Method and apparatus for effecting automatic red eye reduction

• US 20060017825A1
• Filed: 06/30/2004
• Published: 01/26/2006
• Est. Priority Date: 06/30/2004
• Status: Active Grant

• Current Assignee: John V. Pezdek
• Original Assignee: John V. Pezdek
• Inventors: Thakur, Khageshwar
• Granted Patent: US 7,627,146 B2
• Time in Patent Office: Days
• US Class Current: 348/242
• CPC Class Codes: G06T 2207/20041 Distance transform
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/005 Retouching; Inpainting; Scratch removal detecting, correction, reducing or removing defects, e.g. non-responsive pixels of solid state image sensors H04N25/68, scratch removal for cinematographic films scanned by electronic image sensor H04N5/253
• CPC Class Codes: G06T 5/008 Local, e.g. shadow enhancement
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611

Abstract

A method, and an apparatus employing the method, of reducing red eye effect from image data having image attributes. In some embodiments, the method includes identifying image data with a first image attribute having characteristics of skin pixels, determining a shape of the identified image data having the first image attribute, mapping other image attributes within the determined shape, and determining a red eye presence from the other mapped image attributes.

Claims

1. A method of reducing red eye effect from image data having image attributes, the method comprising:

identifying image data with a first image attribute having a characteristic of skin pixels;

determining a shape of the identified image data having the first image attribute;

mapping at least one other image attribute within the determined shape; and

determining a red eye presence from at least one other mapped image attribute.

2. The method of claim 1, wherein the first image attribute comprises at least one of a luminance, RGB triplets, Lab, and HSV.

3. The method of claim 1, further comprising determining if the first image attribute is inside a first image attribute boundary.

4. The method of claim 1, wherein identifying the image data with the first image attribute further comprises determining an elliptical area of the image data.

5. The method of claim 1, wherein determining the shape further comprises determining if the identified image data is connected.

6. The method of claim 5, further comprising comparing a number of the connected image data with a threshold.

7. The method of claim 5, wherein determining the shape further comprises solidifying the connected image data in the shape.

8. The method of claim 1, wherein the shape comprises a rectangle.

9. The method of claim 1, wherein mapping image attributes further comprises determining a distance map between the image data and data having a neutral color.

10. The method of claim 9, further comprising equalizing the distance map.

11. The method of claim 9, further comprising comparing values of the distance map with a distance threshold.

12. The method of claim 1, wherein mapping image attributes further comprises determining a red eye map of the image data.

13. The method of claim 1, further comprising opening the image data in the shape.

14. The method of claim 1, wherein mapping image attributes further comprises determining a contrast map of the image data having characteristics of skin pixels.

15. A method of reducing red eye effect from image data having image attributes, the method comprising:

comparing the image pixel data with data from a skin tone database;

identifying the image pixel data based upon a match between the image pixel data and the data from the skin tone database;

determining a shape of the identified image pixels;

locating at least one pixel having an image attribute in the determined shape;

comparing data of the located pixels with data from a plurality of red eye maps; and

locating a red eye based on a match between the image data of the located pixels and the data from the red eye maps.

16. The method of claim 15, wherein the data from the skin tone database comprises at least one of a luminance, RGB triplets, Lab, and HSV.

17. The method of claim 15, wherein identifying the image pixel data further comprises determining an elliptical area of the image data.

18. The method of claim 15, wherein determining the shape further comprises determining if the identified image pixel data is connected.

19. The method of claim 18, further comprising comparing a number of the connected image data with a threshold.

20. The method of claim 18, wherein determining the shape further comprises solidifying the connected image data in the shape.

21. The method of claim 15, wherein the shape comprises a rectangle.

22. The method of claim 15, further comprising determining a distance map between the image pixel data and data having a neutral color.

23. The method of claim 22, further comprising equalizing the distance map.

24. The method of claim 22, further comprising comparing values of the distance map with a distance threshold.

25. The method of claim 15, further comprising opening the image data in the shape.

26. The method of claim 15, further comprising determining a contrast map of the image pixel data having characteristics of skin tones.

27. A red eye reduction system adapted to reduce an red eye effect of an image, the system comprising:

a skin tone identifier configured to identify image data with a first image attribute having characteristics of skin pixels;

a shape identifier coupled to the skin tone identifier, and configured to determine a shape of the identified image pixel data having characteristics of the skin pixels;

a mapping module coupled to the shape identifier, and configured to map other image attributes within the determined shape; and

a red eye detector coupled to the mapping module, and configured to determine a red eye presence from the mapped image attributes.

28. The system of claim 27, wherein the first image attribute comprises at least one of a luminance, RGB triplets, Lab, and HSV.

29. The system of claim 27, wherein the skin tone identifier determines if the first image attribute is inside a first image attribute boundary.

30. The system of claim 27, wherein the skin tone identifier determines an elliptical area of the image data.

31. The system of claim 27, wherein skin tone identifier determines if the identified image data is connected.

32. The system of claim 31, wherein the skin tone identifier compares a number of the connected image data with a threshold.

33. The system of claim 31, wherein the skin tone identifier solidifies the connected image data in the shape.

34. The system of claim 27, wherein the shape comprises a rectangle.

35. The system of claim 27, wherein the mapping module further comprises a distance mapping module configured to determine a distance map between the image data and data having a neutral color.

36. The system of claim 35, further comprising an equalizer configured to equalize the distance map.

37. The system of claim 35, wherein the mapping module compares values of the distance map with a distance threshold.

38. The system of claim 27, wherein the mapping module further comprises a red eye mapping module configured to map a plurality of red eye pixels of the image data.

39. The system of claim 27, further comprising opening the image data in the shape.

40. The system of claim 27, wherein the mapping module further comprises a contrast mapping module configured to determine a contrast map of the image data having characteristics of skin pixels.

41. An apparatus comprising:

skin tone identifying software configured to identify image data with a first image attribute having characteristics of skin pixels;

shape identifying software configured to determine a shape of the identified image pixel data having characteristics of the skin pixels;

mapping software configured to map other image attributes within the determined shape; and

red eye detecting software configured to determine a red eye presence from the mapped image attributes.

42. The apparatus of claim 41, wherein the first image attribute comprises at least one of a luminance, RGB triplets, Lab, and HSV.

43. The apparatus of claim 41, wherein the skin tone identifying software determines if the first image attribute is inside a first image attribute boundary.

44. The apparatus of claim 41, wherein the skin tone identifying software determines an elliptical area of the image data.

45. The apparatus of claim 41, wherein skin tone identifying software determines if the identified image data is connected.

46. The apparatus of claim 45, wherein the skin tone identifying software compares a number of the connected image data with a threshold.

47. The apparatus of claim 45, wherein the skin tone identifying software solidifies the connected image data in the shape.

48. The apparatus of claim 41, wherein the shape comprises a rectangle.

49. The apparatus of claim 41, wherein the mapping software further comprises a distance mapping software configured to determine a distance map between the image data and data having a neutral color.

50. The apparatus of claim 49, further comprising an equalizing software configured to equalize the distance map.

51. The apparatus of claim 49, wherein the mapping software compares values of the distance map with a distance threshold.

52. The apparatus of claim 41, wherein the mapping software further comprises a red eye mapping software configured to map a plurality of red eye pixels of the image data.

53. The apparatus of claim 41, further comprising an opening software configured to open the image data in the shape.

54. The apparatus of claim 41, wherein the mapping software further comprises a contrast mapping software configured to determine a contrast map of the image data having characteristics of skin pixels.

55. The apparatus of claim 41, further comprising at least one of a digital camera, a video camera, a computer, and a printer.