Method for processing digital photographic image data that includes a method for the automatic detection of red-eye defects

• US 20030044063A1
• Filed: 07/09/2002
• Published: 03/06/2003
• Est. Priority Date: 09/03/2001
• Status: Abandoned Application

• Current Assignee: Agfaphoto GmbH (Agfaphoto Holding GmbH)
• Original Assignee: Agfaphoto GmbH (Agfaphoto Holding GmbH)
• Inventors: Hartmann, Klaus, Meckes, Guenter, Schuhrke, Thomas, Taresch, Gudrun, Oberhardt, Knut, Damm, Tobias, Fuersich, Manfred
• Application Number:
  US10/192,713
• Publication Number:
  US 20030044063A1
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06T 2207/30216 Redeye defect
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611

Abstract

A method for processing digital photographic image data includes a method for the automatic detection of red-eye defects. Before the image data are subjected to an elaborate process for the detection of red-eye defects, exclusion criteria are analyzed in the course of an exclusion process, whereby the criteria provide the information to definitively rule out the occurrence of red-eye defects. The red-eye detection process is not carried out if such exclusion criteria are fulfilled.

Claims

1. In a method for processing digital photographic image data, where a method for the automatic detection of red-eye defects is applied to the image data, the improvement comprising the step of analyzing at least one exclusion criterion prior to the application of the method for the detection of red-eye defects, said exclusion criterion possibly including information which, if present, definitively rules out the occurrence of red-eye defects;

and terminating the method for the detection of red-eye defects if said information is present.

2. Method as set forth in claim 1, wherein said at least one exclusion criterion is analyzed using auxiliary film data.

3. Method as set forth in claim 1, wherein the presence of flash markers in the recording data is an exclusion criterion, and wherein said exclusion criterion is analyzed to determine whether no flash was used when creating the photographic image data.

4. Method as set forth in claim 1, wherein the presence of a black and white photograph is an exclusion criterion.

5. Method as set forth in claim 1, wherein said analysis of at least one exclusion criterion is operative on a reduced image data set as compared to a data set used for detecting red-eye defects.

6. Method as set forth in claim 5, wherein said reduced image data set is a low-resolution image data set.

7. Method as set forth in claim 6, further comprising the step of pre-scanning, in low resolution, a film containing the image data.

8. Method as set forth in claim 6, wherein said image data are present in digital form and further comprising the step of reducing the resolution of said image data.

9. Method as set forth in claim 5, wherein the resolution reduction step includes the step of generating a gray scale image of the image data.

10. Method as set forth in claim 1, wherein a plurality of exclusion criteria are analyzed independently of one another.

11. Method as set forth in claim 10, wherein a plurality of exclusion criterion are analyzed simultaneously with one another.

12. Method as set forth in claim 10, wherein the results of the analyses of a plurality of exclusion criterion are combined to provide an overall evaluation.

13. Method as set forth in claim 1, wherein the absence of a flash photograph is an exclusion criterion, and wherein the step of analyzing the exclusion criterion includes determining whether the dominant light source for a photographic image is other than a camera flash.

14. Method as set forth in claim 13, wherein said analysis step includes the step of detecting an artificial light photograph, thereby to determine that an artificial light source was the dominant light source when the photograph was created.

15. Method as set forth in claim 13, wherein said analyzing step includes the step of detecting a photograph low in contrast, thereby to determine that no flash has been used.

16. Method as set forth in claim 1, wherein a significant drop of Fourier transformed signals of the image data is an exclusion criterion.

17. Method as set forth in claim 1, wherein the absence of large skin tone areas is an exclusion criterion.