Method and apparatus for red-eye detection in an acquired digital image

• US 7,953,250 B2
• Filed: 08/18/2009
• Issued: 05/31/2011
• Est. Priority Date: 10/28/2004
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: Tessera Technologies Ireland Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Nanu, Florin, Bigioi, Petronel
• Primary Examiner(s): Do; Anh Hong
• Application Number:
  US12/543,405
• Publication Number:
  US 20090304278A1
• Time in Patent Office: 651 Days
• Field of Search: 382/117, 382/118, 382/167, 382/103, 382/164, 382/299, 382/165, 382/284, 348/239, 348/246
• US Class Current: 382/117
• CPC Class Codes: G06T 2207/20008 Globally adaptive
• 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: G06V 40/193 Preprocessing; Feature extraction

Abstract

A method for red-eye detection in an acquired digital image comprises acquiring a first image and analyzing the first acquired image to provide a plurality of characteristics indicative of image quality. The process then determines if one or more corrective processes can be beneficially applied to the first acquired image according to the characteristics. Any such corrective processes are then applied to the first acquired image. Red-eye defects are then detected in a second acquired image using the corrected first acquired image. Defect detection can comprise applying a chain of one or more red-eye filters to the first acquired image. In this case, prior to the detecting step, it is determined if the red-eye filter chain can be adapted in accordance with the plurality of characteristics; and the red-eye filter is adapted accordingly.

Claims

1. One or more processor-readable storage media having embedded therein processor-readable code for programming a processor to perform a method of detecting one or more flash-induced eye defects in an acquired digital image, wherein the method comprises:

a) acquiring a first image;

b) analyzing the first acquired image to detect one or more image acquisition conditions of the image;

c) determining if a chain of one or more defect filters can be adapted in accordance with said one or more image acquisition conditions;

d) adapting said defect filter chain; and

e) applying said filter chain to detect one or more flash-induced eye defects in a second acquired image.

2. The one or more processor-readable storage media of claim 1, wherein the method further comprises:

f) determining if one or more corrective processes can be beneficially applied to said first acquired image according to said one or more conditions; and

g) applying one or more of such corrective processes to said first acquired image.

3. The one or more processor-readable storage media of claim 2, wherein said corrective processes comprise one or more of:

(i) contrast normalization and image sharpening;

(ii) image color adjustment and tone scaling;

(iii) exposure adjustment and digital fill flash;

(iv) brightness adjustment with color space matching;

(v) image auto-gamma determination with image enhancement;

(v) image enhancement; and

(vi) face based image enhancement.

4. The one or more processor-readable storage media of claim 2, wherein the method further comprises, responsive to determining that corrective processing is necessary but cannot be beneficially applied to said first acquired image according to said one or more conditions, disabling the corrective processing and providing an indication of such to a user.

5. The one or more processor-readable storage media of claim 2, wherein the applying a corrective process includes performing a color or luminance space transformation, or both.

6. The one or more processor-readable storage media of claim 2, wherein the method further comprises determining a sequence in which more than one corrective process can be beneficially applied to said first acquired image according to said one or more conditions.

7. The one or more processor-readable storage media of claim 1, in which said adapting comprises providing an altered set of parameters for one or more filters of said filter chain.

8. The one or more processor-readable storage media of claim 1, in which said adapting comprises re-ordering a sequence in which said filters are applied to said first acquired image.

9. The one or more processor-readable storage media of claim 1, in which said adapting comprises determining which filters are to be applied in said chain.

10. The one or more processor-readable storage media of claim 1, wherein said analyzing comprises recognizing one or more faces in the first acquired image.

11. The one or more processor-readable storage media of claim 1, wherein said filter chain comprises:

(i) a pixel locator and segmentor;

(ii) a shape analyser;

(iii) a falsing analyser; and

(iv) a pixel modifier.

12. The one or more processor-readable storage media of claim 11, wherein said pixel locator and segmentor includes a pixel transformer.

13. The one or more processor-readable storage media of claim 1, wherein the analyzing comprises recognizing one or more types of faces in the first acquired image.

