Illumination detection using classifier chains

• US 8,503,800 B2
• Filed: 02/27/2008
• Issued: 08/06/2013
• Est. Priority Date: 03/05/2007
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Blonk, Leendert, Gangea, Mihnea, Corcoran, Peter
• Primary Examiner(s): Bhatnagar, Anand
• Assistant Examiner(s): PARK, SOO JIN
• Application Number:
  US12/038,777
• Publication Number:
  US 20080219517A1
• Time in Patent Office: 1,987 Days
• Field of Search: 382/224, 382/227, 382/274, 382/226
• US Class Current: 382/226
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images

Abstract

A face illumination normalization method includes acquiring a digital image including a face that appears to be illuminated unevenly. One or more uneven illumination classifier programs are applied to the face data to determine the presence of the face within the digital image and/or the uneven illumination condition of the face. The uneven illumination condition may be corrected to thereby generate a corrected face image appearing to have more uniform illumination, for example, to enhance face recognition.

Claims

1. A face illumination normalization method, comprising:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination cascaded classifier chains to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination cascaded classifier chains;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.

2. The method of claim 1, further comprising applying a face recognition program to the corrected face image.

3. The method of claim 1, wherein said cascaded classifier chains comprise branched classifier chains configured such that the identifying of the face data and the determining of the uneven illumination condition of the face are performed simultaneously.

4. The method of claim 1, further comprising applying a set of feature detector programs to reject non-face data from being identified as face data.

5. The method of claim 1, further comprising applying a front illumination cascaded classifier chain to the face data.

6. The method of claim 5, further comprising determining an illumination condition based on acceptance of the face data by one of the cascaded classifier chains.

7. The method of claim 6, wherein the digital image is one of multiple images in a series that include said face, and wherein said correcting is applied to a different image in the series than said digital image within which the illuminating condition is determined.

8. The method of claim 1, wherein said uneven illumination cascaded classifier chain comprise a top illumination cascaded classifier chain, a bottom illumination cascaded classifier chain, and one or both of right and left illumination cascaded classifier chains.

9. The method of claim 8, further comprising applying a front illumination cascaded classifier chain to the face data.

10. A face illumination normalization method, comprising:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination classifier programs to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination classifier programs;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.

11. A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a face illumination normalization method, wherein the method comprises:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination cascaded classifier chains to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination cascaded classifier chains;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.

12. The device of claim 11, wherein the method further comprises applying a face recognition program to the corrected face image.

13. The device of claim 11, wherein said cascaded classifier chains comprise branched classifier chains configured such that the identifying of the face data and the determining of the uneven illumination condition of the face are performed simultaneously.

14. The device of claim 11, wherein the method further comprises applying a set of feature detector programs to reject non-face data from being identified as face data.

15. The device of claim 11, wherein the method further comprises applying a front illumination cascaded classifier chain to the face data.

16. The device of claim 15, wherein the method further comprises determining an illumination condition based on acceptance of the face data by one of the cascaded classifier chains.

17. The device of claim 16, wherein the digital image is one of multiple images in a series that include said face, and wherein said correcting is applied to a different image in the series than said digital image within which the illuminating condition is determined.

18. The device of claim 11, wherein said uneven illumination cascaded classifier chain comprise a top illumination cascaded classifier chain, a bottom illumination cascaded classifier chain, and one or both of right and left illumination cascaded classifier chains.

19. The device of claim 18, wherein the method further comprises applying a front illumination cascaded classifier chain to the face data.

20. A digital image acquisition device including an optoelectonic system for acquiring a digital image, and a digital memory having stored therein processor-readable code for programming the processor to perform a face illumination normalization method, wherein the method comprises:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination classifier programs to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination classifier programs;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.

21. A non-transitory computer readable memory having stored therein processor-readable code for programming a processor to perform a face illumination normalization method, wherein the method comprises:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination cascaded classifier chains to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination cascaded classifier chains;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.

22. The digital memory of claim 21, wherein the method further comprises applying a face recognition program to the corrected face image.

23. The digital memory of claim 21, wherein said cascaded classifier chains comprise branched classifier chains configured such that the identifying of the face data and the determining of the uneven illumination condition of the face are performed simultaneously.

24. The digital memory of claim 21, wherein the method further comprises applying a set of feature detector programs to reject non-face data from being identified as face data.

25. The digital memory of claim 21, wherein the method further comprises applying a front illumination cascaded classifier chain to the face data.

26. The digital memory of claim 25, wherein the method further comprises determining an illumination condition based on acceptance of the face data by one of the cascaded classifier chains.

27. The digital memory of claim 26, wherein the digital image is one of multiple images in a series that include said face, and wherein said correcting is applied to a different image in the series than said digital image within which the illuminating condition is determined.

28. The digital memory of claim 21, wherein said uneven illumination cascaded classifier chain comprise a top illumination cascaded classifier chain, a bottom illumination cascaded classifier chain, and one or both of right and left illumination cascaded classifier chains.

29. The digital memory of claim 28, wherein the method further comprises applying a front illumination cascaded classifier chain to the face data.

30. A non-transitory computer readable memory having stored therein processor-readable code for programming a processor to perform a face illumination normalization method, wherein the method comprises:

(a) acquiring a digital image including data corresponding to a face that appears to be illuminated unevenly;

(b) applying one or more uneven illumination classifier programs to the face data;

(c) identifying the face data as corresponding to said face within the digital image;

(d) determining an uneven illumination condition for the face also as a result of the applying of the one or more uneven illumination classifier programs;

(e) correcting the uneven illumination condition of the face based on the determining to thereby generate a corrected face image appearing to have more uniform illumination; and

(f) electronically storing, transmitting, applying a face recognition program to, editing, or displaying the corrected face image, or combinations thereof,

(g) wherein the applying comprises applying at least two full classifier sets after determining that no single illumination condition applies and that the face data is not rejected as a face.