DETECTING ORIENTATION OF DIGITAL IMAGES USING FACE DETECTION INFORMATION

• US 20090245693A1
• Filed: 06/10/2009
• Published: 10/01/2009
• Est. Priority Date: 06/26/2003
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: FotoNation Ireland Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Gangea, Mihnea, Bigioi, Petronel, Corcoran, Peter, Vertan, Constantin, Blonk, Leo
• Granted Patent: US 7,844,135 B2
• Time in Patent Office: Days
• US Class Current: 382/296
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.

Claims

1. A method of detecting an orientation of a digital image using statistical classifier techniques comprising using a processor in performing the following:

(a) acquiring a digital image;

(b) cropping the digital image including selecting a facial region within the digital image excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying a set of face detection classifiers to the cropped image in a first orientation and determining a first level of match between said cropped image at said first orientation and said classifiers;

(d) rotating said cropped image to a second orientation to obtain a rotated image, applying the classifiers to said rotated image at said second orientation, and determining a second level of match between said rotated image at said second orientation and said classifiers;

(e) comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; and

(f) determining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match.

2. The method of claim 1, further comprising, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

3. The method of claim 1, wherein said classifiers comprise elliptical classifiers.

4. The method of claim 3, wherein said elliptical classifiers are oriented at known orientations.

5. The method of claim 1, wherein said classifiers correspond to regions of a detected face.

6. The method of claim 5, wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.

12. The method of claim 1 wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.

7. A method of detecting an orientation of a digital image using statistical classifier techniques comprising:

(a) acquiring a digital image;

(b) cropping the digital image including selecting a facial region within the digital region excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying a set of face detection classifiers to the cropped image in a first orientation and determining a first level of match between said cropped image at said first orientation and said classifiers;

(d) rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;

(d) comparing said first and second levels of match between said classifiers and said digital image and between said rotated classifiers and said cropped image, respectively; and

(e) determining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image.

8. The method of claim 7, further comprising, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

9. The method of claim 7, wherein said classifiers comprise elliptical classifiers.

10. The method of claim 9, wherein said elliptical classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations.

11. The method of claim 7, wherein said classifiers correspond to regions of a detected face.

13. One or more processor readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of a digital image using statistical classifier techniques, the method comprising:

(a) applying a set of face detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;

(b) cropping the digital image including selecting a facial region within the digital image excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;

(c) rotating said cropped image to a second orientation, applying the classifiers to the rotated image at said second orientation, and determining a second level of match between the rotated image at said second orientation and said classifiers;

(d) comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; and

(e) determining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match.

14. The one or more storage devices of claim 13, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

15. The one or more storage devices of claim 13, wherein said classifiers comprise elliptical classifiers.

16. The one or more storage devices of claim 15, wherein said elliptical classifiers are oriented at known orientations.

17. The one or more storage devices of claim 13, wherein said classifiers correspond to regions of a detected face.

18. The one or more storage devices of claim 17, wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.

19. One or more processor readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of a digital image using statistical classifier techniques, the method comprising:

(a) applying a set of face detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;

(b) cropping the digital image including selecting a facial region within the digital image excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;

(c) rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;

(d) comparing said first and second levels of match between said classifiers and said cropped image and between said rotated classifiers and said cropped image, respectively; and

(e) determining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image.

20. The one or more storage devices of claim 19, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

21. The one or more storage devices of claim 19, wherein said classifiers comprise elliptical classifiers.

22. The one or more storage devices of claim 21, wherein said elliptical classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations.

23. The one or more storage devices of claim 19, wherein said classifiers correspond to regions of a detected face.

24. The one or more storage devices of claim 23, wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.

25. A portable digital camera, comprising one or more optics and a sensor for acquiring a digital image, a processor, and one or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of a digital image using statistical classifier techniques, wherein the method comprises:

(a) applying a set of face detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;

(b) cropping the digital image including selecting a facial region within the digital image excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;

(c) rotating said cropped image to a second orientation, applying the classifiers to the rotated image at said second orientation, and determining a second level of match between the rotated image at said second orientation and said classifiers;

(d) comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; and

(e) determining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match.

26. The camera of claim 25, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

27. The camera of claim 25, wherein said classifiers comprise elliptical classifiers.

28. The camera of claim 27, wherein said elliptical classifiers are oriented at known orientations.

29. The camera of claim 25, wherein said classifiers correspond to regions of a detected face.

30. The camera of claim 29, wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.

31. A portable digital camera, comprising one or more optics and a sensor for acquiring a digital image, a processor, and one or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of a digital image using statistical classifier techniques, wherein the method comprises:

(a) applying a set of face detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;

(b) cropping the digital image including selecting a facial region within the digital image excluding one or more regions of the digital image outside of said facial region to obtain a cropped image including said facial region;

(c) applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;

(c) rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;

(d) comparing said first and second levels of match between said classifiers and said cropped image and between said rotated classifiers and said cropped image, respectively; and

(e) determining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image.

32. The camera of claim 31, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof.

33. The camera of claim 31, wherein said classifiers comprise elliptical classifiers.

34. The camera of claim 33, wherein said elliptical classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations.

35. The camera of claim 31, wherein said classifiers correspond to regions of a detected face.

36. The camera of claim 35, wherein said regions include an eye, two eyes, a nose, a mouth, or an entire face, or combinations thereof.