PERFECTING THE OPTICS WITHIN A DIGITAL IMAGE ACQUISITION DEVICE USING FACE DETECTION

• US 20080143854A1
• Filed: 11/18/2007
• Published: 06/19/2008
• Est. Priority Date: 06/26/2003
• Status: Abandoned Application

• Current Assignee: Tessera Technologies Ireland Limited (Adeia Inc.)
• Original Assignee: FotoNation Vision Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Corcoran, Peter
• Application Number:
  US11/941,956
• Publication Number:
  US 20080143854A1
• Time in Patent Office: Days
• US Class Current: 348/239
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/73 by influencing the exposure time

Abstract

Within a digital acquisition device, acquisition parameters of a digital image are perfected as part of an image capture process using face detection within the captured image to achieve one or more desired image acquisition parameters. Default values are determined of one or more image attributes of at least some portion of the digital image. Values of one or more camera acquisition parameters are determined. Groups of pixels are identified that correspond to an image of a face within the digitally-captured image. Corresponding image attributes to the groups of pixels are determined. One or more default image attribute values are compared with one or more captured image attribute values based upon analysis of the image of the face. Camera acquisition parameters are then adjusted corresponding to adjusting the image attribute values.

Claims

1. Within a digital acquisition device with an adjustable optical system having an auto focusing mechanism, a method of perfecting the auto focus mechanism of the adjustable optical system as part of an image capture process using face detection in the image capture process to achieve one or more desired image acquisition parameters, comprising:

identifying a plurality of groups of pixels including an image of a face within a digitally-captured image;

and determining image attributes corresponding to the group of pixels, the identifying of the pixels performed using one or more parameters including a size of the faces and a relative exposure of the faces.

2. The method of claim 1, further comprising an initial step of performing the auto focus on the entire the image.

3. The method of claim 1, wherein the auto focusing mechanism and the method of perfecting the auto focus mechanism automatically adjust one or more properties of the adjustable optical system.

4. The method of claim 1, further comprising a user manually activating the camera to perform the perfecting the auto focus.

5. The method of claim 1, the face pixels identifying step being automatically performed by an image processing apparatus, the method further comprising manually removing one or more of the plurality of groups of pixels detected as faces.

6. A method of manually removing one or more detected faces as recited in claim 5, the method being performed in response to false detection of one or more regions as one or more faces.

7. A method of manually removing one or more detected faces as recited in claim 5, the method being performed in response to a determination to concentrate on less of the image faces than faces identified in the identifying.

8. A method of manually removing one or more detected faces as recited in claim 5, the method being performed by increasing a sensitivity level of the face identifying.

9. A method of manually removing one or more detected faces as recited in claim 5, the method being performed by an interactive visual method.

10. An interactive visual method for manually removing one or more detected faces as recited in claim 9, the method being performed using an image acquisition built-in display.

11. A method of perfecting the auto focus mechanism as recited in claim 1, wherein performing the auto focus on the plurality of groups includes calculating a weighted average on the individual objects of the groups.

12. The method of claim 1, the identifying of face pixels being automatically performed by an image processing apparatus which receives a relative value as to detection assurance.

13. A method of perfecting the auto focus mechanism as recited in claim 12, the calculating a weighted average being done based on the relative values as to the detection assurance.

14. The method of claim 1, the face pixels identifying step being automatically performed by an image processing apparatus which receives a relative value as to an estimated importance of the detected regions.

15. A digital image acquisition device with an adjustable optical system having an auto focusing mechanism, at least one processor coupled to a corresponding digital storage device having stored thereon instruction which when executed by the processor cause the processor to perform a method, the method comprising:

identifying a plurality of groups of pixels including an image of a face within a digitally-captured image; and

determining image attributes corresponding to the group of pixels, the identifying of the pixels performed using one or more parameters including a size of the faces and a relative exposure of the faces.

16. The digital image acquisition device of claim 15 wherein the method further comprises an initial step of performing the auto focus on the entire the image.

17. The digital image acquisition device of claim 15 wherein the auto focusing mechanism and the method of perfecting the auto focus mechanism automatically adjust one or more properties of the adjustable optical system.

18. The digital image acquisition device of claim 15 A method of manually removing one or more detected faces as recited in claim 5, the method being performed by an interactive visual method.

19. The digital image acquisition device of claim 15, wherein performing the auto focus on the plurality of groups includes calculating a weighted average on the individual objects of the groups.

20. The digital image acquisition device of claim 15, the face pixels identifying being performed using a relative value as to an estimated importance of the detected regions.