IP Library Granted Patent US 8,334,926
Granted Patent B2
US 8,334,926 · App. 13/164,685 · Granted Dec 18, 2012

In-camera based method of detecting defect eye with high accuracy

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,334,926
App. No.
13/164,685
Granted
Dec 18, 2012
Kind
B2
Abstract

A portable digital image acquisition device includes multiple lenses and/or multiple flashes. A main digital image and first and second reference images are acquired. The first and second reference images are acquired with different flash-lens combinations that have different flash-lens distances. One or more flash eye defects are detected and corrected in the main image based on analysis of the first and second reference images.

Claims (53)

1. A portable digital image acquisition device, comprising:

(a) first and second lenses and at least one sensor for acquiring a main digital image and first and second reference images;

(b) a light source disposed at different distances from the first and second lenses for illuminating one or more objects within an acquired scene;

(c) a memory for storing the main digital image;

(d) one or more processor-readable media having digital code embedded therein for programming a processor to perform a method of determining and correcting a flash eye defect in the main digital image using the first and second reference images, wherein the method comprises:

(i) acquiring the first and second reference images using the light source and the first and second lenses respectively;

(ii) normalizing the first and second images to generate normalized first and second reference images;

(iii) analyzing one or more differences between the first and second normalized reference images;

(iv) determining and correcting the flash eye defect within the main image based on the analyzing to generate a corrected main image; and

(v) storing, transmitting, communicating, displaying, or projecting the corrected main image or a further processed version, or combinations thereof.

2. The device of claim 1 , wherein the analyzing comprises subtracting the first and second reference images.

3. The device of claim 1 , wherein the normalizing comprises luminance normalizing.

4. The device of claim 1 , wherein the flash eye defect comprises a red eye defect.

5. The device of claim 1 , wherein the normalizing comprises re-sizing one or both of the first and second reference images.

6. The device of claim 1 , wherein the normalizing comprises aligning the first and second reference images.

7. The device of claim 6 , wherein the aligning comprises aligning one or more eyes within the first and second images.

8. The device of claim 1 , wherein the differences comprise color differences.

9. The device of claim 1 , wherein the differences comprise brightness differences.

10. The device of claim 1 , wherein the first and second reference images are each acquired using relatively low-intensity pre-flashes compared with an intensity of a flash used in acquiring the main digital image.

11. The device of claim 1 , wherein the analyzing takes into account the specific different distances from the first and second lenses of the light source.

12. The device of claim 11 , wherein the analyzing further takes into account distance to one or more objects, a gaze angle, an ambient lighting condition, color of an iris or a skin tone of a face within the acquired scene, or combinations thereof.

13. The device of claim 1 , wherein the first and second preview images are acquired consecutively prior to acquiring the main digital image.

14. A method of determining and correcting a flash eye defect in a main digital image using first and second reference images, wherein the method comprises using a processor-based digital image acquisition device to perform the following: (i) acquiring first and second reference images using a light source and first and second lenses respectively disposed different distances from the light source; (ii) normalizing the first and second images to generate normalized first and second reference images; (iii) analyzing one or more differences between the first and second normalized reference images; (iv) determining and correcting a flash eye defect within the main image based on the analyzing to generate a corrected main image; (v) storing, transmitting, communicating, displaying, or projecting the corrected main image or a further processed version, or combinations thereof.

15. The method of claim 14 , wherein the analyzing comprises subtracting the first and second reference images.

16. The method of claim 14 , wherein the normalizing comprises luminance normalizing.

17. The method of claim 14 , wherein the flash eye defect comprises a red eye defect.

18. The method of claim 14 , wherein the normalizing comprises re-sizing one or both of the first and second reference images.

19. The method of claim 14 , wherein the normalizing comprises aligning the first and second reference images.

20. The method of claim 19 , wherein the aligning comprises aligning one or more eyes within the first and second images.

21. The method of claim 14 , wherein the differences comprise color differences.

22. The method of claim 14 , wherein the differences comprise brightness differences.

23. The method of claim 14 , wherein the first and second reference images are each acquired using relatively low-intensity pre-flashes compared with an intensity of a flash used in acquiring the main digital image.

24. The method of claim 14 , wherein the analyzing takes into account the specific different distances from the first and second lenses of the light source.

25. The method of claim 24 , wherein the analyzing further takes into account distance to one or more objects, a gaze angle, an ambient lighting condition, color of an iris or a skin tone of a face within the acquired scene, or combinations thereof.

26. The method of claim 14 , wherein the first and second preview images are acquired consecutively prior to acquiring the main digital image.

27. One or more non-transitory processor-readable media having digital code embedded therein for programming a processor to perform a method of determining and correcting a flash eye defect in a main digital image using first and second reference images, wherein the method comprises:

(i) acquiring the first and second reference images using a light source and first and second lenses respectively disposed at different distances from the light source;

(ii) normalizing the first and second images to generate normalized first and second reference images;

(iii) analyzing one or more differences between the first and second normalized reference images;

(iv) determining and correcting a flash eye defect within the main image based on the analyzing to generate a corrected main image; and

(v) storing, transmitting, communicating, displaying, or projecting the corrected main image or a further processed version, or combinations thereof.

28. The one or more media of claim 27 , wherein the analyzing comprises subtracting the first and second reference images.

29. The one or more media of claim 27 , wherein the normalizing comprises luminance normalizing.

30. The one or more media of claim 27 , wherein the flash eye defect comprises a red eye defect.

31. The one or more media of claim 27 , wherein the normalizing comprises re-sizing one or both of the first and second reference images.

32. The one or more media of claim 27 , wherein the normalizing comprises aligning the first and second reference images.

33. The one or more media of claim 32 , wherein the aligning comprises aligning one or more eyes within the first and second images.

34. The one or more media of claim 27 , wherein the differences comprise color differences.

35. The one or more media of claim 27 , wherein the differences comprise brightness differences.

36. The one or more media of claim 27 , wherein the first and second reference images are each acquired using relatively low-intensity pre-flashes compared with an intensity of a flash used in acquiring the main digital image.

37. The one or more media of claim 27 , wherein the analyzing takes into account the specific different distances from the first and second lenses of the light source.

38. The one or more media of claim 37 , wherein the analyzing further takes into account distance to one or more objects, a gaze angle, an ambient lighting condition, color of an iris or a skin tone of a face within the acquired scene, or combinations thereof.

39. The one or more media of claim 27 , wherein the first and second preview images are acquired consecutively prior to acquiring the main digital image.