Perfecting the effect of flash within an image acquisition devices using face detection

• US 7,702,136 B2
• Filed: 07/05/2007
• Issued: 04/20/2010
• 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, Bigioi, Petronel, Corcoran, Peter
• Primary Examiner(s): Seth; Manav
• Application Number:
  US11/773,815
• Publication Number:
  US 20080043122A1
• Time in Patent Office: 1,020 Days
• Field of Search: 382/103, 382115-118, 382/254, 382/274, 348/61, 348/68, 348 77- 78, 348/143, 348/152, 348/155, 348/158, 348/169, 348/207.99, 3482201-2291
• US Class Current: 382/118
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/72 Combination of two or more compensation controls
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means

Abstract

Within a digital acquisition device with a built in flash unit, the exposure of an acquired digital image is perfected using face detection in the acquired image is provided. Groups of pixels that correspond to plural images of faces are identified within a digitally acquired image, and corresponding image attributes to the group of pixels are determined. An analysis is performed of the corresponding attributes of the groups of pixels. It is then determined to activate the built-in flash unit based on the analysis. An intensity of the built-in flash unit is determined based on the analysis. Alternatively based on similar analysis, a digital simulation of the fill flash is performed on the image.

Claims

1. Within a digital camera, a method of digital image processing using face detection for achieving a desired image parameter, comprising:

identifying a group of pixels that correspond to a face in a foreground region within a digital image taken with flash;

determining first initial values of white point of pixels of the group of pixels;

determining second initial values of white point of pixels other than pixels of the group of pixels and located within a background region of the digital image;

comparing the first and second initial values, respectively, with a desired white point of pixels based on known flash characteristics and with one or more desired white points of background region pixels; and

determining adjusted values of white point separately for the foreground and background regions based on the comparing of the first and second initial values with a desired white point of pixels based on known flash characteristics and with a desired white point of pixels within said background region, and on a comparison of white points corresponding to the first and second initial values.

2. The method of claim 1, further comprising the step of automatically generating the adjusted digital image using the adjusted values.

3. The method of claim 1, further comprising automatically providing an option to generate the adjusted digital image using the adjusted values.

4. The method of claim 1, further comprising applying fill-flash to provide one or more of the adjusted values of white-point.

5. The method of claim 1, wherein one or more of the adjusted values of white point are provided by a digitally-simulated fill flash.

6. Within a digital camera, 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 digital image processing using face detection for achieving a desired image parameter, wherein the method comprises:

identifying a group of pixels that correspond to a face in a foreground region within a digital image taken with flash;

determining first initial values of white point of pixels of the group of pixels;

determining second initial values of white point of pixels other than pixels of the group of pixels and located within a background region of the digital image;

comparing the first and second initial values, respectively, with a desired white point of pixels based on known flash characteristics and with one or more desired white points of background region pixels; and

determining adjusted values of white point separately for the foreground and background regions based on the comparing of the first and second initial values with a desired white point of pixels based on known flash characteristics and with a desired white point of pixels within said background region, and on a comparison of white points corresponding to the first and second initial values.

7. The one or more storage devices of claim 6, wherein the method further comprises automatically generating the adjusted digital image using the adjusted values.

8. The one or more storage devices of claim 6, wherein the method further comprises automatically providing an option to generate the adjusted digital image using the adjusted values.

9. The one or more storage devices of claim 6, wherein the method further comprises applying fill-flash to provide one or more of the adjusted values of white point.

10. The one or more storage devices of claim 6, wherein one or more of the adjusted values of white point are provided by a digitally-simulated fill flash.

11. A digital image acquisition device, comprising:

a lens;

an image sensor;

a shutter;

a processor; and

one or more processor readable storage devices having processor readable code embodied thereon, said processor readable code for programming the processor to perform a method of digital image processing using face detection for achieving a desired image parameter, wherein the method comprises;

identifying a group of pixels that correspond to a face in a foreground region within a digital image taken with flash;

determining first initial values of white point of pixels of the group of pixels;

determining second initial values of white point of pixels other than pixels of the group of pixels and located within a background region of the digital image;

comparing the first and second initial values, respectively, with a desired white point of pixels based on known flash characteristics and with one or more desired white points of background region pixels; and

determining adjusted values of white point separately for the foreground and background regions based on the comparing of the first and second initial values with a desired white point of pixels based on known flash characteristics and with a desired white point of pixels within said background region, and on a comparison of white points corresponding to the first and second initial values.

12. The device of claim 11, wherein the method further comprises automatically generating the adjusted digital image using the adjusted values.

13. The device of claim 11, wherein the method further comprises automatically providing an option to generate the adjusted digital image using the adjusted values.

14. The device of claim 11, wherein the method further comprising applying fill-flash to provide one or more of the adjusted values of white point.

15. The device of claim 11, wherein one or more of the adjusted values of white point are provided by a digitally-simulated fill flash.