Detecting red eye filter and apparatus using meta-data

• US 8,648,938 B2
• Filed: 02/18/2013
• Issued: 02/11/2014
• Est. Priority Date: 10/09/1997
• Status: Expired due to Fees

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: DeLuca, Michael J., Prilutsky, Yury, Steinberg, Eran, Corcoran, Peter, Bigioi, Petronel, Pososin, Alexei
• Primary Examiner(s): GILES, NICHOLAS G
• Application Number:
  US13/769,812
• Publication Number:
  US 20130155298A1
• Time in Patent Office: 358 Days
• Field of Search: 348/241, 348/222.1, 348/370, 348/371, 348/78, 382/117, 382/274, 382/275, 396/158
• US Class Current: 348/241
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04N 1/6086 by scene illuminant, i.e. conditions at the time of picture capture, e.g. flash, optical filter used, evening, cloud, daylight, artificial lighting, white point measurement, colour temperature
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611
• CPC Class Codes: H04N 23/74 by influencing the scene brightness using illuminating means
• CPC Class Codes: H04N 23/81 for suppressing or minimising disturbance in the image signal generation
• CPC Class Codes: H04N 25/60 Noise processing, e.g. detecting, correcting, reducing or removing noise

Abstract

A method of filtering a red-eye phenomenon from an acquired digital image including a multiplicity of pixels indicative of color, the pixels forming various shapes of the image, includes analyzing meta-data information, determining one or more regions within the digital image suspected as including red eye artifact, and determining, based at least in part on the meta-data analysis, whether the regions are actual red eye artifact. The meta-data information may include information describing conditions under which the image was acquired, captured and/or digitized, acquisition device-specific information, and film information.

Claims

1. A method of detecting and correcting an eye defect within a digital image that has been acquired with a cell phone equipped with a digital camera and that comprises a multiplicity of pixels indicative of luminance and color, the multiplicity of pixels forming various shapes within the image, the method comprising:

acquiring with said cell phone equipped with said digital camera said digital image including said multiplicity of pixels indicative of luminance and color;

detecting a candidate eye defect region based on color or shape or both within the digital image;

analyzing meta-data information including image acquisition device-specific information including image acquisition device-specific information, including f-stop, aperture, exposure, gain, white balance or color transformation, or focusing distance information at a time of acquisition, or combinations thereof;

analyzing anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof;

utilizing said meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and

filtering said candidate eye defect region from the digital image.

2. The method of claim 1, further comprising analyzing pixel information within one or more regions suspected as including an eye defect based on said meta-data analysis, and determining whether any of said one or more suspected regions continue to be suspected as including the eye defect based on said pixel analysis.

3. The method of claim 1, said filtering being executed at least partially within said cell phone equipped with said digital camera.

4. The method of claim 1, said filtering being executed entirely within said cell phone equipped with said digital camera.

5. The method of claim 1, said determining operation including a probability determination process based upon a plurality of criteria.

6. The method of claim 1, further comprising adjusting a pixel color within regions wherein an eye defect is suspected, and outputting an adjusted image to a printer.

7. The method of claim 1, said meta-data information comprising an indication of whether a flash was used when the image was acquired.

8. The method of claim 1, wherein the focusing distance information at the time of acquisition comprises distance information as recorded by an auto-focus mechanism of said cell phone equipped with said digital camera.

9. A cell phone equipped with a digital camera, comprising:

optics and a sensor for acquiring digital images,

a processor and

a red eye filter configured to detect a candidate eye defect region based on color or shape or both within a digital image acquired by said cell phone; and

wherein the red eye filter is configured to analyze meta-data information including image acquisition device-specific information including f-stop, aperture, exposure, gain, white balance, color transformation, focusing distance information at a time of acquisition, or combinations thereof; and

wherein the red eye filter is further configured to analyze anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof; and

wherein said red eye filter is further configured to utilize said meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and

to filter said candidate eye defect region from the digital image.

10. The cell phone of claim 9, wherein the method further comprises analyzing pixel information within one or more regions suspected as including an eye defect based on said meta-data analysis, and determining whether any of said one or more suspected regions continue to be suspected as including the eye defect based on said pixel analysis.

11. The cell phone of claim 9, said filtering being executed at least partially within said cell phone equipped with said digital camera.

12. The cell phone of claim 9, said filtering being executed entirely within said cell phone equipped with said digital camera.

13. The cell phone of claim 9, said determining operation including a probability determination process based upon a plurality of criteria.

14. The cell phone of claim 9, wherein the method further comprises adjusting a pixel color within regions wherein an eye defect is suspected, and outputting an adjusted image to an external device.

15. The cell phone of claim 9, said meta-data information comprising an indication of whether a flash was used when the image was acquired.

16. The cell phone of claim 9, wherein the focusing distance information at the time of acquisition comprises distance information as recorded by an auto-focus mechanism of said cell phone equipped with said digital camera.

17. One or more non-transitory media configured to perform on a cell phone equipped with a digital camera a method of detecting and correcting an eye defect within a digital image that was acquired with said cell phone equipped with said digital camera and that comprises a multiplicity of pixels indicative of luminance and color, the multiplicity of pixels forming various shapes within the image, wherein the method comprises:

detecting a candidate eye defect region based on color or shape or both within said digital image acquired with said cell phone equipped with said digital camera;

analyzing meta-data information including image acquisition device-specific information, including f-stop, aperture, exposure, gain, white balance, color transformation, or focusing distance information at a time of acquisition, or combinations thereof;

analyzing anthropometric information including statistics relating to at least one relationship between said focusing distance information at the time of acquisition and a location of a second detected eye, lips, nostrils or a surrounding face, or combinations thereof;

utilizing meta-data information and anthropometric information to determine whether said candidate eye defect region is suspected as including an eye defect region; and

filtering said candidate eye defect region from the digital image.

18. The one or more media of claim 17, wherein the method further comprises analyzing pixel information within one or more regions suspected as including an eye defect based on said meta-data analysis, and determining whether any of said one or more suspected regions continue to be suspected as including the eye defect based on said pixel analysis.

19. The one or more media of claim 17, said filtering being executed at least partially within said cell phone equipped with said digital camera.

20. The one or more media of claim 17, said filtering being executed entirely within said cell phone equipped with said digital camera.

21. The one or more media of claim 17, said determining operation including a probability determination process based upon a plurality of criteria.

22. The one or more media of claim 17, wherein the method further comprises adjusting a pixel color within regions wherein an eye defect is suspected, and outputting an adjusted image to an external device.

23. The one or more media of claim 17, said meta-data information comprising an indication of whether a flash was used when the image was acquired.

24. The one or more media of claim 17, wherein the focusing distance information at the time of acquisition comprises distance information as recorded by an auto-focus mechanism of said cell phone equipped with said digital camera.