Analyzing partial face regions for red-eye detection in acquired digital images

• US 8,265,388 B2
• Filed: 09/25/2011
• Issued: 09/11/2012
• Est. Priority Date: 10/28/2004
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Nanu, Florin, Steinberg, Eran, Corcoran, Peter, Pososin, Alexei, Bigioi, Petronel, Drimbarean, Alexandru, Petrescu, Stefan, Gangea, Mihnea, Capata, Adrian, Ciuc, Mihai, Zamfir, Adrian
• Primary Examiner(s): Do, Anh Hong
• Application Number:
  US13/244,658
• Publication Number:
  US 20120014600A1
• Time in Patent Office: 352 Days
• Field of Search: 382/103, 382/117, 382/164, 382/165, 382/167, 382/275, 345/589, 345/593, 358/522, 358/515, 715/243, 348/453, 707/796, 707/915
• US Class Current: 382/167
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30216 Redeye defect
• 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 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611
• CPC Class Codes: H04N 23/56 provided with illuminating means
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

A method for red-eye detection in an acquired digital image includes acquiring a first image, and analyzing one or more partial face regions within the first image. One or more characteristics of the first image are determined. One or more corrective processes are identified including red eye correction that can be beneficially applied to the first image according to the one or more characteristics. The one or more corrective processes are applied to the first image.

Claims

1. A method for red-eye detection in an acquired digital image comprising:

acquiring a first image with a portable processor-based device having a processor and an image acquisition component including a lens and an image sensor;

using the processor;

analyzing one or more partial face regions within the first image, including segmenting two or more regions of at least one eye and determining one or more characteristics of the first image;

identifying one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

applying said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction; and

electronically storing, transmitting, further processing or editing, or displaying the corrected image, or combinations thereof.

2. The method of claim 1, further comprising detecting and correcting a non-red flash-induced eye defect in the eye region.

3. The method of claim 1, wherein said applying comprises applying a chain of two or more filters to said first image including an iris color correction filter and a red eye defect filter.

4. The method of claim 1, wherein said analyzing is performed in part on a full resolution partial face region and in part on a subsample resolution of at least one different partial face region.

5. The method of claim 1, wherein said first image comprises a sub-sampled copy of an acquired image.

6. The method of claim 1, wherein the analyzing comprises recognizing one or more faces or types of faces, or both, within the first image.

7. The method of claim 1, wherein the applying comprises applying an iris color correction filter, including:

applying a pixel locator and segmentor;

applying a shape analyzer;

applying a falsing analyzer;

or

applying a pixel modifier, or combinations thereof.

8. The method of claim 1, wherein the one or more corrective processes comprises a color space transformation.

13. One or more non-transitory computer-readable media having digital code embedded therein for programming a processor to perform a method for iris color correction in an acquired digital image, wherein the method comprises any of the methods recited at claims 1-8 comprising:

a first code subset that is configured to program the processor to analyze one or more full face regions within the first image, including a second code subset configured to segment two or more regions of at least one eye and determining one or more characteristics of the first image;

a third code subset that is configured to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

a fourth code subset that is configured to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.

14. One or more non-transitory computer-readable media having digital code embedded therein for programming a processor to perform a method for iris color correction in an acquired digital image, wherein the method comprises any of the methods recited at claims 1-8 comprising:

a first code subset that is configured to program the processor to analyze one or more full face regions and one or more partial face regions within the first image, including a second code subset configured to segment two or more regions of at least one eye and determining one or more characteristics of the first image;

a third code subset that is configured to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

a fourth code subset that is configured to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.

9. One or more non-transitory computer-readable media having digital code embedded therein for programming a processor to perform a method for iris color correction in an acquired digital image, comprising:

a first code subset that is configured to program the processor to analyze one or more partial face regions within the first image, including a second code subset configured to segment two or more regions of at least one eye and determining one or more characteristics of the first image;

a third code subset that is configured to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

a fourth code subset that is configured to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.

10. A portable processor-based device, comprising:

an image acquisition component configured to capture digital images, including

a lens,

an image sensor, and

a processor programmed by digital code embedded in one or more processor-readable media to perform iris-color correction in an acquired digital image,

wherein the device is configured to acquire a first image using the image acquisition component including the lens and the image sensor; and

wherein the processor is programmed to analyze one or more partial face regions within the first image, and to segment two or more regions of at least one eye and determining one or more characteristics of the first image; and

wherein the processor is further programmed to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

wherein the processor is further programmed to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.

11. A method for red-eye detection in an acquired digital image comprising:

acquiring a first image with a portable processor-based device having a processor and an image acquisition component including a lens and an image sensor;

using the processor;

analyzing one or more full face regions within the first image, including segmenting two or more regions of at least one eye and determining one or more characteristics of the first image;

identifying one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

applying said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction; and

electronically storing, transmitting, further processing or editing, or displaying the corrected image, or combinations thereof.

12. A method for red-eye detection in an acquired digital image comprising:

acquiring a first image with a portable processor-based device having a processor and an image acquisition component including a lens and an image sensor;

using the processor;

analyzing one or more full face regions and one or more partial face regions within the first image, including segmenting two or more regions of at least one eye and determining one or more characteristics of the first image;

identifying one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

applying said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction; and

electronically storing, transmitting, further processing or editing, or displaying the corrected image, or combinations thereof.

15. A portable processor-based device, comprising:

a lens, and

an image sensor for capturing digital images, and

a processor programmed to perform iris-color correction in an acquired digital image,

wherein the device is configured to acquire a first image using the image acquisition component including the lens and the image sensor; and

wherein the processor is programmed to analyze one or more full face regions within the first image, and to segment two or more regions of at least one eye and determining one or more characteristics of the first image; and

wherein the processor is further programmed to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

wherein the processor is further programmed to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.

16. A portable processor-based device, comprising:

a lens, and

an image sensor for capturing digital images, and

a processor programmed to perform iris-color correction in an acquired digital image,

wherein the device is configured to acquire a first image using the image acquisition component including the lens and the image sensor; and

wherein the processor is programmed to analyze one or more full face regions and one or more partial face regions within the first image, and to segment two or more regions of at least one eye and determining one or more characteristics of the first image; and

wherein the processor is further programmed to identify one or more corrective processes including red eye defect correction and iris color correction that can be beneficially applied to said first image according to said one or more characteristics; and

wherein the processor is further programmed to apply said one or more corrective processes to said first image to generate a corrected image, including said red eye defect correction and said iris color correction.