14. The one or more processor-readable storage media of claim 13, wherein the method further comprises recognizing a same type of face in a second acquired image as in said first acquired image, and applying one or more same corrective processes to said second image as said first image.

15. A digital image acquisition and processing device comprising a lens, an image sensor, a processor and a processor-readable storage medium having embedded therein processor-readable code for programming the processor to perform a method for detecting flash-induced eye defects in an acquired digital image, wherein the method comprises:

a) acquiring a first image;

b) analyzing the first acquired image to detect one or more image acquisition conditions of the image;

c) determining if a chain of one or more defect filters can be adapted in accordance with said one or more image acquisition conditions;

d) adapting said defect filter chain; and

e) applying said filter chain to detect a flash-induced eye defect in a second acquired image.

16. The device of claim 15, wherein the method further comprises:

f) determining if one or more corrective processes can be beneficially applied to said first acquired image according to said one or more conditions; and

g) applying one or more of such corrective processes to said first acquired image.

17. The device of claim 16, wherein said corrective processes comprise one or more of:

(i) contrast normalization and image sharpening;

(ii) image color adjustment and tone scaling;

(iii) exposure adjustment and digital fill flash;

(iv) brightness adjustment with color space matching;

(v) image auto-gamma determination with image enhancement;

(v) image enhancement; and

(vi) face based image enhancement.

18. The device of claim 16, wherein the method further comprises, responsive to determining that corrective processing is necessary but cannot be beneficially applied to said first acquired image according to said one or more conditions, disabling the corrective processing and providing an indication of such to a user.

19. The device of claim 16, wherein the applying a corrective process includes performing a color or luminance space transformation, or both.

20. The device of claim 16, wherein the method further comprises determining a sequence in which more than one corrective process can be beneficially applied to said first acquired image according to said one or more conditions.

21. The device of claim 15, in which said adapting comprises providing an altered set of parameters for one or more filters of said filter chain.

22. The device of claim 15, in which said adapting comprises re-ordering a sequence in which said filters are applied to said first acquired image.

23. The device of claim 15, in which said adapting comprises determining which filters are to be applied in said chain.

24. The device of claim 15, wherein said analyzing comprises recognizing one or more faces in the first acquired image.

25. The device of claim 15, wherein said filter chain comprises:

(i) a pixel locator and segmentor;

(ii) a shape analyzer;

(iii) a falsing analyzer; and

(iv) a pixel modifier.

26. The device of claim 25, wherein said pixel locator and segmentor includes a pixel transformer.

27. The device of claim 15, wherein the analyzing comprises recognizing one or more types of faces in the first acquired image.

28. The device of claim 27, wherein the method further comprises recognizing a same type of face in a second acquired image as in said first acquired image, and applying one or more same corrective processes to said second image as said first image.

29. A method of detecting flash-induced eye defects in an acquired digital image, wherein the method comprises using a processor in:

a) acquiring a first image;

b) analyzing the first acquired image to detect one or more image acquisition conditions of the image;

c) determining if a chain of one or more defect filters can be adapted in accordance with said one or more image acquisition conditions;

d) adapting said defect filter chain; and

e) applying said filter chain to detect a flash-induced eye defect in a second acquired image.

30. The method device of claim 29, further comprising:

f) determining if one or more corrective processes can be beneficially applied to said first acquired image according to said one or more conditions; and

g) applying one or more of such corrective processes to said first acquired image.

31. The method of claim 30, further comprising, responsive to determining that corrective processing is necessary but cannot be beneficially applied to said first acquired image according to said one or more conditions, disabling the corrective processing and providing an indication of such to a user.

32. The method of claim 30, wherein the applying one or more corrective processes includes performing a color or luminance space transformation, or both.

33. The method of claim 30, wherein the method further comprises determining a sequence in which more than one corrective process can be beneficially applied to said first acquired image according to said one or more conditions.

34. The method of claim 29, wherein said adapting comprises providing an altered set of parameters for one or more filters of said filter chain.

35. The method of claim 29, wherein said adapting comprises re-ordering a sequence in which said filters are applied to said first acquired image.

36. The method of claim 29, wherein said adapting comprises determining which filters are to be applied in said chain.