Red-eye filter method and apparatus

• US 20050041121A1
• Filed: 08/16/2004
• Published: 02/24/2005
• Est. Priority Date: 10/09/1997
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: Tessera Technologies Ireland Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Bigioi, Petronel, Corcoran, Peter, DeLuca, Michael J.
• Granted Patent: US 7,738,015 B2
• Time in Patent Office: Days
• US Class Current: 348/239
• 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 digital image acquisition system having no photographic film, comprising a portable apparatus for capturing digital images, 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, said detection being based upon a comparison of said captured image and at least one reference eye color characteristic.

2. The system of claim 1, wherein said at least one reference eye color characteristic comprises an eye color characteristic of a reference image of nominally the same scene taken without flash.

3. A system according to claim 2, wherein the reference image is a preview image of lower pixel resolution than the captured image, the filter including programming code for matching the pixel resolutions of the captured and reference images by at least one of up-sampling the preview image and sub-sampling the captured image.

4. A system according to claim 3, the filter including further programming code for aligning at least portions of the captured image and reference image prior to said comparison.

5. A system according to claim 4, wherein the filter also includes a shape analyser so that the filter is configured to identify a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

6. A system according to claim 4, wherein the filter also includes a shape analyser to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

7. A system according to claim 2, the filter further including programming code for aligning at least portions of the captured image and reference image prior to said comparison.

8. A system according to claim 7, wherein the filter also includes a shape analyser so that the filter is configured to identify a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

9. A system according to claim 7, wherein the filter also includes a shape analyser to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

10. A system according to claim 2, wherein the filter detects said region indicative of a red-eye phenomenon by identifying a region in the captured image at least having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, the filter further designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

11. A system according to claim 10, wherein the decision as to whether a region has a color indicative of a red-eye phenomenon is determined on a statistical basis as a global operation on the entire region.

12. A system according to claim 2, wherein the filter also includes a shape analyser so that the filter is configured to identify a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

13. A system according to claim 2, wherein the filter also includes a shape analyser to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

14. A system according to claim 2, wherein said digital image acquisition system is a digital camera.

15. A system according to claim 2, wherein said digital image acquisition system is a camera is a combination of a digital camera and an external processing device.

16. A system as claimed in claim 15, wherein said red-eye filter is located in said external processing device.

17. A system according to claim 2, further including a pixel modifier for modifying the color of the pixels within a region indicative of a red-eye phenomenon.

18. A system according to claim 1, wherein the filter also includes a shape analyser so that the filter is configured to identify a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with a reference eye shape characteristic and the reference eye color characteristic, respectively.

19. A system according to claim 18, further including a pixel modifier for modifying the color of the pixels within a region indicative of a red-eye phenomenon.

20. A system according to claim 1, further including a pixel modifier for modifying the color of the pixels within a region indicative of a red-eye phenomenon.

21. A digital image acquisition system having no photographic film, comprising a portable apparatus for capturing digital images, a flash unit for providing illumination during image capture, and a red-eye filter for detecting red-eye phenomenon in a captured image based upon a comparison of said captured image and a reference image of nominally the same scene taken without flash, wherein the reference image is a preview image of lower pixel resolution than the captured image, the filter including means for matching the pixel resolutions of the captured and reference images by at least one of up-sampling the preview image and sub-sampling the captured image.

22. A system according to claim 21, the filter further including means for aligning at least portions of the captured image and reference image prior to said comparison.

23. A system according to claim 22, wherein the filter detects said red-eye phenomenon by identifying a region in the captured image having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, the filter further designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

24. A system according to claim 21, wherein the decision as to whether a region has a color indicative of a red-eye phenomenon is determined on a statistical basis as a global operation on the entire region.

25. A system according to claim 21, wherein the filter detects said red-eye phenomenon by identifying a region in the captured image having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, the filter further designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

26. A digital image acquisition system having no photographic film, comprising a portable apparatus for capturing digital images, a flash unit for providing illumination during image capture, and a red-eye filter for detecting red-eye phenomenon in a captured image based upon a comparison of said captured image and a reference image of nominally the same scene taken without flash, the filter further including means for aligning at least portions of the captured image and reference image prior to said comparison.

