis of the at least one reference imager.

39. The one or more non-transitory media of claim 28, wherein the method further comprises aligning the at least one reference image with the main image.

40. The one or more media of claim 39, wherein the aligning comprises estimating camera or object movement, or both, in one or more intervals between capture of the main and reference images.