Digital Image Processing Using Face Detection and Skin Tone Information

• US 20070110305A1
• Filed: 10/30/2006
• Published: 05/17/2007
• Est. Priority Date: 06/26/2003
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: FotoNation Vision Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Bigioi, Petronel, Corcoran, Peter, Barcovschi, Igor
• Granted Patent: US 7,844,076 B2
• Time in Patent Office: Days
• US Class Current: 382/167
• CPC Class Codes: A61B 5/1176 Recognition of faces
• CPC Class Codes: G06F 16/784 the detected or recognised objects being people
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/635 Region indicators; Field of view indicators
• CPC Class Codes: H04N 23/675 comprising setting of focusing regions
• CPC Class Codes: H04N 23/695 Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof

Abstract

A technique for processing a digital image uses face detection to achieve one or more desired image processing parameters. A group of pixels is identified that corresponds to a face image within the digital image. A skin tone is detected for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels. Values of one or more parameters are adjusted for the group of pixels that correspond to the face image based on the detected skin tone.

Claims

1. A method of processing a digital image using face detection to achieve one or more desired image processing parameters, comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(c) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.

2. The method of claim 1, wherein the adjusting comprises applying fill-flash to the face image in an amount depending on the skin tone.

3. The method of claim 1, further comprising repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises applying fill-flash to the two face images in different relative amounts depending on the different skin tones.

4. The method of claim 1, wherein the adjusting comprises adjusting a luminance of the face image depending on the skin tone.

5. The method of claim 1, further comprising repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises adjusting luminance values of pixels of the two face images in different relative amounts depending on the different skin tones.

6. The method of claim 1, wherein the color or tonal values for the group of pixels comprise one or more average color or tonal values.

7. The method of claim 6, wherein the color or tonal values comprise multiple colors or tones, or combinations thereof, determined for each of multiple regions of the face image.

8. A method of processing a digital image using face detection to achieve one or more desired image processing parameters, comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a luminance of the face image by determining one or more default luminance values for the group of pixels; and

(c) providing fill-flash for the face image based on the detected luminance.

9. The method of claim 8, further comprising:

(d) identifying a second group of pixels that corresponds to a second face within the digital image;

(e) detecting a luminance of the second face image which differs from that of the first face image;

(f) providing fill-flash for the second face image which differs from that provided for the first face image.

10. The method of claim 9, wherein the corrected luminances of the two face images are closer to each other than their original luminances.

11. The method of claim 9, wherein the corrected luminances of the two face images are substantially equal to each other.

12. The method of claim 8, further comprising:

(d) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(e) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.

13. An image acquisition apparatus including an imaging optical system and digital image detector and storage medium, and having stored therein program instructions for programming one or more processors to perform a method of processing a digital image using face detection to achieve one or more desired image processing parameters, the method comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(c) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.

14. The apparatus of claim 13, wherein the adjusting comprises applying fill-flash to the face image in an amount depending on the skin tone.

15. The apparatus of claim 13, wherein the method further comprises repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises applying fill-flash to the two face images in different relative amounts depending on the different skin tones.

16. The apparatus of claim 13, wherein the adjusting comprises adjusting a luminance of the face image depending on the skin tone.

17. The apparatus of claim 13, wherein the method further comprises repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises adjusting luminance values of pixels of the two face images in different relative amounts depending on the different skin tones.

18. The apparatus of claim 13, wherein the color or tonal values for the group of pixels comprise one or more average color or tonal values.

19. The apparatus of claim 18, wherein the color or tonal values comprise multiple colors or tones, or combinations thereof, determined for each of multiple regions of the face image.

20. An image acquisition apparatus including an imaging optical system and digital image detector and storage medium, and having stored therein program instructions for programming one or more processors to perform a method of processing a digital image using face detection to achieve one or more desired image processing parameters, the method comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a luminance of the face image by determining one or more default luminance values for the group of pixels; and

(c) providing fill-flash for the face image based on the detected luminance.

21. The apparatus of claim 20, wherein the method further comprises:

(d) identifying a second group of pixels that corresponds to a second face within the digital image;

(e) detecting a luminance of the second face image which differs from that of the first face image;

(f) providing fill-flash for the second face image which differs from that provided for the first face image.

22. The apparatus of claim 21, wherein the corrected luminances of the two face images are closer to each other than their original luminances.

23. The apparatus of claim 21, wherein the corrected luminances of the two face images are substantially equal to each other.

24. The apparatus of claim 20, wherein the method further comprises:

(d) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(e) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.

25. One or more digital storage devices having embodied therein program instructions for programming one or more processors to perform a method of processing a digital image using face detection to achieve one or more desired image processing parameters, the method comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(c) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.

26. The one or more storage devices of claim 25, wherein the adjusting comprises applying fill-flash to the face image in an amount depending on the skin tone.

27. The one or more storage devices of claim 25, wherein the method further comprises repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises applying fill-flash to the two face images in different relative amounts depending on the different skin tones.

28. The one or more storage devices of claim 25, wherein the adjusting comprises adjusting a luminance of the face image depending on the skin tone.

29. The one or more storage devices of claim 25, wherein the method further comprises repeating the identifying, detecting and adjusting for a second face image having a different skin tone than the first face image, and the adjusting comprises adjusting luminance values of pixels of the two face images in different relative amounts depending on the different skin tones.

30. The one or more storage devices of claim 25, wherein the color or tonal values for the group of pixels comprise one or more average color or tonal values.

31. The one or more storage devices of claim 30, wherein the color or tonal values comprise multiple colors or tones, or combinations thereof, determined for each of multiple regions of the face image.

32. One or more digital storage devices having embedded therein program instructions for programming one or more processors to perform a method of processing a digital image using face detection to achieve one or more desired image processing parameters, the method comprising:

(a) identifying a group of pixels that correspond to a face image within the digital image;

(b) detecting a luminance of the face image by determining one or more default luminance values for the group of pixels; and

(c) providing fill-flash for the face image based on the detected luminance.

33. The one or more storage devices of claim 32, wherein the method further comprises:

(d) identifying a second group of pixels that corresponds to a second face within the digital image;

(e) detecting a luminance of the second face image which differs from that of the first face image;

(f) providing fill-flash for the second face image which differs from that provided for the first face image.

34. The one or more storage devices of claim 33, wherein the corrected luminances of the two face images are closer to each other than their original luminances.

35. The one or more storage devices of claim 33, wherein the corrected luminances of the two face images are substantially equal to each other.

36. The one or more storage devices of claim 32, wherein the method further comprises:

(d) detecting a skin tone for the face image by determining one or more default color or tonal values, or combinations thereof, for the group of pixels; and

(e) adjusting values of one or more parameters for the group of pixels that correspond to the face image based on the detected skin tone.