27. A system according to claim 26, wherein the filter detects said red-eye phenomenon by identifying a region in the captured image having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, the filter further designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

28. A system according to claim 27, wherein the decision as to whether a region has a color indicative of a red-eye phenomenon is determined on a statistical basis as a global operation on the entire region.

29. A digital image acquisition system having no photographic film, comprising a portable apparatus for capturing digital images, a flash unit for providing illumination during image capture, and a red-eye filter for detecting red-eye phenomenon in a captured image based upon a comparison of said captured image and a reference image of nominally the same scene taken without flash, wherein the filter further comprising means for detecting said red-eye phenomenon by identifying a region in the captured image having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, the filter further designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

30. A system according to claim 29, wherein the decision as to whether a region has a color indicative of a red-eye phenomenon is determined on a statistical basis as a global operation on the entire region.

31. A method of detecting a red-eye phenomenon within a digital image acquired by a digital image acquisition device having no photographic film, the device comprising a portable apparatus for capturing digital images, and a flash unit for providing illumination during image capture, the method comprising identifying a region within a captured image indicative of a red-eye phenomenon including comparing said captured image and at least one reference eye color characteristic.

32. The method of claim 31, wherein said at least one reference eye color characteristic comprises an eye color characteristic of a reference image of nominally the same scene taken without flash.

33. A method according to claim 32, wherein the reference image is a preview image of lower pixel resolution than the captured image, the method further comprising matching the pixel resolutions of the captured and reference images including up-sampling the preview image or sub-sampling the captured image, or a combination thereof.

34. A method according to claim 33, further comprising aligning at least portions of the captured image and reference image prior to said comparison.

35. A method according to claim 34, further comprising analysing a shape so that the identifying comprises identifying a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

36. A method according to claim 34, further comprising analysing a shape to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

37. A method according to claim 32, further comprising aligning at least portions of the captured image and reference image prior to said comparison.

38. A method according to claim 37, further comprising analysing a shape so that the identifying comprises identifying a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

39. A method according to claim 38, further comprising analysing a shape to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

40. A method according to claim 32, further comprising detecting said region indicative of a red-eye phenomenon by identifying a region in the captured image at least having a color indicative of a red-eye phenomenon and comparing said identified region with the corresponding region in the reference image, and designating said region as indicative of a red-eye phenomenon if said corresponding region does not have a color indicative of a red-eye phenomenon.

41. A method according to claim 40, further comprising deciding whether a region has a color indicative of a red-eye phenomenon by determining on a statistical basis as a global operation on the entire region.

42. A method according to claim 32, further comprising analysing a shape so that the identifying comprises identifying a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with the corresponding region in the reference image.

43. A method according to claim 32, further comprising analysing a shape to determine subsequent to said comparison whether a region designated as indicative of a red-eye phenomenon has a shape indicative of a red-eye phenomenon.

44. A method according to claim 32, wherein said digital image acquisition system is a digital camera.

45. A method according to claim 32, wherein said digital image acquisition system is a camera is a combination of a digital camera and an external processing device.

46. A method as claimed in claim 45, wherein said red-eye filter is located in said external processing device.

47. A method according to claim 32, further comprising modifying the color of the pixels within a region indicative of a red-eye phenomenon.

48. A method according to claim 31, further comprising analysing a shape, so that the identifying comprises identifying a region in the captured image having both a shape and color indicative of a red-eye phenomenon for subsequent comparison with a reference eye shape characteristic and the reference eye color characteristic, respectively.

49. A method according to claim 48, further comprising modifying the color of the pixels within a region indicative of a red-eye phenomenon.

50. A method according to claim 31, further comprising modifying the color of the pixels within a region indicative of a red-eye phenomenon.