Method and Apparatus for Detection and Correction of Multiple Image Defects Within Digital Images Using Preview or Other Reference Images

• US 20110221936A1
• Filed: 05/23/2011
• Published: 09/15/2011
• Est. Priority Date: 10/28/2004
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: Tessera Technologies Ireland Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Zamfir, Adrian, Nanu, Florin, Drimbarean, Alexandru, Bigioi, Petronel, Corcoran, Peter
• Granted Patent: US 8,135,184 B2
• Time in Patent Office: Days
• US Class Current: 348/241
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 2207/20008 Globally adaptive
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A method for red-eye detection in an acquired digital image acquiring one or more preview or other reference images without a flash. Any red regions that exist within the one or more reference images are determined. A main image is acquired with a flash of approximately a same scene as the one or more reference images. The main image is analyzed to determine any candidate red eye defect regions that exist within the main image. Any red regions determined to exist within the one or more reference images are compared with any candidate red eye defect regions determined to exist within the main image. Any candidate red eye defect regions within the main image corresponding to red regions determined also to exist within the one or more reference images are removed as candidate red eye defect regions.

Claims

1. A portable image acquisition and processing device which automatically detects and corrects face region defects within digital images, comprising a processor, image sensor and lens to acquire digital images, and a memory having code embedded therein for programming the processor to perform a multiple image defect detection and correction method that comprises:

using the processor, image sensor and lens to acquire and process a main digital image;

applying an analysis filter to one or more preview or other reference images of approximately a same scene as said main digital image;

interpreting results of the applying said analysis filter;

determining an optimal correction strategy for application to the main digital image based on the interpreting;

determining an optimal combination of corrective image processing and filter adaptation based on the strategy; and

correcting multiple image defects based on said applying said analysis filter in accordance with said optimal combination, including detecting and correcting one or more defects within a specific region of interest within said digital image.

2. The device of claim 1, wherein the method further comprises:

obtaining a subsampled version of the main digital image;

detecting an image defect within said subsampled version of said digital image; and

correcting a corresponding image defect within said digital image.

3. The device of claim 2, wherein the subsampled version of the main digital image comprises a different resolution than the main digital image.

4. The device of claim 2, wherein the subsampled version of the main digital image comprises a same resolution as the main digital image.

5. The device of claim 2, wherein the obtaining said subsampled version of the main digital image comprises subsampling luminance and chrominance data.

6. The device of claim 1, wherein the analysis filter comprises an analysis prefilter applied before detecting said specific region of interest.

7. The device of claim 1, wherein said correcting said multiple image defects is performed prior to detecting said specific region of interest.

8. One or more processor-readable media having code embedded therein for programming a processor to perform a multiple image defect detection and correction method that comprises:

applying an analysis filter to one or more preview or other reference images of approximately a same scene as a main digital image;

interpreting results of the applying said analysis filter;

determining an optimal correction strategy for application to the main digital image based on the interpreting;

determining an optimal combination of corrective image processing and filter adaptation based on the strategy; and

correcting multiple image defects based on said applying said analysis filter in accordance with said optimal combination, including detecting and correcting one or more defects within a specific region of interest within said digital image.

9. The one or more processor-readable media of claim 8, wherein the method further comprises:

obtaining a subsampled version of the main digital image;

detecting an image defect within said subsampled version of said digital image; and

correcting a corresponding image defect within said digital image.

10. The one or more processor-readable media of claim 9, wherein the subsampled version of the main digital image comprises a different resolution than the main digital image.

11. The one or more processor-readable media of claim 9, wherein the subsampled version of the main digital image comprises a same resolution as the main digital image.

12. The one or more processor-readable media of claim 9, wherein the obtaining said subsampled version of the main digital image comprises subsampling luminance and chrominance data.

13. The one or more processor-readable media of claim 8, wherein the analysis filter comprises an analysis prefilter applied before detecting said specific region of interest.

14. The one or more processor-readable media of claim 8, wherein said correcting said multiple image defects is performed prior to detecting said specific region of interest.

15. A method of detecting and correcting multiple image defects within a digital image, comprising:

using the processor, image sensor and lens to acquire and process a main digital image;

applying an analysis filter to one or more preview or other reference images of approximately a same scene as a main digital image;

interpreting results of the applying said analysis filter;

determining an optimal correction strategy for application to the main digital image based on the interpreting;

determining an optimal combination of corrective image processing and filter adaptation based on the strategy; and

correcting multiple image defects based on said applying said analysis filter in accordance with said optimal combination, including detecting and correcting one or more defects within a specific region of interest within said main digital image.

16. The method of claim 15, further comprising:

obtaining a subsampled version of the main digital image;

detecting an image defect within said subsampled version of said digital image; and

correcting a corresponding image defect within said digital image.

17. The method of claim 16, wherein the subsampled version of the main digital image comprises a different resolution than the main digital image.

18. The method of claim 16, wherein the subsampled version of the main digital image comprises a same resolution as the main digital image.

19. The method of claim 16, wherein the obtaining said subsampled version of the main digital image comprises subsampling luminance and chrominance data.

20. The method of claim 15, wherein the analysis filter comprises an analysis prefilter applied before detecting said specific region of interest.

21. The method of claim 15, wherein said correcting said multiple image defects is performed prior to detecting said specific region of interest.